[
  {
    "id": "swarm_intelligence_coordinator_lab.py",
    "name": "Swarm Intelligence Coordinator",
    "description": "Swarm Intelligence Coordinator\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "nanotechnology_lab.py",
    "name": "Nanotechnology",
    "description": "Nanomaterial design and simulation",
    "capabilities": [
      {
        "tool_name": "simulate_nanoparticle_synthesis",
        "args": [
          "size_nm",
          "temperature_c"
        ],
        "doc": "Simulate nanoparticle synthesis"
      },
      {
        "tool_name": "calculate_surface_properties",
        "args": [
          "diameter_nm"
        ],
        "doc": "Calculate surface area and properties"
      },
      {
        "tool_name": "predict_quantum_confinement",
        "args": [
          "size_nm",
          "material"
        ],
        "doc": "Predict quantum confinement effects"
      }
    ]
  },
  {
    "id": "biomedical_engineering_lab.py",
    "name": "Biomedical Engineering",
    "description": "Comprehensive biomedical engineering calculations including:\n- Biomechanics calculations\n- Drug delivery modeling\n- Medical device analysis\n- Tissue engineering parameters\n- Biosignal processing\n- Implant design criteria",
    "capabilities": [
      {
        "tool_name": "stress_strain_bone",
        "args": [
          "stress",
          "strain_rate"
        ],
        "doc": "Calculate bone mechanical response with viscoelastic effects\n\nArgs:\n    stress: Applied stress in Pa\n    strain_rate: Strain rate in 1/s\n\nReturns:\n    Dictionary with strain, safety factor, and viscoelastic modulus"
      },
      {
        "tool_name": "wolff_law_remodeling",
        "args": [
          "strain",
          "time_days"
        ],
        "doc": "Calculate bone remodeling response using Wolff's Law\n\nArgs:\n    strain: Mechanical strain (dimensionless)\n    time_days: Time period in days\n\nReturns:\n    Bone density change as fraction"
      },
      {
        "tool_name": "joint_force_analysis",
        "args": [
          "body_weight",
          "activity"
        ],
        "doc": "Calculate joint reaction forces for different activities\n\nArgs:\n    body_weight: Body weight in N\n    activity: Type of activity ('standing', 'walking', 'running', 'jumping')\n\nReturns:\n    Dictionary with joint forces for hip, knee, and ankle"
      },
      {
        "tool_name": "muscle_force_length",
        "args": [
          "length_ratio"
        ],
        "doc": "Calculate muscle force using force-length relationship\n\nArgs:\n    length_ratio: Current length / optimal length\n\nReturns:\n    Force as fraction of maximum (0-1)"
      },
      {
        "tool_name": "hill_muscle_model",
        "args": [
          "velocity",
          "max_velocity",
          "max_force"
        ],
        "doc": "Calculate muscle force using Hill's muscle model\n\nArgs:\n    velocity: Contraction velocity in m/s (negative for shortening)\n    max_velocity: Maximum shortening velocity in m/s\n    max_force: Maximum isometric force in N\n\nReturns:\n    Force in N"
      },
      {
        "tool_name": "drug_diffusion_tissue",
        "args": [
          "concentration_surface",
          "distance",
          "time",
          "diffusivity"
        ],
        "doc": "Calculate drug concentration in tissue using Fick's law\n\nC(x,t) = C0 * erfc(x / (2*\u221a(D*t)))\n\nArgs:\n    concentration_surface: Surface concentration in mol/m\u00b3\n    distance: Distance from surface in meters\n    time: Time in seconds\n    diffusivity: Diffusion coefficient in m\u00b2/s\n\nReturns:\n    Concentration at given distance and time in mol/m\u00b3"
      },
      {
        "tool_name": "compartment_model_pk",
        "args": [
          "dose",
          "volume",
          "clearance",
          "time",
          "ka"
        ],
        "doc": "Calculate drug concentration using one-compartment pharmacokinetic model\n\nArgs:\n    dose: Drug dose in mg\n    volume: Volume of distribution in L\n    clearance: Clearance rate in L/h\n    time: Time array in hours\n    ka: Absorption rate constant in 1/h (for oral administration)\n\nReturns:\n    Concentration array in mg/L"
      },
      {
        "tool_name": "drug_release_matrix",
        "args": [
          "initial_loading",
          "diffusivity",
          "matrix_thickness",
          "time"
        ],
        "doc": "Calculate drug release from polymer matrix (Higuchi model)\n\nM_t = A * \u221a(D * (2C0 - Cs) * Cs * t)\n\nArgs:\n    initial_loading: Initial drug concentration in matrix (kg/m\u00b3)\n    diffusivity: Drug diffusivity in matrix (m\u00b2/s)\n    matrix_thickness: Matrix thickness in meters\n    time: Time array in seconds\n\nReturns:\n    Cumulative drug release array (fraction)"
      },
      {
        "tool_name": "michaelis_menten_kinetics",
        "args": [
          "substrate",
          "vmax",
          "km"
        ],
        "doc": "Calculate enzyme reaction rate using Michaelis-Menten kinetics\n\nv = Vmax * [S] / (Km + [S])\n\nArgs:\n    substrate: Substrate concentration in mol/L\n    vmax: Maximum reaction velocity in mol/(L\u00b7s)\n    km: Michaelis constant in mol/L\n\nReturns:\n    Reaction rate in mol/(L\u00b7s)"
      },
      {
        "tool_name": "oxygen_transport_krogh",
        "args": [
          "capillary_po2",
          "radius",
          "consumption_rate"
        ],
        "doc": "Calculate tissue oxygen tension using Krogh cylinder model\n\nArgs:\n    capillary_po2: Capillary oxygen partial pressure in Pa\n    radius: Distance from capillary center in meters\n    consumption_rate: Oxygen consumption rate in mol/(m\u00b3\u00b7s)\n\nReturns:\n    Tissue oxygen partial pressure in Pa"
      },
      {
        "tool_name": "blood_flow_resistance",
        "args": [
          "vessel_radius",
          "vessel_length",
          "viscosity",
          "flow_rate"
        ],
        "doc": "Calculate vascular resistance and pressure drop (Poiseuille's law)\n\nR = 8\u03bcL/(\u03c0r\u2074)\n\nArgs:\n    vessel_radius: Vessel radius in meters\n    vessel_length: Vessel length in meters\n    viscosity: Blood viscosity in Pa\u00b7s\n    flow_rate: Flow rate in m\u00b3/s\n\nReturns:\n    Dictionary with resistance and pressure drop"
      },
      {
        "tool_name": "wall_shear_stress",
        "args": [
          "flow_rate",
          "vessel_radius",
          "viscosity"
        ],
        "doc": "Calculate wall shear stress in blood vessel\n\n\u03c4_wall = 4\u03bcQ/(\u03c0r\u00b3)\n\nArgs:\n    flow_rate: Blood flow rate in m\u00b3/s\n    vessel_radius: Vessel radius in meters\n    viscosity: Blood viscosity in Pa\u00b7s\n\nReturns:\n    Wall shear stress in Pa"
      },
      {
        "tool_name": "windkessel_model",
        "args": [
          "pressure_in",
          "resistance",
          "compliance",
          "time_step"
        ],
        "doc": "Calculate arterial pressure using two-element Windkessel model\n\nArgs:\n    pressure_in: Input pressure array in Pa\n    resistance: Peripheral resistance in Pa\u00b7s/m\u00b3\n    compliance: Arterial compliance in m\u00b3/Pa\n    time_step: Time step in seconds\n\nReturns:\n    Output pressure array in Pa"
      },
      {
        "tool_name": "ecg_signal_features",
        "args": [
          "ecg_signal",
          "sampling_rate"
        ],
        "doc": "Extract features from ECG signal\n\nArgs:\n    ecg_signal: ECG signal array in mV\n    sampling_rate: Sampling frequency in Hz\n\nReturns:\n    Dictionary with heart rate, QRS duration, etc."
      },
      {
        "tool_name": "fourier_transform_biosignal",
        "args": [
          "signal",
          "sampling_rate"
        ],
        "doc": "Perform FFT on biosignal and extract frequency components\n\nArgs:\n    signal: Biosignal array\n    sampling_rate: Sampling frequency in Hz\n\nReturns:\n    Dictionary with frequencies and power spectrum"
      },
      {
        "tool_name": "filter_biosignal",
        "args": [
          "signal",
          "sampling_rate",
          "low_cutoff",
          "high_cutoff",
          "order"
        ],
        "doc": "Apply Butterworth filter to biosignal\n\nArgs:\n    signal: Input signal array\n    sampling_rate: Sampling frequency in Hz\n    low_cutoff: High-pass cutoff frequency in Hz\n    high_cutoff: Low-pass cutoff frequency in Hz\n    order: Filter order\n\nReturns:\n    Filtered signal array"
      },
      {
        "tool_name": "implant_stress_shielding",
        "args": [
          "implant_modulus",
          "bone_modulus"
        ],
        "doc": "Calculate stress shielding factor for orthopedic implant\n\nArgs:\n    implant_modulus: Implant Young's modulus in Pa\n    bone_modulus: Bone Young's modulus in Pa\n\nReturns:\n    Stress shielding factor (0=no shielding, 1=complete shielding)"
      },
      {
        "tool_name": "biocompatibility_index",
        "args": [
          "cytotoxicity",
          "protein_adsorption",
          "cell_adhesion",
          "inflammatory_response"
        ],
        "doc": "Calculate overall biocompatibility index (0-100)\n\nArgs:\n    cytotoxicity: Cell viability (0-1, 1=no toxicity)\n    protein_adsorption: Protein binding (0-1, optimal ~0.5)\n    cell_adhesion: Cell attachment (0-1, 1=excellent)\n    inflammatory_response: Inflammation (0-1, 0=no inflammation)\n\nReturns:\n    Biocompatibility index (0-100)"
      },
      {
        "tool_name": "tissue_scaffold_porosity",
        "args": [
          "pore_size",
          "scaffold_thickness",
          "diffusion_required"
        ],
        "doc": "Calculate optimal scaffold porosity for tissue engineering\n\nArgs:\n    pore_size: Average pore diameter in meters\n    scaffold_thickness: Scaffold thickness in meters\n    diffusion_required: Required nutrient diffusion rate in m\u00b2/s\n\nReturns:\n    Dictionary with porosity, permeability, and cell capacity"
      },
      {
        "tool_name": "cell_growth_logistic",
        "args": [
          "initial_cells",
          "growth_rate",
          "carrying_capacity",
          "time"
        ],
        "doc": "Model cell population growth using logistic equation\n\nN(t) = K / (1 + ((K-N0)/N0) * exp(-rt))\n\nArgs:\n    initial_cells: Initial cell count\n    growth_rate: Growth rate constant in 1/day\n    carrying_capacity: Maximum cell count\n    time: Time array in days\n\nReturns:\n    Cell count array"
      },
      {
        "tool_name": "bioreactor_oxygen_transfer",
        "args": [
          "flow_rate",
          "volume",
          "kla",
          "oxygen_saturation",
          "consumption_rate"
        ],
        "doc": "Calculate steady-state oxygen concentration in bioreactor\n\nArgs:\n    flow_rate: Gas flow rate in L/min\n    volume: Bioreactor volume in L\n    kla: Oxygen transfer coefficient in 1/h\n    oxygen_saturation: Saturation concentration in mg/L\n    consumption_rate: Cell oxygen consumption in mg/(L\u00b7h)\n\nReturns:\n    Steady-state dissolved oxygen in mg/L"
      }
    ]
  },
  {
    "id": "cryptography_lab.py",
    "name": "Cryptography",
    "description": "Comprehensive cryptography laboratory with modern encryption algorithms",
    "capabilities": [
      {
        "tool_name": "is_prime",
        "args": [
          "n",
          "k"
        ],
        "doc": "Miller-Rabin primality test\nTime: O(k log\u00b3 n)"
      },
      {
        "tool_name": "generate_prime",
        "args": [
          "bits"
        ],
        "doc": "Generate a prime number with specified bit length"
      },
      {
        "tool_name": "extended_gcd",
        "args": [
          "a",
          "b"
        ],
        "doc": "Extended Euclidean algorithm\nReturns (gcd, x, y) such that ax + by = gcd(a, b)"
      },
      {
        "tool_name": "mod_inverse",
        "args": [
          "a",
          "m"
        ],
        "doc": "Find modular multiplicative inverse of a mod m"
      },
      {
        "tool_name": "generate_rsa_keypair",
        "args": [
          "key_size"
        ],
        "doc": "Generate RSA public/private key pair\nTime: O(n\u00b3) where n is key size in bits"
      },
      {
        "tool_name": "rsa_encrypt",
        "args": [
          "message",
          "key"
        ],
        "doc": "Encrypt message using RSA public key"
      },
      {
        "tool_name": "rsa_decrypt",
        "args": [
          "ciphertext",
          "key"
        ],
        "doc": "Decrypt ciphertext using RSA private key"
      },
      {
        "tool_name": "rsa_sign",
        "args": [
          "message_hash",
          "key"
        ],
        "doc": "Create RSA signature of message hash"
      },
      {
        "tool_name": "rsa_verify",
        "args": [
          "message_hash",
          "signature",
          "key"
        ],
        "doc": "Verify RSA signature"
      },
      {
        "tool_name": "aes_key_expansion",
        "args": [
          "key"
        ],
        "doc": "Expand AES key for all rounds\nSupports 128, 192, 256-bit keys"
      },
      {
        "tool_name": "aes_encrypt_block",
        "args": [
          "block",
          "expanded_key"
        ],
        "doc": "Encrypt single AES block (simplified version for demonstration)\nReal implementation would include MixColumns, ShiftRows"
      },
      {
        "tool_name": "aes_cbc_encrypt",
        "args": [
          "plaintext",
          "key",
          "iv"
        ],
        "doc": "AES-CBC mode encryption\nAdds PKCS7 padding"
      },
      {
        "tool_name": "sha256",
        "args": [
          "data"
        ],
        "doc": "SHA-256 hash function\nReturns 256-bit hash"
      },
      {
        "tool_name": "sha3_256",
        "args": [
          "data"
        ],
        "doc": "SHA3-256 hash function (Keccak)\nMore resistant to length extension attacks"
      },
      {
        "tool_name": "blake2b",
        "args": [
          "data",
          "key"
        ],
        "doc": "BLAKE2b hash function\nFaster than SHA-2, as secure as SHA-3"
      },
      {
        "tool_name": "hmac_sha256",
        "args": [
          "key",
          "message"
        ],
        "doc": "HMAC-SHA256 for message authentication\nProvides integrity and authenticity"
      },
      {
        "tool_name": "pbkdf2",
        "args": [
          "password",
          "salt",
          "iterations"
        ],
        "doc": "PBKDF2 key derivation function\nUsed for password hashing"
      },
      {
        "tool_name": "merkle_tree_root",
        "args": [
          "leaves"
        ],
        "doc": "Calculate Merkle tree root hash\nUsed in blockchain and distributed systems"
      },
      {
        "tool_name": "create_signature",
        "args": [
          "message",
          "private_key",
          "algorithm"
        ],
        "doc": "Create digital signature for message"
      },
      {
        "tool_name": "verify_signature",
        "args": [
          "message",
          "signature",
          "public_key"
        ],
        "doc": "Verify digital signature"
      },
      {
        "tool_name": "diffie_hellman_generate_params",
        "args": [
          "key_size"
        ],
        "doc": "Generate Diffie-Hellman parameters (prime p and generator g)"
      },
      {
        "tool_name": "diffie_hellman_generate_keypair",
        "args": [
          "p",
          "g"
        ],
        "doc": "Generate Diffie-Hellman key pair\nReturns (private_key, public_key)"
      },
      {
        "tool_name": "diffie_hellman_compute_shared",
        "args": [
          "other_public",
          "my_private",
          "p"
        ],
        "doc": "Compute shared secret in Diffie-Hellman"
      },
      {
        "tool_name": "elliptic_curve_add",
        "args": [
          "p1",
          "p2",
          "a",
          "p"
        ],
        "doc": "Add two points on elliptic curve y\u00b2 = x\u00b3 + ax + b (mod p)\nSimplified version for demonstration"
      },
      {
        "tool_name": "rc4",
        "args": [
          "key",
          "data"
        ],
        "doc": "RC4 stream cipher (for educational purposes only - not secure)"
      },
      {
        "tool_name": "chacha20_quarter_round",
        "args": [
          "a",
          "b",
          "c",
          "d"
        ],
        "doc": "ChaCha20 quarter round operation\nModern stream cipher by D. J. Bernstein"
      },
      {
        "tool_name": "generate_random_key",
        "args": [
          "size"
        ],
        "doc": "Generate cryptographically secure random key"
      },
      {
        "tool_name": "constant_time_compare",
        "args": [
          "a",
          "b"
        ],
        "doc": "Constant-time comparison to prevent timing attacks"
      },
      {
        "tool_name": "secure_erase",
        "args": [
          "data"
        ],
        "doc": "Securely erase sensitive data from memory\nNote: Python doesn't guarantee this works due to GC"
      }
    ]
  },
  {
    "id": "dijkstra_graph_shortest_path_lab.py",
    "name": "Dijkstra Graph Shortest Path",
    "description": "Dijkstra Graph Shortest Path\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "metabolomics_lab.py",
    "name": "Metabolomics",
    "description": "Metabolic profiling and pathway analysis",
    "capabilities": [
      {
        "tool_name": "analyze_metabolite_profile",
        "args": [
          "sample_data"
        ],
        "doc": "Analyze metabolite concentrations"
      },
      {
        "tool_name": "calculate_flux_balance",
        "args": [
          "pathway"
        ],
        "doc": "Calculate metabolic flux through pathway"
      },
      {
        "tool_name": "identify_biomarkers",
        "args": [
          "control",
          "disease"
        ],
        "doc": "Identify disease biomarkers"
      }
    ]
  },
  {
    "id": "synthetic_biology_lab.py",
    "name": "Synthetic Biology",
    "description": "Design and simulate genetic circuits",
    "capabilities": [
      {
        "tool_name": "design_genetic_circuit",
        "args": [
          "circuit_type"
        ],
        "doc": "Design genetic logic gates"
      },
      {
        "tool_name": "simulate_crispr_efficiency",
        "args": [
          "guide_sequence",
          "pam_type"
        ],
        "doc": "Calculate CRISPR-Cas9 cutting efficiency"
      },
      {
        "tool_name": "predict_metabolic_flux",
        "args": [
          "pathway_genes",
          "expression_levels"
        ],
        "doc": "Predict metabolic flux through engineered pathway"
      }
    ]
  },
  {
    "id": "high_frequency_trading_backtester_lab.py",
    "name": "High Frequency Trading Backtester",
    "description": "High-Frequency Trading Backtester\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "analytical_chemistry_lab.py",
    "name": "Analytical Chemistry",
    "description": "Production-ready analytical chemistry laboratory",
    "capabilities": [
      {
        "tool_name": "create_calibration_curve",
        "args": [
          "concentrations",
          "responses",
          "curve_type",
          "weighted"
        ],
        "doc": "Create and fit calibration curve"
      },
      {
        "tool_name": "calculate_lod_loq",
        "args": [
          "curve",
          "blank_responses"
        ],
        "doc": "Calculate limit of detection (LOD) and limit of quantification (LOQ)"
      },
      {
        "tool_name": "internal_standard_correction",
        "args": [
          "analyte_response",
          "istd_response",
          "istd_concentration"
        ],
        "doc": "Apply internal standard correction"
      },
      {
        "tool_name": "simulate_chromatogram",
        "args": [
          "compounds",
          "time_points",
          "mode"
        ],
        "doc": "Simulate a chromatogram with multiple peaks"
      },
      {
        "tool_name": "integrate_peak",
        "args": [
          "signal",
          "start_time",
          "end_time",
          "baseline_correction"
        ],
        "doc": "Integrate chromatographic peak area"
      },
      {
        "tool_name": "calculate_resolution",
        "args": [
          "peak1",
          "peak2"
        ],
        "doc": "Calculate chromatographic resolution between peaks"
      },
      {
        "tool_name": "calculate_theoretical_plates",
        "args": [
          "retention_time",
          "peak_width",
          "width_type"
        ],
        "doc": "Calculate number of theoretical plates"
      },
      {
        "tool_name": "van_deemter_equation",
        "args": [
          "flow_rate",
          "A",
          "B",
          "C"
        ],
        "doc": "Van Deemter equation for plate height"
      },
      {
        "tool_name": "simulate_mass_spectrum",
        "args": [
          "molecular_formula",
          "fragmentation_pattern"
        ],
        "doc": "Simulate a mass spectrum with isotope patterns"
      },
      {
        "tool_name": "calculate_exact_mass",
        "args": [
          "molecular_formula"
        ],
        "doc": "Calculate exact molecular mass"
      },
      {
        "tool_name": "mass_accuracy_ppm",
        "args": [
          "measured_mass",
          "exact_mass"
        ],
        "doc": "Calculate mass accuracy in ppm"
      },
      {
        "tool_name": "beer_lambert_law",
        "args": [
          "epsilon",
          "path_length",
          "concentration"
        ],
        "doc": "Calculate absorbance using Beer-Lambert law"
      },
      {
        "tool_name": "calculate_transmittance",
        "args": [
          "absorbance"
        ],
        "doc": "Convert absorbance to transmittance"
      },
      {
        "tool_name": "spectral_deconvolution",
        "args": [
          "signal",
          "n_components"
        ],
        "doc": "Deconvolute overlapping spectral peaks"
      },
      {
        "tool_name": "fluorescence_quantum_yield",
        "args": [
          "sample_area",
          "sample_absorbance",
          "reference_area",
          "reference_absorbance",
          "reference_qy",
          "n_sample",
          "n_reference"
        ],
        "doc": "Calculate fluorescence quantum yield"
      },
      {
        "tool_name": "calculate_method_precision",
        "args": [
          "replicate_measurements"
        ],
        "doc": "Calculate method precision statistics"
      },
      {
        "tool_name": "calculate_recovery",
        "args": [
          "measured",
          "expected"
        ],
        "doc": "Calculate analytical recovery percentage"
      },
      {
        "tool_name": "matrix_spike_recovery",
        "args": [
          "sample",
          "spiked_sample",
          "spike_amount"
        ],
        "doc": "Calculate matrix spike recovery"
      },
      {
        "tool_name": "calculate_linearity",
        "args": [
          "x",
          "y"
        ],
        "doc": "Assess linearity of analytical method"
      },
      {
        "tool_name": "method_detection_limit",
        "args": [
          "blank_measurements",
          "low_conc_measurements",
          "concentration"
        ],
        "doc": "Calculate method detection limit (MDL)"
      },
      {
        "tool_name": "signal_smoothing",
        "args": [
          "signal",
          "window_length",
          "polyorder"
        ],
        "doc": "Apply Savitzky-Golay filter for signal smoothing"
      },
      {
        "tool_name": "baseline_correction",
        "args": [
          "signal",
          "method"
        ],
        "doc": "Perform baseline correction"
      },
      {
        "tool_name": "peak_detection",
        "args": [
          "signal",
          "height_threshold",
          "prominence_threshold"
        ],
        "doc": "Detect and characterize peaks in signal"
      },
      {
        "tool_name": "calculate_signal_to_noise",
        "args": [
          "signal",
          "signal_region",
          "noise_region"
        ],
        "doc": "Calculate signal-to-noise ratio"
      },
      {
        "tool_name": "uncertainty_propagation",
        "args": [
          "values",
          "uncertainties",
          "operation"
        ],
        "doc": "Calculate propagated uncertainty for basic operations"
      }
    ]
  },
  {
    "id": "transfer_learning_feature_extractor_lab.py",
    "name": "Transfer Learning Feature Extractor",
    "description": "Transfer Learning Feature Extractor\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "environmental_engineering_lab.py",
    "name": "Environmental Engineering",
    "description": "Comprehensive environmental engineering laboratory\nImplements real-world treatment and assessment algorithms",
    "capabilities": [
      {
        "tool_name": "activated_sludge_design",
        "args": [
          "wastewater",
          "target_effluent_bod"
        ],
        "doc": "Design activated sludge treatment system using Monod kinetics\nBased on Lawrence-McCarty model"
      },
      {
        "tool_name": "calculate_aqi",
        "args": [
          "pollutant",
          "concentration",
          "averaging_period"
        ],
        "doc": "Calculate Air Quality Index (AQI) using EPA methodology"
      },
      {
        "tool_name": "soil_remediation_design",
        "args": [
          "contamination",
          "remediation_type"
        ],
        "doc": "Design soil remediation system based on contaminant characteristics\nSupports bioremediation, soil washing, and thermal desorption"
      },
      {
        "tool_name": "life_cycle_assessment",
        "args": [
          "process_name",
          "inputs",
          "outputs"
        ],
        "doc": "Perform simplified Life Cycle Assessment (LCA)\nCalculate environmental impacts using ReCiPe methodology"
      },
      {
        "tool_name": "trickling_filter_design",
        "args": [
          "wastewater",
          "filter_media"
        ],
        "doc": "Design trickling filter for secondary treatment\nUsing NRC equations and Eckenfelder model"
      },
      {
        "tool_name": "membrane_bioreactor_design",
        "args": [
          "wastewater"
        ],
        "doc": "Design Membrane Bioreactor (MBR) system\nCombines biological treatment with membrane filtration"
      },
      {
        "tool_name": "wetland_treatment_design",
        "args": [
          "wastewater",
          "wetland_type"
        ],
        "doc": "Design constructed wetland for wastewater treatment\nBased on first-order kinetics and EPA design manual"
      },
      {
        "tool_name": "anaerobic_digestion_design",
        "args": [
          "organic_waste"
        ],
        "doc": "Design anaerobic digestion system for organic waste treatment\nProduces biogas and digestate"
      }
    ]
  },
  {
    "id": "electrical_engineering_lab.py",
    "name": "Electrical Engineering",
    "description": "Comprehensive electrical engineering calculations including:\n- AC/DC circuit analysis\n- Filter design (Butterworth, Chebyshev, Elliptic)\n- Power calculations (real, reactive, apparent)\n- Control system stability analysis\n- Signal processing basics\n- Semiconductor modeling",
    "capabilities": [
      {
        "tool_name": "ohms_law",
        "args": [
          "voltage",
          "current",
          "resistance"
        ],
        "doc": "Calculate missing value using Ohm's Law: V = I * R\n\nArgs:\n    voltage: Voltage in volts\n    current: Current in amperes\n    resistance: Resistance in ohms\n\nReturns:\n    Dictionary with all three values"
      },
      {
        "tool_name": "series_resistance",
        "args": [
          "resistances"
        ],
        "doc": "Calculate total resistance of series resistors: R_total = R1 + R2 + ..."
      },
      {
        "tool_name": "parallel_resistance",
        "args": [
          "resistances"
        ],
        "doc": "Calculate total resistance of parallel resistors: 1/R_total = 1/R1 + 1/R2 + ..."
      },
      {
        "tool_name": "voltage_divider",
        "args": [
          "v_in",
          "r1",
          "r2"
        ],
        "doc": "Calculate output voltage of voltage divider: V_out = V_in * R2 / (R1 + R2)\n\nArgs:\n    v_in: Input voltage in volts\n    r1: First resistor (connected to V_in) in ohms\n    r2: Second resistor (connected to ground) in ohms\n\nReturns:\n    Output voltage in volts"
      },
      {
        "tool_name": "current_divider",
        "args": [
          "i_total",
          "r1",
          "r2"
        ],
        "doc": "Calculate branch currents in current divider\n\nArgs:\n    i_total: Total current in amperes\n    r1: First branch resistance in ohms\n    r2: Second branch resistance in ohms\n\nReturns:\n    Tuple of (i1, i2) branch currents"
      },
      {
        "tool_name": "ac_impedance",
        "args": [
          "resistance",
          "inductance",
          "capacitance",
          "frequency"
        ],
        "doc": "Calculate complex impedance: Z = R + j(XL - XC)\n\nArgs:\n    resistance: Resistance in ohms\n    inductance: Inductance in henries\n    capacitance: Capacitance in farads\n    frequency: Frequency in Hz (default: self.frequency)\n\nReturns:\n    Complex impedance in ohms"
      },
      {
        "tool_name": "ac_power",
        "args": [
          "voltage",
          "current",
          "phase_angle"
        ],
        "doc": "Calculate AC power components\n\nArgs:\n    voltage: RMS voltage in volts\n    current: RMS current in amperes\n    phase_angle: Phase angle in radians\n\nReturns:\n    Dictionary with real, reactive, apparent power and power factor"
      },
      {
        "tool_name": "three_phase_power",
        "args": [
          "voltage_line",
          "current_line",
          "phase_angle",
          "configuration"
        ],
        "doc": "Calculate three-phase power\n\nArgs:\n    voltage_line: Line voltage in volts\n    current_line: Line current in amperes\n    phase_angle: Phase angle in radians\n    configuration: 'wye' or 'delta'\n\nReturns:\n    Dictionary with power calculations"
      },
      {
        "tool_name": "rc_time_constant",
        "args": [
          "resistance",
          "capacitance"
        ],
        "doc": "Calculate RC circuit time constant: \u03c4 = R * C"
      },
      {
        "tool_name": "rl_time_constant",
        "args": [
          "resistance",
          "inductance"
        ],
        "doc": "Calculate RL circuit time constant: \u03c4 = L / R"
      },
      {
        "tool_name": "resonant_frequency",
        "args": [
          "inductance",
          "capacitance"
        ],
        "doc": "Calculate resonant frequency of LC circuit: f_0 = 1 / (2\u03c0\u221a(LC))\n\nArgs:\n    inductance: Inductance in henries\n    capacitance: Capacitance in farads\n\nReturns:\n    Resonant frequency in Hz"
      },
      {
        "tool_name": "quality_factor",
        "args": [
          "resistance",
          "inductance",
          "capacitance"
        ],
        "doc": "Calculate Q factor of RLC circuit: Q = (1/R) * \u221a(L/C)\n\nArgs:\n    resistance: Resistance in ohms\n    inductance: Inductance in henries\n    capacitance: Capacitance in farads\n\nReturns:\n    Quality factor (dimensionless)"
      },
      {
        "tool_name": "butterworth_filter",
        "args": [
          "order",
          "cutoff_freq",
          "filter_type"
        ],
        "doc": "Design Butterworth filter\n\nArgs:\n    order: Filter order\n    cutoff_freq: Cutoff frequency in Hz\n    filter_type: 'low', 'high', 'band', or 'stop'\n\nReturns:\n    Tuple of (numerator coefficients, denominator coefficients)"
      },
      {
        "tool_name": "transfer_function_poles_zeros",
        "args": [
          "numerator",
          "denominator"
        ],
        "doc": "Find poles and zeros of transfer function\n\nArgs:\n    numerator: Numerator polynomial coefficients\n    denominator: Denominator polynomial coefficients\n\nReturns:\n    Dictionary with poles, zeros, and stability status"
      },
      {
        "tool_name": "pid_controller",
        "args": [
          "error",
          "error_integral",
          "error_derivative",
          "kp",
          "ki",
          "kd"
        ],
        "doc": "Calculate PID controller output\n\nArgs:\n    error: Current error signal\n    error_integral: Integral of error over time\n    error_derivative: Derivative of error\n    kp: Proportional gain\n    ki: Integral gain\n    kd: Derivative gain\n\nReturns:\n    Controller output"
      },
      {
        "tool_name": "bode_plot_data",
        "args": [
          "numerator",
          "denominator",
          "frequencies"
        ],
        "doc": "Generate data for Bode plot\n\nArgs:\n    numerator: Transfer function numerator coefficients\n    denominator: Transfer function denominator coefficients\n    frequencies: Frequency array in Hz (default: logspace from 0.1 to 10kHz)\n\nReturns:\n    Dictionary with frequency, magnitude (dB), and phase (degrees)"
      },
      {
        "tool_name": "diode_current",
        "args": [
          "voltage",
          "saturation_current",
          "ideality_factor"
        ],
        "doc": "Calculate diode current using Shockley equation\n\nI = Is * (e^(V/(n*Vt)) - 1)\n\nArgs:\n    voltage: Applied voltage in volts\n    saturation_current: Saturation current in amperes\n    ideality_factor: Ideality factor (1-2)\n\nReturns:\n    Diode current in amperes"
      },
      {
        "tool_name": "transistor_amplifier",
        "args": [
          "vbe",
          "beta",
          "vcc",
          "rc",
          "re"
        ],
        "doc": "Calculate common-emitter amplifier parameters\n\nArgs:\n    vbe: Base-emitter voltage in volts\n    beta: Current gain (hFE)\n    vcc: Collector supply voltage in volts\n    rc: Collector resistance in ohms\n    re: Emitter resistance in ohms\n\nReturns:\n    Dictionary with amplifier parameters"
      },
      {
        "tool_name": "op_amp_gain",
        "args": [
          "rf",
          "r1",
          "config"
        ],
        "doc": "Calculate operational amplifier gain\n\nArgs:\n    rf: Feedback resistance in ohms\n    r1: Input resistance in ohms\n    config: 'inverting' or 'non_inverting'\n\nReturns:\n    Voltage gain"
      },
      {
        "tool_name": "transmission_line_impedance",
        "args": [
          "inductance_per_length",
          "capacitance_per_length"
        ],
        "doc": "Calculate characteristic impedance of transmission line\n\nZ0 = \u221a(L/C)\n\nArgs:\n    inductance_per_length: Inductance per unit length in H/m\n    capacitance_per_length: Capacitance per unit length in F/m\n\nReturns:\n    Characteristic impedance in ohms"
      },
      {
        "tool_name": "signal_to_noise_ratio",
        "args": [
          "signal_power",
          "noise_power"
        ],
        "doc": "Calculate signal-to-noise ratio in dB\n\nSNR = 10 * log10(P_signal / P_noise)\n\nArgs:\n    signal_power: Signal power in watts\n    noise_power: Noise power in watts\n\nReturns:\n    SNR in decibels"
      },
      {
        "tool_name": "fourier_series_coefficients",
        "args": [
          "signal_func",
          "period",
          "n_harmonics"
        ],
        "doc": "Calculate Fourier series coefficients\n\nArgs:\n    signal_func: Function representing the signal\n    period: Signal period in seconds\n    n_harmonics: Number of harmonics to calculate\n\nReturns:\n    Dictionary with DC component and harmonic coefficients"
      }
    ]
  },
  {
    "id": "astrobiology_lab.py",
    "name": "Astrobiology",
    "description": "Analyze conditions for life beyond Earth",
    "capabilities": [
      {
        "tool_name": "calculate_habitability_index",
        "args": [
          "planet_params"
        ],
        "doc": "Calculate planetary habitability index"
      },
      {
        "tool_name": "analyze_biosignatures",
        "args": [
          "spectrum",
          "wavelengths"
        ],
        "doc": "Detect potential biosignatures in atmospheric spectrum"
      },
      {
        "tool_name": "estimate_drake_equation",
        "args": [
          "custom_params"
        ],
        "doc": "Calculate Drake equation for number of communicating civilizations"
      }
    ]
  },
  {
    "id": "virology_lab.py",
    "name": "Virology",
    "description": "Advanced virology simulation and analysis",
    "capabilities": [
      {
        "tool_name": "simulate_viral_replication",
        "args": [
          "initial_load",
          "time_hours"
        ],
        "doc": "Simulate viral replication dynamics"
      },
      {
        "tool_name": "predict_mutations",
        "args": [
          "genome_length",
          "generations"
        ],
        "doc": "Predict mutation accumulation"
      },
      {
        "tool_name": "analyze_antiviral_efficacy",
        "args": [
          "drug_concentration"
        ],
        "doc": "Calculate antiviral drug efficacy"
      }
    ]
  },
  {
    "id": "carbon_capture_lab.py",
    "name": "Carbon Capture",
    "description": "Comprehensive carbon capture laboratory\nImplements real-world capture, utilization, and storage (CCUS) models",
    "capabilities": [
      {
        "tool_name": "langmuir_isotherm",
        "args": [
          "pressure",
          "temperature",
          "q_max",
          "b0",
          "delta_h"
        ],
        "doc": "Langmuir adsorption isotherm for CO2\nq = q_max * b * P / (1 + b * P)\nwhere b = b0 * exp(-\u0394H/RT)"
      },
      {
        "tool_name": "freundlich_isotherm",
        "args": [
          "pressure",
          "temperature",
          "k_f",
          "n"
        ],
        "doc": "Freundlich adsorption isotherm\nq = k_f * P^(1/n)\nEmpirical model for heterogeneous surfaces"
      },
      {
        "tool_name": "dual_site_langmuir",
        "args": [
          "pressure",
          "temperature",
          "q_max1",
          "b01",
          "delta_h1",
          "q_max2",
          "b02",
          "delta_h2"
        ],
        "doc": "Dual-site Langmuir model for heterogeneous adsorbents\nq = q_max1 * b1 * P / (1 + b1 * P) + q_max2 * b2 * P / (1 + b2 * P)"
      },
      {
        "tool_name": "membrane_separation",
        "args": [
          "gas_stream",
          "membrane_type",
          "membrane_area"
        ],
        "doc": "Gas separation using membrane technology\nBased on solution-diffusion mechanism"
      },
      {
        "tool_name": "direct_air_capture",
        "args": [
          "air_temperature",
          "air_humidity",
          "capture_material"
        ],
        "doc": "Direct Air Capture (DAC) system model\nBased on adsorption/desorption cycles"
      },
      {
        "tool_name": "geological_storage_capacity",
        "args": [
          "storage_type",
          "formation_properties"
        ],
        "doc": "Calculate CO2 storage capacity for geological formations\nBased on volumetric and solubility trapping mechanisms"
      },
      {
        "tool_name": "pressure_swing_adsorption",
        "args": [
          "gas_stream",
          "adsorbent",
          "n_beds"
        ],
        "doc": "Pressure Swing Adsorption (PSA) cycle model\nFor high-purity CO2 separation"
      },
      {
        "tool_name": "amine_scrubbing",
        "args": [
          "gas_stream",
          "amine_type"
        ],
        "doc": "Amine-based chemical absorption\nMost mature technology for post-combustion capture"
      },
      {
        "tool_name": "breakthrough_curve",
        "args": [
          "bed_length",
          "velocity",
          "co2_concentration",
          "time_points"
        ],
        "doc": "Calculate breakthrough curve for fixed-bed adsorption\nUsing Linear Driving Force (LDF) model"
      }
    ]
  },
  {
    "id": "electromagnetism_lab.py",
    "name": "Electromagnetism",
    "description": "",
    "capabilities": [
      {
        "tool_name": "setup_conductor",
        "args": [
          "conductivity_value"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "calculate_magnetic_flux_density_for_current_sheet",
        "args": [
          "current_per_unit_length",
          "distance_from_sheet",
          "conductor"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "calculate_electric_field_strength_at_boundary",
        "args": [
          "voltage_diff",
          "distance_between_boundaries",
          "conductor"
        ],
        "doc": "No description available."
      }
    ]
  },
  {
    "id": "inorganic_chemistry_lab.py",
    "name": "Inorganic Chemistry",
    "description": "Production-ready inorganic chemistry laboratory",
    "capabilities": [
      {
        "tool_name": "calculate_crystal_field_splitting",
        "args": [
          "metal",
          "ligands",
          "geometry"
        ],
        "doc": "Calculate crystal field splitting energy and diagram"
      },
      {
        "tool_name": "calculate_ligand_field_parameters",
        "args": [
          "complex"
        ],
        "doc": "Calculate comprehensive ligand field parameters"
      },
      {
        "tool_name": "predict_complex_stability",
        "args": [
          "complex"
        ],
        "doc": "Predict stability constants and formation energies"
      },
      {
        "tool_name": "calculate_metal_ligand_bonding",
        "args": [
          "complex"
        ],
        "doc": "Analyze metal-ligand bonding using MO theory"
      },
      {
        "tool_name": "calculate_redox_potential",
        "args": [
          "half_cell1",
          "half_cell2",
          "concentrations"
        ],
        "doc": "Calculate cell potential using Nernst equation"
      },
      {
        "tool_name": "analyze_spectrochemical_series",
        "args": [
          "ligands"
        ],
        "doc": "Analyze ligands position in spectrochemical series"
      },
      {
        "tool_name": "calculate_tanabe_sugano_parameters",
        "args": [
          "metal",
          "field_strength"
        ],
        "doc": "Calculate Tanabe-Sugano diagram parameters for d-electron systems"
      },
      {
        "tool_name": "predict_magnetic_properties",
        "args": [
          "complex"
        ],
        "doc": "Predict magnetic moment and susceptibility"
      },
      {
        "tool_name": "calculate_lattice_energy",
        "args": [
          "cation",
          "anion",
          "structure_type"
        ],
        "doc": "Calculate lattice energy using Born-Land\u00e9 equation"
      }
    ]
  },
  {
    "id": "control_systems_lab.py",
    "name": "Control Systems",
    "description": "Comprehensive control systems laboratory",
    "capabilities": [
      {
        "tool_name": "pid_control",
        "args": [
          "controller",
          "setpoint",
          "measurement"
        ],
        "doc": "Calculate PID controller output with anti-windup and derivative filtering"
      },
      {
        "tool_name": "auto_tune_pid",
        "args": [
          "system",
          "method"
        ],
        "doc": "Auto-tune PID controller using various methods"
      },
      {
        "tool_name": "cascade_pid",
        "args": [
          "outer_controller",
          "inner_controller",
          "outer_setpoint",
          "outer_measurement",
          "inner_measurement"
        ],
        "doc": "Cascade PID control for improved performance"
      },
      {
        "tool_name": "create_state_space",
        "args": [
          "num",
          "den"
        ],
        "doc": "Create state-space model from transfer function"
      },
      {
        "tool_name": "linearize_system",
        "args": [
          "f",
          "g",
          "x0",
          "u0",
          "delta"
        ],
        "doc": "Linearize nonlinear system around operating point\ndx/dt = f(x, u), y = g(x, u)"
      },
      {
        "tool_name": "controllability_matrix",
        "args": [
          "system"
        ],
        "doc": "Compute controllability matrix [B, AB, A\u00b2B, ...]"
      },
      {
        "tool_name": "is_controllable",
        "args": [
          "system"
        ],
        "doc": "Check if system is controllable"
      },
      {
        "tool_name": "observability_matrix",
        "args": [
          "system"
        ],
        "doc": "Compute observability matrix [C; CA; CA\u00b2; ...]"
      },
      {
        "tool_name": "is_observable",
        "args": [
          "system"
        ],
        "doc": "Check if system is observable"
      },
      {
        "tool_name": "lqr",
        "args": [
          "system",
          "Q",
          "R"
        ],
        "doc": "Linear Quadratic Regulator design\nReturns gain matrix K and Riccati solution P"
      },
      {
        "tool_name": "lqr_with_integral",
        "args": [
          "system",
          "Q",
          "R"
        ],
        "doc": "LQR with integral action for zero steady-state error"
      },
      {
        "tool_name": "lqg",
        "args": [
          "system",
          "Q",
          "R",
          "Qn",
          "Rn"
        ],
        "doc": "Linear Quadratic Gaussian control (LQR + Kalman filter)"
      },
      {
        "tool_name": "kalman_predict",
        "args": [
          "kf",
          "u"
        ],
        "doc": "Kalman filter prediction step"
      },
      {
        "tool_name": "kalman_update",
        "args": [
          "kf",
          "y"
        ],
        "doc": "Kalman filter update step"
      },
      {
        "tool_name": "extended_kalman_filter",
        "args": [
          "f",
          "h",
          "F_jac",
          "H_jac",
          "x",
          "P",
          "u",
          "y",
          "Q",
          "R"
        ],
        "doc": "Extended Kalman filter for nonlinear systems"
      },
      {
        "tool_name": "h_infinity_norm",
        "args": [
          "system"
        ],
        "doc": "Compute H-infinity norm of system"
      },
      {
        "tool_name": "mu_synthesis",
        "args": [
          "system",
          "uncertainty"
        ],
        "doc": "\u03bc-synthesis for robust control with structured uncertainty\nSimplified version for demonstration"
      },
      {
        "tool_name": "mpc",
        "args": [
          "system",
          "x0",
          "horizon",
          "Q",
          "R",
          "constraints"
        ],
        "doc": "Model Predictive Control with constraints\nSimplified version - real MPC requires quadratic programming"
      },
      {
        "tool_name": "mrac",
        "args": [
          "reference_model",
          "plant",
          "learning_rate"
        ],
        "doc": "Model Reference Adaptive Control"
      },
      {
        "tool_name": "sliding_mode_control",
        "args": [
          "system",
          "sliding_surface",
          "switching_gain"
        ],
        "doc": "Sliding mode control for robust nonlinear control"
      },
      {
        "tool_name": "system_identification",
        "args": [
          "input_data",
          "output_data",
          "order"
        ],
        "doc": "System identification using least squares"
      },
      {
        "tool_name": "simulate_system",
        "args": [
          "system",
          "controller",
          "t_span",
          "x0",
          "reference"
        ],
        "doc": "Simulate controlled system"
      }
    ]
  },
  {
    "id": "diffusion_model_sampler_lab.py",
    "name": "Diffusion Model Sampler",
    "description": "Diffusion Model Sampler\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "ecology_lab.py",
    "name": "Ecology",
    "description": "Advanced ecology laboratory.\nImplements population dynamics, food webs, biodiversity metrics, and ecosystem services.",
    "capabilities": [
      {
        "tool_name": "lotka_volterra_dynamics",
        "args": [
          "initial_populations",
          "interactions",
          "time_years",
          "stochastic"
        ],
        "doc": "Generalized Lotka-Volterra population dynamics.\nCan handle predator-prey, competition, and mutualism."
      },
      {
        "tool_name": "food_web_structure",
        "args": [
          "species_list"
        ],
        "doc": "Analyze food web structure and stability.\nReturns network metrics and trophic relationships."
      },
      {
        "tool_name": "biodiversity_metrics",
        "args": [
          "abundances",
          "spatial_distribution"
        ],
        "doc": "Calculate comprehensive biodiversity metrics.\nIncludes alpha, beta, and gamma diversity."
      },
      {
        "tool_name": "species_area_relationship",
        "args": [
          "min_area",
          "max_area",
          "n_samples"
        ],
        "doc": "Model species-area relationship (SAR).\nS = c * A^z where S is species, A is area."
      },
      {
        "tool_name": "metapopulation_dynamics",
        "args": [
          "patches",
          "colonization_rate",
          "extinction_rate",
          "initial_occupied",
          "time_years",
          "connectivity_matrix"
        ],
        "doc": "Levins metapopulation model with spatial structure.\nTracks patch occupancy over time."
      },
      {
        "tool_name": "island_biogeography",
        "args": [
          "island_area",
          "distance_to_mainland",
          "mainland_species"
        ],
        "doc": "MacArthur-Wilson island biogeography theory.\nPredicts species richness based on area and isolation."
      },
      {
        "tool_name": "ecological_succession",
        "args": [
          "disturbance_type",
          "time_years"
        ],
        "doc": "Model ecological succession after disturbance.\nTracks community composition changes over time."
      },
      {
        "tool_name": "ecosystem_services_valuation",
        "args": [
          "land_use",
          "population"
        ],
        "doc": "Calculate economic value of ecosystem services.\nBased on land use and ecosystem health."
      },
      {
        "tool_name": "habitat_fragmentation_analysis",
        "args": [
          "landscape_matrix",
          "cell_size"
        ],
        "doc": "Analyze habitat fragmentation metrics.\n1 = habitat, 0 = non-habitat in matrix."
      },
      {
        "tool_name": "carbon_cycle_model",
        "args": [
          "vegetation_biomass",
          "soil_carbon",
          "temperature",
          "precipitation",
          "time_years"
        ],
        "doc": "Ecosystem carbon cycle model.\nTracks carbon pools and fluxes."
      },
      {
        "tool_name": "demo",
        "args": [],
        "doc": "Demonstrate ecology modeling capabilities"
      }
    ]
  },
  {
    "id": "propulsion_lab.py",
    "name": "Propulsion",
    "description": "",
    "capabilities": [
      {
        "tool_name": "calculate_thrust",
        "args": [
          "mass_flow_rate",
          "exhaust_velocity",
          "pressure_exit",
          "pressure_ambient",
          "area_exit"
        ],
        "doc": "Calculates rocket thrust equation: F = q * Ve + (Pe - Pa) * Ae"
      },
      {
        "tool_name": "ion_thruster_sim",
        "args": [
          "power",
          "efficiency",
          "isp"
        ],
        "doc": "Simulate Ion Drive performance.\nF = (2 * eta * P) / (g0 * Isp)"
      },
      {
        "tool_name": "run_demo",
        "args": [],
        "doc": "No description available."
      }
    ]
  },
  {
    "id": "evolutionary_biology_lab.py",
    "name": "Evolutionary Biology",
    "description": "Production-ready evolutionary biology analysis laboratory.",
    "capabilities": [
      {
        "tool_name": "initialize_substitution_models",
        "args": [],
        "doc": "Initialize nucleotide substitution models."
      },
      {
        "tool_name": "initialize_population",
        "args": [
          "genome_length"
        ],
        "doc": "Initialize population with random genomes."
      },
      {
        "tool_name": "wright_fisher_model",
        "args": [
          "allele_freq",
          "Ne",
          "selection"
        ],
        "doc": "Wright-Fisher model with selection."
      },
      {
        "tool_name": "moran_process",
        "args": [
          "population",
          "fitness_function"
        ],
        "doc": "Moran process for continuous time evolution."
      },
      {
        "tool_name": "coalescent_simulation",
        "args": [
          "n_samples",
          "theta"
        ],
        "doc": "Coalescent simulation for genealogy reconstruction."
      },
      {
        "tool_name": "jukes_cantor_distance",
        "args": [
          "seq1",
          "seq2"
        ],
        "doc": "Calculate Jukes-Cantor corrected distance."
      },
      {
        "tool_name": "kimura_2p_distance",
        "args": [
          "seq1",
          "seq2"
        ],
        "doc": "Calculate Kimura 2-parameter distance."
      },
      {
        "tool_name": "build_distance_matrix",
        "args": [
          "sequences",
          "method"
        ],
        "doc": "Build pairwise distance matrix."
      },
      {
        "tool_name": "neighbor_joining",
        "args": [
          "distance_matrix"
        ],
        "doc": "Neighbor-joining tree construction algorithm."
      },
      {
        "tool_name": "calculate_dn_ds_ratio",
        "args": [
          "codon_seq1",
          "codon_seq2"
        ],
        "doc": "Calculate dN/dS ratio for detecting selection."
      },
      {
        "tool_name": "tajima_d_test",
        "args": [
          "sequences"
        ],
        "doc": "Tajima's D test for neutral evolution."
      },
      {
        "tool_name": "mcdonald_kreitman_test",
        "args": [
          "sequences_sp1",
          "sequences_sp2"
        ],
        "doc": "McDonald-Kreitman test for adaptive evolution."
      },
      {
        "tool_name": "fst_calculation",
        "args": [
          "pop1_alleles",
          "pop2_alleles"
        ],
        "doc": "Calculate FST for population differentiation."
      },
      {
        "tool_name": "hardy_weinberg_test",
        "args": [
          "genotypes"
        ],
        "doc": "Test for Hardy-Weinberg equilibrium."
      },
      {
        "tool_name": "simulate_genetic_drift",
        "args": [
          "initial_freq",
          "Ne",
          "generations"
        ],
        "doc": "Simulate genetic drift over time."
      },
      {
        "tool_name": "molecular_clock_dating",
        "args": [
          "sequences",
          "calibration_time",
          "calibration_nodes"
        ],
        "doc": "Estimate divergence times using molecular clock."
      },
      {
        "tool_name": "simulate_adaptive_landscape",
        "args": [
          "genome_length",
          "n_peaks"
        ],
        "doc": "Create adaptive landscape with multiple fitness peaks."
      },
      {
        "tool_name": "hill_climbing_evolution",
        "args": [
          "initial_genotype",
          "fitness_function",
          "max_steps"
        ],
        "doc": "Simulate evolution via hill climbing."
      },
      {
        "tool_name": "linkage_disequilibrium",
        "args": [
          "genotypes",
          "locus1",
          "locus2"
        ],
        "doc": "Calculate linkage disequilibrium between two loci."
      },
      {
        "tool_name": "run_comprehensive_analysis",
        "args": [
          "sequences"
        ],
        "doc": "Run complete evolutionary analysis pipeline."
      }
    ]
  },
  {
    "id": "computational_chemistry_lab.py",
    "name": "Computational Chemistry",
    "description": "Advanced computational chemistry laboratory for molecular simulations.",
    "capabilities": [
      {
        "tool_name": "molecular_mechanics_energy",
        "args": [
          "molecule"
        ],
        "doc": "Calculate molecular mechanics energy using force field.\n\nE_total = E_bond + E_angle + E_dihedral + E_vdw + E_electrostatic"
      },
      {
        "tool_name": "am1_energy",
        "args": [
          "molecule"
        ],
        "doc": "Calculate energy using AM1 semi-empirical method.\nSimplified implementation for demonstration."
      },
      {
        "tool_name": "simple_dft_energy",
        "args": [
          "molecule",
          "functional"
        ],
        "doc": "Calculate energy using simplified DFT.\nImplements Local Density Approximation (LDA) and GGA basics."
      },
      {
        "tool_name": "conformational_search",
        "args": [
          "molecule",
          "n_conformers",
          "method"
        ],
        "doc": "Search for low-energy conformations.\nMethods: systematic, random, genetic"
      },
      {
        "tool_name": "optimize_geometry",
        "args": [
          "molecule",
          "method",
          "max_iter"
        ],
        "doc": "Optimize molecular geometry.\nMethods: MM (molecular mechanics), AM1, DFT"
      },
      {
        "tool_name": "run_comprehensive_demo",
        "args": [],
        "doc": "Run comprehensive demonstration of computational chemistry capabilities."
      }
    ]
  },
  {
    "id": "biochemistry_lab.py",
    "name": "Biochemistry",
    "description": "Advanced biochemistry laboratory for comprehensive biomolecular simulations.",
    "capabilities": [
      {
        "tool_name": "michaelis_menten",
        "args": [
          "enzyme",
          "substrate_conc",
          "enzyme_conc"
        ],
        "doc": "Calculate reaction velocity using Michaelis-Menten equation.\n\nv = (Vmax * [S]) / (Km + [S])\nwhere Vmax = kcat * [E]"
      },
      {
        "tool_name": "michaelis_menten_inhibition",
        "args": [
          "enzyme",
          "substrate_conc",
          "inhibitor_conc",
          "enzyme_conc",
          "inhibition_type"
        ],
        "doc": "Calculate reaction velocity with enzyme inhibition.\n\nTypes: competitive, noncompetitive, uncompetitive, mixed"
      },
      {
        "tool_name": "hill_equation",
        "args": [
          "enzyme",
          "substrate_conc",
          "enzyme_conc"
        ],
        "doc": "Calculate reaction velocity with cooperativity using Hill equation.\n\nv = (Vmax * [S]^n) / (K0.5^n + [S]^n)"
      },
      {
        "tool_name": "allosteric_regulation",
        "args": [
          "enzyme",
          "substrate_conc",
          "activator_conc",
          "inhibitor_conc",
          "enzyme_conc"
        ],
        "doc": "Model allosteric regulation using MWC (Monod-Wyman-Changeux) model."
      },
      {
        "tool_name": "ph_activity_profile",
        "args": [
          "enzyme",
          "substrate_conc",
          "ph_range",
          "enzyme_conc"
        ],
        "doc": "Calculate enzyme activity as function of pH."
      },
      {
        "tool_name": "gibbs_unfolding",
        "args": [
          "protein",
          "temp"
        ],
        "doc": "Calculate Gibbs free energy of protein unfolding.\n\n\u0394G = \u0394H - T\u0394S + \u0394Cp[(T - Tm) - T*ln(T/Tm)]"
      },
      {
        "tool_name": "protein_stability_curve",
        "args": [
          "protein",
          "temp_range"
        ],
        "doc": "Calculate protein stability over temperature range.\nReturns temperatures and fraction folded."
      },
      {
        "tool_name": "calculate_melting_curve",
        "args": [
          "protein",
          "temp_range"
        ],
        "doc": "Calculate protein melting curve with van't Hoff analysis."
      },
      {
        "tool_name": "metabolic_flux_balance",
        "args": [
          "stoichiometry",
          "flux_bounds",
          "objective"
        ],
        "doc": "Solve flux balance analysis for metabolic network.\n\nMaximizes: c^T * v\nSubject to: S * v = 0 (steady state)\n           lb <= v <= ub (flux bounds)"
      },
      {
        "tool_name": "pathway_thermodynamics",
        "args": [
          "metabolites",
          "stoichiometry"
        ],
        "doc": "Calculate overall Gibbs free energy change for a pathway.\n\n\u0394G = \u0394G\u00b0 + RT*ln(Q)"
      },
      {
        "tool_name": "simulate_pathway_dynamics",
        "args": [
          "initial_conc",
          "rate_constants",
          "stoichiometry",
          "time_points"
        ],
        "doc": "Simulate metabolic pathway dynamics using ODEs."
      },
      {
        "tool_name": "ligand_binding_curve",
        "args": [
          "kd",
          "ligand_range",
          "n_sites",
          "cooperativity"
        ],
        "doc": "Calculate fractional saturation for ligand binding.\n\nUses Hill equation for cooperativity."
      },
      {
        "tool_name": "scatchard_analysis",
        "args": [
          "bound",
          "free"
        ],
        "doc": "Perform Scatchard analysis to determine Kd and number of binding sites.\n\nScatchard equation: B/F = n/Kd - B/Kd"
      },
      {
        "tool_name": "dna_melting_temperature",
        "args": [
          "sequence",
          "salt_conc"
        ],
        "doc": "Calculate DNA melting temperature using nearest-neighbor model."
      },
      {
        "tool_name": "nernst_potential",
        "args": [
          "e0",
          "n_electrons",
          "ox_conc",
          "red_conc"
        ],
        "doc": "Calculate redox potential using Nernst equation.\n\nE = E\u00b0 - (RT/nF) * ln(red/ox)"
      },
      {
        "tool_name": "phosphorylation_potential",
        "args": [
          "atp_conc",
          "adp_conc",
          "pi_conc"
        ],
        "doc": "Calculate phosphorylation potential (\u0394Gp).\n\n\u0394Gp = \u0394G\u00b0' + RT*ln([ADP][Pi]/[ATP])"
      },
      {
        "tool_name": "run_comprehensive_demo",
        "args": [],
        "doc": "Run comprehensive demonstration of all biochemistry capabilities."
      }
    ]
  },
  {
    "id": "clinical_trials_simulation_lab.py",
    "name": "Clinical Trials Simulation",
    "description": "Advanced clinical trials simulation and analysis",
    "capabilities": [
      {
        "tool_name": "generate_patient_population",
        "args": [
          "n"
        ],
        "doc": "Generate realistic patient population based on eligibility criteria\n\nReference: Pocock, S.J. (1983) Clinical Trials: A Practical Approach. Wiley."
      },
      {
        "tool_name": "simple_randomization",
        "args": [],
        "doc": "Simple randomization (coin flip)\n\nReference: Friedman, L.M. et al. (2015) Fundamentals of Clinical Trials. Springer."
      },
      {
        "tool_name": "block_randomization",
        "args": [
          "block_size"
        ],
        "doc": "Block randomization to ensure balance\n\nReference: Schulz, K.F. & Grimes, D.A. (2002) Lancet 359(9305):515-519"
      },
      {
        "tool_name": "stratified_randomization",
        "args": [
          "factors"
        ],
        "doc": "Stratified randomization based on prognostic factors\n\nReference: Kernan, W.N. et al. (1999) Journal of Clinical Epidemiology 52(1):19-26"
      },
      {
        "tool_name": "adaptive_randomization",
        "args": [
          "responses"
        ],
        "doc": "Response-adaptive randomization (play-the-winner)\n\nReference: Wei, L.J. & Durham, S. (1978) JASA 73(364):840-843"
      },
      {
        "tool_name": "minimization_randomization",
        "args": [
          "imbalance_weight"
        ],
        "doc": "Minimization method to balance covariates\n\nReference: Taves, D.R. (1974) Clinical Pharmacology & Therapeutics 15(5):443-453"
      },
      {
        "tool_name": "simulate_survival_times",
        "args": [
          "arm",
          "n_patients"
        ],
        "doc": "Simulate survival and progression times using Weibull distribution\n\nReference: Collett, D. (2015) Modelling Survival Data in Medical Research. CRC Press."
      },
      {
        "tool_name": "kaplan_meier_estimate",
        "args": [
          "times",
          "events"
        ],
        "doc": "Kaplan-Meier survival curve estimation\n\nReference: Kaplan, E.L. & Meier, P. (1958) JASA 53(282):457-481"
      },
      {
        "tool_name": "cox_proportional_hazards",
        "args": [
          "times",
          "events",
          "covariates"
        ],
        "doc": "Cox proportional hazards regression (simplified)\n\nReference: Cox, D.R. (1972) Journal of the Royal Statistical Society B 34(2):187-220"
      },
      {
        "tool_name": "calculate_sample_size",
        "args": [
          "effect_size",
          "alpha",
          "power",
          "two_sided"
        ],
        "doc": "Sample size calculation for two-arm trial\n\nReference: Chow, S.C. et al. (2017) Sample Size Calculations. CRC Press."
      },
      {
        "tool_name": "obrien_fleming_boundaries",
        "args": [
          "n_analyses",
          "alpha"
        ],
        "doc": "O'Brien-Fleming spending function for group sequential design\n\nReference: O'Brien, P.C. & Fleming, T.R. (1979) Biometrics 35(3):549-556"
      },
      {
        "tool_name": "pocock_boundaries",
        "args": [
          "n_analyses",
          "alpha"
        ],
        "doc": "Pocock boundaries for group sequential design\n\nReference: Pocock, S.J. (1977) Biometrika 64(2):191-199"
      },
      {
        "tool_name": "simulate_trial_outcomes",
        "args": [
          "assignments"
        ],
        "doc": "Simulate individual patient outcomes based on treatment assignment"
      },
      {
        "tool_name": "perform_interim_analysis",
        "args": [
          "fraction_enrolled"
        ],
        "doc": "Perform interim analysis with early stopping rules\n\nReference: Jennison, C. & Turnbull, B.W. (1999) Group Sequential Methods. CRC Press."
      },
      {
        "tool_name": "calculate_trial_power",
        "args": [
          "n",
          "effect_size",
          "alpha"
        ],
        "doc": "Post-hoc power calculation\n\nReference: Hintze, J.L. (2008) PASS Software. NCSS."
      }
    ]
  },
  {
    "id": "renewable_energy_lab.py",
    "name": "Renewable Energy",
    "description": "Comprehensive renewable energy laboratory",
    "capabilities": [
      {
        "tool_name": "solar_irradiance",
        "args": [
          "latitude",
          "day_of_year",
          "hour",
          "tilt_angle",
          "azimuth"
        ],
        "doc": "Calculate solar irradiance on tilted surface\nUsing simplified clear-sky model"
      },
      {
        "tool_name": "solar_cell_iv_curve",
        "args": [
          "cell",
          "irradiance",
          "temperature"
        ],
        "doc": "Calculate I-V characteristic curve of solar cell\nUsing single-diode model"
      },
      {
        "tool_name": "solar_cell_efficiency",
        "args": [
          "cell",
          "spectrum"
        ],
        "doc": "Calculate detailed balance limit (Shockley-Queisser) efficiency"
      },
      {
        "tool_name": "tandem_solar_cell",
        "args": [
          "top_cell",
          "bottom_cell",
          "irradiance"
        ],
        "doc": "Model tandem (multi-junction) solar cell"
      },
      {
        "tool_name": "perovskite_stability",
        "args": [
          "temperature",
          "humidity",
          "illumination_hours"
        ],
        "doc": "Model perovskite solar cell degradation"
      },
      {
        "tool_name": "wind_power_curve",
        "args": [
          "turbine",
          "wind_speeds"
        ],
        "doc": "Calculate wind turbine power output curve"
      },
      {
        "tool_name": "wind_profile_height",
        "args": [
          "wind_speed_ref",
          "height_ref",
          "height",
          "roughness_length"
        ],
        "doc": "Calculate wind speed at different heights using log law\nroughness_length: 0.0002 (water), 0.03 (open field), 0.5 (suburban), 1.0 (urban)"
      },
      {
        "tool_name": "weibull_wind_distribution",
        "args": [
          "k",
          "c",
          "wind_speeds"
        ],
        "doc": "Weibull probability distribution for wind speeds\nk: shape parameter (typically 1.5-3)\nc: scale parameter (m/s)"
      },
      {
        "tool_name": "capacity_factor",
        "args": [
          "turbine",
          "wind_distribution"
        ],
        "doc": "Calculate capacity factor for wind turbine"
      },
      {
        "tool_name": "wake_effect",
        "args": [
          "turbines",
          "wind_direction",
          "wind_speed"
        ],
        "doc": "Calculate wake effects in wind farm\nturbines: list of (x, y) positions"
      },
      {
        "tool_name": "vertical_axis_turbine",
        "args": [
          "height",
          "diameter",
          "wind_speed",
          "solidity"
        ],
        "doc": "Model Vertical Axis Wind Turbine (VAWT) like Darrieus or Savonius"
      },
      {
        "tool_name": "battery_charge_discharge",
        "args": [
          "battery",
          "power_profile",
          "time_step"
        ],
        "doc": "Simulate battery charge/discharge with power profile\npower_profile: positive for charging, negative for discharging\ntime_step: hours"
      },
      {
        "tool_name": "battery_degradation",
        "args": [
          "battery",
          "cycles",
          "average_dod",
          "average_temperature"
        ],
        "doc": "Model battery capacity fade over cycles"
      },
      {
        "tool_name": "flow_battery_model",
        "args": [
          "power",
          "energy",
          "electrolyte_volume"
        ],
        "doc": "Model flow battery (Vanadium redox, Zinc-bromine, etc.)"
      },
      {
        "tool_name": "grid_frequency_response",
        "args": [
          "grid",
          "power_imbalance",
          "system_inertia"
        ],
        "doc": "Calculate grid frequency response to power imbalance"
      },
      {
        "tool_name": "inverter_control",
        "args": [
          "dc_power",
          "dc_voltage",
          "grid_voltage",
          "grid_frequency"
        ],
        "doc": "Model grid-tied inverter with MPPT and grid synchronization"
      },
      {
        "tool_name": "microgrid_optimization",
        "args": [
          "solar_power",
          "wind_power",
          "load_demand",
          "battery",
          "grid",
          "time_step"
        ],
        "doc": "Optimize microgrid operation with renewable sources, storage, and grid connection"
      },
      {
        "tool_name": "hydrogen_storage",
        "args": [
          "excess_power",
          "electrolyzer_efficiency",
          "fuel_cell_efficiency"
        ],
        "doc": "Model hydrogen energy storage system"
      },
      {
        "tool_name": "tidal_energy",
        "args": [
          "tidal_velocity",
          "turbine_area",
          "efficiency"
        ],
        "doc": "Calculate tidal energy generation"
      },
      {
        "tool_name": "geothermal_power",
        "args": [
          "flow_rate",
          "inlet_temp",
          "outlet_temp",
          "efficiency"
        ],
        "doc": "Calculate geothermal power generation\nflow_rate: kg/s\ntemperatures: Celsius"
      },
      {
        "tool_name": "biomass_gasification",
        "args": [
          "biomass_kg",
          "moisture_content",
          "gasifier_efficiency"
        ],
        "doc": "Model biomass gasification for power generation"
      },
      {
        "tool_name": "levelized_cost",
        "args": [
          "capital_cost",
          "operating_cost",
          "energy_produced",
          "lifetime_years",
          "discount_rate"
        ],
        "doc": "Calculate Levelized Cost of Energy (LCOE)"
      }
    ]
  },
  {
    "id": "fluid_dynamics_lab.py",
    "name": "Fluid Dynamics",
    "description": "Advanced fluid dynamics calculations for incompressible and compressible flows",
    "capabilities": [
      {
        "tool_name": "navier_stokes_2d_cavity",
        "args": [
          "Re",
          "nx",
          "ny",
          "nt",
          "dt"
        ],
        "doc": "Solve 2D incompressible Navier-Stokes for lid-driven cavity flow\n\nArgs:\n    Re: Reynolds number\n    nx, ny: Grid points in x and y\n    nt: Number of time steps\n    dt: Time step size\n\nReturns:\n    Velocity and pressure fields"
      },
      {
        "tool_name": "blasius_boundary_layer",
        "args": [
          "x",
          "U_inf",
          "nu"
        ],
        "doc": "Calculate Blasius boundary layer solution for flat plate\n\nArgs:\n    x: Streamwise positions (m)\n    U_inf: Freestream velocity (m/s)\n    nu: Kinematic viscosity (m\u00b2/s)\n\nReturns:\n    Boundary layer properties"
      },
      {
        "tool_name": "turbulent_channel_flow",
        "args": [
          "Re_tau",
          "y_plus"
        ],
        "doc": "Calculate turbulent channel flow velocity profile (law of the wall)\n\nArgs:\n    Re_tau: Friction Reynolds number\n    y_plus: Dimensionless wall distance\n\nReturns:\n    Velocity profiles for different regions"
      },
      {
        "tool_name": "compressible_shock_tube",
        "args": [
          "x",
          "t",
          "P_ratio"
        ],
        "doc": "Solve Sod shock tube problem (Riemann problem)\n\nArgs:\n    x: Spatial coordinates\n    t: Time after diaphragm rupture\n    P_ratio: Initial pressure ratio\n\nReturns:\n    Flow properties"
      },
      {
        "tool_name": "karman_vortex_street",
        "args": [
          "Re",
          "St"
        ],
        "doc": "Calculate von Karman vortex street parameters\n\nArgs:\n    Re: Reynolds number\n    St: Strouhal number\n\nReturns:\n    Vortex shedding parameters"
      },
      {
        "tool_name": "pipe_flow_friction",
        "args": [
          "Re",
          "roughness"
        ],
        "doc": "Calculate Darcy friction factor for pipe flow\n\nArgs:\n    Re: Reynolds number\n    roughness: Relative roughness (e/D)\n\nReturns:\n    Darcy friction factor"
      },
      {
        "tool_name": "mixing_layer_growth",
        "args": [
          "x",
          "U1",
          "U2",
          "nu"
        ],
        "doc": "Calculate turbulent mixing layer growth rate\n\nArgs:\n    x: Downstream distance (m)\n    U1, U2: Velocities of streams (m/s)\n    nu: Kinematic viscosity (m\u00b2/s)\n\nReturns:\n    Mixing layer properties"
      },
      {
        "tool_name": "rayleigh_benard_convection",
        "args": [
          "Ra",
          "Pr"
        ],
        "doc": "Calculate Rayleigh-Benard convection parameters\n\nArgs:\n    Ra: Rayleigh number\n    Pr: Prandtl number\n\nReturns:\n    Convection characteristics"
      },
      {
        "tool_name": "jet_spreading_rate",
        "args": [
          "x",
          "D",
          "U_jet",
          "Re"
        ],
        "doc": "Calculate turbulent jet spreading and decay\n\nArgs:\n    x: Axial distance (m)\n    D: Nozzle diameter (m)\n    U_jet: Exit velocity (m/s)\n    Re: Reynolds number\n\nReturns:\n    Jet properties"
      },
      {
        "tool_name": "drag_coefficient",
        "args": [
          "shape",
          "Re"
        ],
        "doc": "Calculate drag coefficient for various shapes\n\nArgs:\n    shape: 'sphere', 'cylinder', 'flat_plate', 'airfoil'\n    Re: Reynolds number\n\nReturns:\n    Drag coefficient"
      },
      {
        "tool_name": "demonstrate",
        "args": [],
        "doc": "Demonstrate all fluid dynamics calculations"
      }
    ]
  },
  {
    "id": "federated_learning_aggregator_lab.py",
    "name": "Federated Learning Aggregator",
    "description": "Federated Learning Aggregator\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "cardiac_fibrosis_predictor_lab.py",
    "name": "Cardiac Fibrosis Predictor",
    "description": "Advanced cardiac fibrosis modeling laboratory.\n\nFeatures:\n- TGF-beta signaling cascade simulation\n- Collagen accumulation dynamics\n- Fibroblast-to-myofibroblast transformation\n- ECM remodeling with MMP/TIMP balance\n- Treatment response prediction\n- Multi-biomarker integration\n- Stiffness progression modeling",
    "capabilities": [
      {
        "tool_name": "tgf_beta_signaling_cascade",
        "args": [
          "time",
          "initial_tgf",
          "stimulus"
        ],
        "doc": "Model TGF-beta signaling cascade in cardiac fibrosis.\n\nBased on: Leask (2015) \"Getting to the heart of the matter: new insights into cardiac fibrosis\"\n\nArgs:\n    time: Time points in days\n    initial_tgf: Initial TGF-beta concentration (ng/mL)\n    stimulus: External stimulus (injury, inflammation)\n\nReturns:\n    Dictionary with signaling molecule concentrations"
      },
      {
        "tool_name": "fibroblast_activation_dynamics",
        "args": [
          "time",
          "tgf_beta"
        ],
        "doc": "Model fibroblast to myofibroblast transformation.\n\nMyofibroblasts are the primary collagen-producing cells in fibrosis.\n\nArgs:\n    time: Time points\n    tgf_beta: TGF-beta concentration over time\n\nReturns:\n    Dictionary with cell populations"
      },
      {
        "tool_name": "ecm_remodeling_simulation",
        "args": [
          "time",
          "collagen",
          "params"
        ],
        "doc": "Simulate extracellular matrix remodeling with MMP/TIMP balance.\n\nMMPs degrade collagen, TIMPs inhibit MMPs.\n\nArgs:\n    time: Time points\n    collagen: Collagen levels over time\n    params: Fibrosis parameters\n\nReturns:\n    Dictionary with ECM components"
      },
      {
        "tool_name": "myocardial_stiffness_progression",
        "args": [
          "collagen_content",
          "crosslinking"
        ],
        "doc": "Calculate myocardial stiffness from collagen content.\n\nBased on: Fomovsky et al. (2010) \"Contribution of extracellular matrix to the mechanical properties of the heart\"\n\nArgs:\n    collagen_content: Collagen levels (relative)\n    crosslinking: Degree of collagen crosslinking\n\nReturns:\n    Myocardial stiffness (kPa)"
      },
      {
        "tool_name": "predict_treatment_response",
        "args": [
          "patient",
          "treatment",
          "duration_months"
        ],
        "doc": "Predict response to anti-fibrotic treatments.\n\nTreatments:\n- ACE inhibitors/ARBs: Reduce TGF-beta\n- Spironolactone: Aldosterone antagonist\n- Pirfenidone: Direct anti-fibrotic\n- SGLT2 inhibitors: Emerging anti-fibrotic effects\n\nArgs:\n    patient: Patient data\n    treatment: Treatment type\n    duration_months: Treatment duration\n\nReturns:\n    Dictionary with treatment response predictions"
      },
      {
        "tool_name": "calculate_fibrosis_score",
        "args": [
          "patient"
        ],
        "doc": "Calculate comprehensive fibrosis score from multimodal data.\n\nIntegrates biomarkers, imaging, and clinical data.\n\nArgs:\n    patient: Patient data\n\nReturns:\n    Dictionary with fibrosis scores"
      },
      {
        "tool_name": "longitudinal_progression_model",
        "args": [
          "patient",
          "years"
        ],
        "doc": "Model longitudinal fibrosis progression over years.\n\nArgs:\n    patient: Baseline patient data\n    years: Follow-up duration\n\nReturns:\n    Dictionary with progression trajectories"
      },
      {
        "tool_name": "analyze_biomarker_correlations",
        "args": [
          "patients"
        ],
        "doc": "Analyze correlations between biomarkers and fibrosis.\n\nArgs:\n    patients: List of patient data\n\nReturns:\n    Dictionary with correlation analysis"
      },
      {
        "tool_name": "simulate_antifibrotic_drug_trial",
        "args": [
          "n_patients",
          "drug",
          "duration_months"
        ],
        "doc": "Simulate clinical trial for anti-fibrotic therapy.\n\nArgs:\n    n_patients: Number of patients\n    drug: Drug being tested\n    duration_months: Trial duration\n\nReturns:\n    Dictionary with trial results"
      },
      {
        "tool_name": "demo",
        "args": [],
        "doc": "Demonstrate cardiac fibrosis prediction and modeling."
      }
    ]
  },
  {
    "id": "nuclear_physics_lab.py",
    "name": "Nuclear Physics",
    "description": "Advanced nuclear physics calculations for reactions and reactor physics",
    "capabilities": [
      {
        "tool_name": "weizsacker_semi_empirical_mass",
        "args": [
          "A",
          "Z"
        ],
        "doc": "Semi-empirical mass formula (SEMF) for nuclear binding energy\n\nArgs:\n    A: Mass number\n    Z: Atomic number\n\nReturns:\n    Binding energy in MeV"
      },
      {
        "tool_name": "decay_chain_solver",
        "args": [
          "lambdas",
          "N0",
          "t_max",
          "steps"
        ],
        "doc": "Solve Bateman equations for radioactive decay chain\n\nArgs:\n    lambdas: Decay constants (1/s) for each isotope\n    N0: Initial populations\n    t_max: Maximum time (s)\n    steps: Number of time steps\n\nReturns:\n    Population evolution over time"
      },
      {
        "tool_name": "neutron_cross_section",
        "args": [
          "E",
          "target_A",
          "reaction_type"
        ],
        "doc": "Calculate neutron cross-sections using Breit-Wigner formula\n\nArgs:\n    E: Neutron energies (eV)\n    target_A: Target mass number\n    reaction_type: 'fission', 'capture', or 'scattering'\n\nReturns:\n    Cross-sections in barns"
      },
      {
        "tool_name": "criticality_equation",
        "args": [
          "k_inf",
          "B_g2",
          "L2",
          "tau"
        ],
        "doc": "Four-factor formula for reactor criticality\n\nArgs:\n    k_inf: Infinite multiplication factor\n    B_g2: Geometric buckling (1/m\u00b2)\n    L2: Thermal diffusion area (m\u00b2)\n    tau: Fermi age (m\u00b2)\n\nReturns:\n    Effective multiplication factor k_eff"
      },
      {
        "tool_name": "fission_yield_distribution",
        "args": [
          "A_frag",
          "A_total"
        ],
        "doc": "Calculate fission fragment yield distribution\n\nArgs:\n    A_frag: Fragment mass numbers\n    A_total: Total mass number (e.g., 236 for U-235 + n)\n\nReturns:\n    Yield probabilities"
      },
      {
        "tool_name": "fusion_reaction_rate",
        "args": [
          "T",
          "reaction"
        ],
        "doc": "Calculate fusion reaction rate using Gamow factor\n\nArgs:\n    T: Temperature (keV)\n    reaction: 'DT', 'DD', or 'DHe3'\n\nReturns:\n    Reaction rate coefficient <\u03c3v> in m\u00b3/s"
      },
      {
        "tool_name": "radiation_shielding_attenuation",
        "args": [
          "E",
          "x",
          "Z",
          "particle"
        ],
        "doc": "Calculate radiation attenuation through shielding\n\nArgs:\n    E: Energy (MeV)\n    x: Shield thickness (cm)\n    Z: Atomic number of shield\n    particle: 'gamma', 'neutron', or 'beta'\n\nReturns:\n    Transmission fraction"
      },
      {
        "tool_name": "reactor_neutron_diffusion",
        "args": [
          "r",
          "R_core",
          "D",
          "Sigma_a",
          "nu_Sigma_f"
        ],
        "doc": "Solve neutron diffusion equation in reactor core\n\nArgs:\n    r: Radial positions (m)\n    R_core: Core radius (m)\n    D: Diffusion coefficient (m)\n    Sigma_a: Absorption cross-section (1/m)\n    nu_Sigma_f: Fission production (1/m)\n\nReturns:\n    Neutron flux distribution"
      },
      {
        "tool_name": "q_value_calculation",
        "args": [
          "reactants",
          "products"
        ],
        "doc": "Calculate Q-value for nuclear reaction\n\nArgs:\n    reactants: Dict of reactant masses (amu)\n    products: Dict of product masses (amu)\n\nReturns:\n    Q-value in MeV"
      },
      {
        "tool_name": "coulomb_barrier_tunneling",
        "args": [
          "E",
          "Z1",
          "Z2",
          "A1",
          "A2"
        ],
        "doc": "Calculate tunneling probability through Coulomb barrier\n\nArgs:\n    E: Center-of-mass energy (MeV)\n    Z1, Z2: Atomic numbers\n    A1, A2: Mass numbers\n\nReturns:\n    Tunneling probability"
      },
      {
        "tool_name": "neutron_moderation_spectrum",
        "args": [
          "E",
          "T",
          "A_mod"
        ],
        "doc": "Calculate neutron energy spectrum after moderation\n\nArgs:\n    E: Neutron energies (eV)\n    T: Moderator temperature (K)\n    A_mod: Moderator mass number\n\nReturns:\n    Neutron flux spectrum"
      },
      {
        "tool_name": "beta_decay_spectrum",
        "args": [
          "E_beta",
          "Q_beta",
          "Z"
        ],
        "doc": "Calculate beta decay energy spectrum (Fermi theory)\n\nArgs:\n    E_beta: Beta particle energies (MeV)\n    Q_beta: Q-value of decay (MeV)\n    Z: Atomic number of daughter\n\nReturns:\n    Beta spectrum intensity"
      },
      {
        "tool_name": "demonstrate",
        "args": [],
        "doc": "Demonstrate all nuclear physics calculations"
      }
    ]
  },
  {
    "id": "natural_language_processing_lab.py",
    "name": "Natural Language Processing",
    "description": "Production-ready NLP algorithms implemented from scratch.",
    "capabilities": [
      {
        "tool_name": "tokenize",
        "args": [
          "text",
          "method"
        ],
        "doc": "Tokenize text using various methods.\n\nArgs:\n    text: Input text\n    method: 'word', 'sentence', 'subword', 'char'\n\nReturns:\n    List of tokens"
      },
      {
        "tool_name": "build_vocabulary",
        "args": [
          "corpus",
          "max_vocab"
        ],
        "doc": "Build vocabulary from corpus.\n\nArgs:\n    corpus: List of documents\n    max_vocab: Maximum vocabulary size"
      },
      {
        "tool_name": "text_to_indices",
        "args": [
          "text"
        ],
        "doc": "Convert text to vocabulary indices."
      },
      {
        "tool_name": "indices_to_text",
        "args": [
          "indices"
        ],
        "doc": "Convert vocabulary indices back to text."
      },
      {
        "tool_name": "compute_tf_idf",
        "args": [
          "corpus"
        ],
        "doc": "Compute TF-IDF vectors for corpus.\n\nArgs:\n    corpus: List of documents\n\nReturns:\n    TF-IDF matrix (n_docs, vocab_size)"
      },
      {
        "tool_name": "word2vec_skipgram",
        "args": [
          "corpus",
          "iterations"
        ],
        "doc": "Train Word2Vec embeddings using Skip-gram with Negative Sampling.\n\nArgs:\n    corpus: List of documents\n    iterations: Training iterations\n\nReturns:\n    Word embedding matrix"
      },
      {
        "tool_name": "attention_mechanism",
        "args": [
          "query",
          "keys",
          "values",
          "mask"
        ],
        "doc": "Implement scaled dot-product attention.\n\nArgs:\n    query: Query matrix (seq_len, d_k)\n    keys: Key matrix (seq_len, d_k)\n    values: Value matrix (seq_len, d_v)\n    mask: Optional attention mask\n\nReturns:\n    Attention output and attention weights"
      },
      {
        "tool_name": "multi_head_attention",
        "args": [
          "query",
          "keys",
          "values",
          "num_heads"
        ],
        "doc": "Implement multi-head attention.\n\nArgs:\n    query: Query matrix\n    keys: Key matrix\n    values: Value matrix\n    num_heads: Number of attention heads\n\nReturns:\n    Multi-head attention output"
      },
      {
        "tool_name": "build_n_gram_model",
        "args": [
          "corpus"
        ],
        "doc": "Build n-gram language model.\n\nArgs:\n    corpus: List of documents"
      },
      {
        "tool_name": "calculate_perplexity",
        "args": [
          "text",
          "model_type"
        ],
        "doc": "Calculate perplexity of text under n-gram model.\n\nArgs:\n    text: Input text\n    model_type: 'bigram' or 'trigram'\n\nReturns:\n    Perplexity score"
      },
      {
        "tool_name": "sequence_to_sequence",
        "args": [
          "encoder_input",
          "decoder_steps"
        ],
        "doc": "Simple sequence-to-sequence model with attention.\n\nArgs:\n    encoder_input: Input sequence (seq_len, embedding_dim)\n    decoder_steps: Number of decoding steps\n\nReturns:\n    Decoded sequence"
      },
      {
        "tool_name": "edit_distance",
        "args": [
          "str1",
          "str2"
        ],
        "doc": "Calculate Levenshtein edit distance between two strings.\n\nArgs:\n    str1: First string\n    str2: Second string\n\nReturns:\n    Edit distance"
      },
      {
        "tool_name": "cosine_similarity",
        "args": [
          "vec1",
          "vec2"
        ],
        "doc": "Calculate cosine similarity between two vectors."
      },
      {
        "tool_name": "text_classification_metrics",
        "args": [
          "y_true",
          "y_pred"
        ],
        "doc": "Calculate classification metrics for text classification.\n\nArgs:\n    y_true: True labels\n    y_pred: Predicted labels\n\nReturns:\n    Dictionary of metrics"
      },
      {
        "tool_name": "beam_search_decoder",
        "args": [
          "start_token",
          "max_length"
        ],
        "doc": "Implement beam search decoding.\n\nArgs:\n    start_token: Starting token index\n    max_length: Maximum sequence length\n\nReturns:\n    Decoded sequence"
      },
      {
        "tool_name": "named_entity_recognition",
        "args": [
          "text"
        ],
        "doc": "Simple rule-based Named Entity Recognition.\n\nArgs:\n    text: Input text\n\nReturns:\n    List of (entity, type) tuples"
      },
      {
        "tool_name": "sentiment_analysis_lexicon",
        "args": [
          "text"
        ],
        "doc": "Simple lexicon-based sentiment analysis.\n\nArgs:\n    text: Input text\n\nReturns:\n    Sentiment scores"
      },
      {
        "tool_name": "text_summarization_extractive",
        "args": [
          "text",
          "num_sentences"
        ],
        "doc": "Extractive text summarization using sentence scoring.\n\nArgs:\n    text: Input text\n    num_sentences: Number of sentences in summary\n\nReturns:\n    Summary text"
      }
    ]
  },
  {
    "id": "regenerative_medicine_lab.py",
    "name": "Regenerative Medicine",
    "description": "Stem cell and tissue regeneration modeling",
    "capabilities": [
      {
        "tool_name": "simulate_stem_cell_differentiation",
        "args": [
          "cell_type",
          "days"
        ],
        "doc": "Simulate stem cell differentiation trajectory"
      },
      {
        "tool_name": "design_scaffold",
        "args": [
          "material",
          "porosity"
        ],
        "doc": "Design tissue engineering scaffold"
      },
      {
        "tool_name": "predict_organoid_growth",
        "args": [
          "initial_cells",
          "days"
        ],
        "doc": "Predict organoid growth dynamics"
      }
    ]
  },
  {
    "id": "algorithm_design_lab.py",
    "name": "Algorithm Design",
    "description": "Comprehensive algorithm design laboratory with sorting, graph, and DP algorithms",
    "capabilities": [
      {
        "tool_name": "quicksort",
        "args": [
          "arr",
          "track_stats"
        ],
        "doc": "Implements quicksort algorithm with Lomuto partition scheme.\nAverage: O(n log n), Worst: O(n\u00b2), Space: O(log n)"
      },
      {
        "tool_name": "mergesort",
        "args": [
          "arr"
        ],
        "doc": "Implements merge sort algorithm.\nTime: O(n log n) always, Space: O(n)"
      },
      {
        "tool_name": "heapsort",
        "args": [
          "arr"
        ],
        "doc": "Implements heap sort algorithm using max heap.\nTime: O(n log n), Space: O(1)"
      },
      {
        "tool_name": "radix_sort",
        "args": [
          "arr"
        ],
        "doc": "Implements radix sort for non-negative integers.\nTime: O(d * n) where d is number of digits, Space: O(n)"
      },
      {
        "tool_name": "dijkstra",
        "args": [
          "graph",
          "start",
          "end"
        ],
        "doc": "Dijkstra's shortest path algorithm using min-heap.\nTime: O((V + E) log V), Space: O(V)"
      },
      {
        "tool_name": "bellman_ford",
        "args": [
          "edges",
          "num_vertices",
          "start"
        ],
        "doc": "Bellman-Ford algorithm for shortest paths with negative weights.\nTime: O(VE), Space: O(V)\nReturns distances and whether negative cycle exists"
      },
      {
        "tool_name": "floyd_warshall",
        "args": [
          "adj_matrix"
        ],
        "doc": "Floyd-Warshall all-pairs shortest path algorithm.\nTime: O(V\u00b3), Space: O(V\u00b2)"
      },
      {
        "tool_name": "kruskal_mst",
        "args": [
          "edges",
          "num_vertices"
        ],
        "doc": "Kruskal's minimum spanning tree algorithm using Union-Find.\nTime: O(E log E), Space: O(V)"
      },
      {
        "tool_name": "topological_sort",
        "args": [
          "graph"
        ],
        "doc": "Topological sort using Kahn's algorithm (BFS-based).\nTime: O(V + E), Space: O(V)\nReturns None if cycle exists"
      },
      {
        "tool_name": "strongly_connected_components",
        "args": [
          "graph"
        ],
        "doc": "Kosaraju's algorithm for finding strongly connected components.\nTime: O(V + E), Space: O(V)"
      },
      {
        "tool_name": "longest_common_subsequence",
        "args": [
          "seq1",
          "seq2"
        ],
        "doc": "Finds longest common subsequence using dynamic programming.\nTime: O(mn), Space: O(mn)"
      },
      {
        "tool_name": "knapsack_01",
        "args": [
          "weights",
          "values",
          "capacity"
        ],
        "doc": "Solves 0/1 knapsack problem using dynamic programming.\nTime: O(nW), Space: O(nW) where W is capacity"
      },
      {
        "tool_name": "edit_distance",
        "args": [
          "str1",
          "str2"
        ],
        "doc": "Computes Levenshtein distance and transformation sequence.\nTime: O(mn), Space: O(mn)"
      },
      {
        "tool_name": "matrix_chain_multiplication",
        "args": [
          "dimensions"
        ],
        "doc": "Finds optimal parenthesization for matrix chain multiplication.\nTime: O(n\u00b3), Space: O(n\u00b2)"
      },
      {
        "tool_name": "analyze_sorting_complexity",
        "args": [
          "size"
        ],
        "doc": "Analyzes complexity of different sorting algorithms"
      },
      {
        "tool_name": "benchmark_algorithms",
        "args": [
          "input_sizes"
        ],
        "doc": "Benchmarks algorithms across different input sizes"
      }
    ]
  },
  {
    "id": "aerospace_engineering_lab.py",
    "name": "Aerospace Engineering",
    "description": "Comprehensive aerospace engineering calculations including:\n- Lift and drag calculations\n- Orbital mechanics and trajectory planning\n- Propulsion system analysis\n- Structural analysis for aircraft and spacecraft\n- Stability and control analysis\n- Trajectory optimization",
    "capabilities": [
      {
        "tool_name": "standard_atmosphere",
        "args": [
          "altitude"
        ],
        "doc": "Calculate atmospheric properties using International Standard Atmosphere model\n\nArgs:\n    altitude: Altitude in meters (0-85000m)\n\nReturns:\n    Dictionary with temperature, pressure, density, and speed of sound"
      },
      {
        "tool_name": "lift_coefficient",
        "args": [
          "angle_of_attack",
          "aspect_ratio",
          "sweep_angle",
          "efficiency"
        ],
        "doc": "Calculate lift coefficient using lifting-line theory\n\nCL = 2\u03c0 * \u03b1 * (AR / (AR + 2))\n\nArgs:\n    angle_of_attack: Angle of attack in radians\n    aspect_ratio: Wing aspect ratio (span\u00b2/area)\n    sweep_angle: Wing sweep angle in radians\n    efficiency: Span efficiency factor (0.8-1.0)\n\nReturns:\n    Lift coefficient"
      },
      {
        "tool_name": "drag_coefficient",
        "args": [
          "lift_coefficient",
          "aspect_ratio",
          "cd_zero",
          "efficiency"
        ],
        "doc": "Calculate drag coefficient using drag polar\n\nCD = CD0 + CL\u00b2/(\u03c0*e*AR)\n\nArgs:\n    lift_coefficient: Lift coefficient\n    aspect_ratio: Wing aspect ratio\n    cd_zero: Zero-lift drag coefficient\n    efficiency: Oswald efficiency factor\n\nReturns:\n    Total drag coefficient"
      },
      {
        "tool_name": "lift_drag_forces",
        "args": [
          "velocity",
          "altitude",
          "wing_area",
          "cl",
          "cd"
        ],
        "doc": "Calculate aerodynamic forces\n\nArgs:\n    velocity: Airspeed in m/s\n    altitude: Altitude in meters\n    wing_area: Wing reference area in m\u00b2\n    cl: Lift coefficient\n    cd: Drag coefficient\n\nReturns:\n    Dictionary with lift, drag, and L/D ratio"
      },
      {
        "tool_name": "mach_number",
        "args": [
          "velocity",
          "altitude"
        ],
        "doc": "Calculate Mach number\n\nArgs:\n    velocity: Airspeed in m/s\n    altitude: Altitude in meters\n\nReturns:\n    Mach number"
      },
      {
        "tool_name": "orbital_velocity",
        "args": [
          "radius",
          "central_mass"
        ],
        "doc": "Calculate circular orbital velocity\n\nv = \u221a(\u03bc/r)\n\nArgs:\n    radius: Orbital radius in meters\n    central_mass: Central body mass in kg (default: Earth)\n\nReturns:\n    Orbital velocity in m/s"
      },
      {
        "tool_name": "orbital_period",
        "args": [
          "semi_major_axis",
          "central_mass"
        ],
        "doc": "Calculate orbital period using Kepler's third law\n\nT = 2\u03c0\u221a(a\u00b3/\u03bc)\n\nArgs:\n    semi_major_axis: Semi-major axis in meters\n    central_mass: Central body mass in kg (default: Earth)\n\nReturns:\n    Period in seconds"
      },
      {
        "tool_name": "hohmann_transfer",
        "args": [
          "r1",
          "r2"
        ],
        "doc": "Calculate Hohmann transfer orbit parameters\n\nArgs:\n    r1: Initial orbit radius in meters\n    r2: Final orbit radius in meters\n\nReturns:\n    Dictionary with delta-v requirements and transfer time"
      },
      {
        "tool_name": "vis_viva_equation",
        "args": [
          "radius",
          "semi_major_axis"
        ],
        "doc": "Calculate orbital velocity at any point using vis-viva equation\n\nv\u00b2 = \u03bc(2/r - 1/a)\n\nArgs:\n    radius: Current radius in meters\n    semi_major_axis: Semi-major axis in meters\n\nReturns:\n    Velocity in m/s"
      },
      {
        "tool_name": "escape_velocity",
        "args": [
          "radius",
          "central_mass"
        ],
        "doc": "Calculate escape velocity\n\nv_escape = \u221a(2\u03bc/r)\n\nArgs:\n    radius: Distance from center in meters\n    central_mass: Central body mass in kg (default: Earth)\n\nReturns:\n    Escape velocity in m/s"
      },
      {
        "tool_name": "specific_impulse",
        "args": [
          "exhaust_velocity"
        ],
        "doc": "Calculate specific impulse from exhaust velocity\n\nIsp = v_e / g0\n\nArgs:\n    exhaust_velocity: Exhaust velocity in m/s\n\nReturns:\n    Specific impulse in seconds"
      },
      {
        "tool_name": "tsiolkovsky_equation",
        "args": [
          "delta_v",
          "specific_impulse",
          "initial_mass"
        ],
        "doc": "Calculate final mass using rocket equation\n\n\u0394v = Isp * g0 * ln(m0/mf)\n\nArgs:\n    delta_v: Required velocity change in m/s\n    specific_impulse: Specific impulse in seconds\n    initial_mass: Initial mass in kg\n\nReturns:\n    Final mass in kg"
      },
      {
        "tool_name": "propellant_mass_fraction",
        "args": [
          "delta_v",
          "specific_impulse"
        ],
        "doc": "Calculate propellant mass fraction for given delta-v\n\nArgs:\n    delta_v: Required velocity change in m/s\n    specific_impulse: Specific impulse in seconds\n\nReturns:\n    Propellant mass fraction (0-1)"
      },
      {
        "tool_name": "thrust_to_weight",
        "args": [
          "thrust",
          "mass",
          "altitude"
        ],
        "doc": "Calculate thrust-to-weight ratio\n\nArgs:\n    thrust: Thrust in Newtons\n    mass: Vehicle mass in kg\n    altitude: Altitude in meters\n\nReturns:\n    Thrust-to-weight ratio"
      },
      {
        "tool_name": "jet_engine_thrust",
        "args": [
          "mass_flow",
          "exit_velocity",
          "exit_pressure",
          "exit_area",
          "ambient_pressure"
        ],
        "doc": "Calculate jet engine thrust\n\nF = \u1e41*Ve + (Pe - Pa)*Ae\n\nArgs:\n    mass_flow: Mass flow rate in kg/s\n    exit_velocity: Exit velocity in m/s\n    exit_pressure: Exit pressure in Pa\n    exit_area: Nozzle exit area in m\u00b2\n    ambient_pressure: Ambient pressure in Pa\n\nReturns:\n    Thrust in Newtons"
      },
      {
        "tool_name": "range_equation",
        "args": [
          "velocity",
          "lift_to_drag",
          "specific_fuel_consumption",
          "initial_weight",
          "final_weight"
        ],
        "doc": "Calculate aircraft range using Breguet equation\n\nR = (V * L/D / SFC) * ln(W0/W1)\n\nArgs:\n    velocity: Cruise velocity in m/s\n    lift_to_drag: L/D ratio\n    specific_fuel_consumption: SFC in 1/s\n    initial_weight: Initial weight in N\n    final_weight: Final weight in N\n\nReturns:\n    Range in meters"
      },
      {
        "tool_name": "endurance_equation",
        "args": [
          "lift_to_drag",
          "specific_fuel_consumption",
          "initial_weight",
          "final_weight"
        ],
        "doc": "Calculate aircraft endurance\n\nE = (L/D / SFC) * ln(W0/W1)\n\nArgs:\n    lift_to_drag: L/D ratio\n    specific_fuel_consumption: SFC in 1/s\n    initial_weight: Initial weight in N\n    final_weight: Final weight in N\n\nReturns:\n    Endurance in seconds"
      },
      {
        "tool_name": "static_stability_margin",
        "args": [
          "cg_location",
          "neutral_point",
          "mean_chord"
        ],
        "doc": "Calculate static stability margin\n\nSM = (x_np - x_cg) / c\n\nArgs:\n    cg_location: Center of gravity location in meters\n    neutral_point: Neutral point location in meters\n    mean_chord: Mean aerodynamic chord in meters\n\nReturns:\n    Static margin (positive = stable)"
      },
      {
        "tool_name": "dutch_roll_frequency",
        "args": [
          "velocity",
          "wingspan",
          "yaw_damping",
          "directional_stability"
        ],
        "doc": "Calculate Dutch roll natural frequency\n\nArgs:\n    velocity: Airspeed in m/s\n    wingspan: Wingspan in meters\n    yaw_damping: Yaw damping derivative\n    directional_stability: Directional stability derivative\n\nReturns:\n    Dutch roll frequency in rad/s"
      },
      {
        "tool_name": "phugoid_period",
        "args": [
          "velocity"
        ],
        "doc": "Calculate phugoid oscillation period\n\nT = 0.138 * V (approximate formula in SI units)\n\nArgs:\n    velocity: Airspeed in m/s\n\nReturns:\n    Period in seconds"
      },
      {
        "tool_name": "beam_stress",
        "args": [
          "moment",
          "distance",
          "inertia"
        ],
        "doc": "Calculate bending stress in structural member\n\n\u03c3 = M*y/I\n\nArgs:\n    moment: Bending moment in N\u00b7m\n    distance: Distance from neutral axis in meters\n    inertia: Second moment of inertia in m\u2074\n\nReturns:\n    Stress in Pa"
      },
      {
        "tool_name": "wing_loading",
        "args": [
          "weight",
          "wing_area"
        ],
        "doc": "Calculate wing loading\n\nW/S = Weight / Wing_Area\n\nArgs:\n    weight: Aircraft weight in N\n    wing_area: Wing area in m\u00b2\n\nReturns:\n    Wing loading in N/m\u00b2"
      },
      {
        "tool_name": "stall_speed",
        "args": [
          "weight",
          "wing_area",
          "cl_max",
          "altitude"
        ],
        "doc": "Calculate stall speed\n\nV_stall = \u221a(2W/(\u03c1*S*CL_max))\n\nArgs:\n    weight: Aircraft weight in N\n    wing_area: Wing area in m\u00b2\n    cl_max: Maximum lift coefficient\n    altitude: Altitude in meters\n\nReturns:\n    Stall speed in m/s"
      },
      {
        "tool_name": "turn_radius",
        "args": [
          "velocity",
          "bank_angle"
        ],
        "doc": "Calculate turning radius for coordinated turn\n\nr = V\u00b2/(g*tan(\u03c6))\n\nArgs:\n    velocity: Airspeed in m/s\n    bank_angle: Bank angle in radians\n\nReturns:\n    Turn radius in meters"
      },
      {
        "tool_name": "load_factor",
        "args": [
          "bank_angle"
        ],
        "doc": "Calculate load factor in turn\n\nn = 1/cos(\u03c6)\n\nArgs:\n    bank_angle: Bank angle in radians\n\nReturns:\n    Load factor (g's)"
      },
      {
        "tool_name": "reynolds_number",
        "args": [
          "velocity",
          "characteristic_length",
          "altitude"
        ],
        "doc": "Calculate Reynolds number for aerodynamic analysis\n\nRe = \u03c1VL/\u03bc\n\nArgs:\n    velocity: Flow velocity in m/s\n    characteristic_length: Characteristic length in meters\n    altitude: Altitude in meters\n\nReturns:\n    Reynolds number"
      },
      {
        "tool_name": "heat_flux_reentry",
        "args": [
          "velocity",
          "altitude",
          "nose_radius"
        ],
        "doc": "Calculate stagnation point heat flux during atmospheric entry\n\nSimplified correlation: q = C * \u221a(\u03c1/r) * V\u00b3\n\nArgs:\n    velocity: Entry velocity in m/s\n    altitude: Altitude in meters\n    nose_radius: Nose radius in meters\n\nReturns:\n    Heat flux in W/m\u00b2"
      },
      {
        "tool_name": "trajectory_simulation",
        "args": [
          "initial_conditions",
          "vehicle_params",
          "time_span",
          "time_steps"
        ],
        "doc": "Simulate 2D trajectory with drag\n\nArgs:\n    initial_conditions: Dict with 'velocity', 'altitude', 'flight_path_angle'\n    vehicle_params: Dict with 'mass', 'area', 'cd'\n    time_span: Tuple of (start_time, end_time) in seconds\n    time_steps: Number of time steps\n\nReturns:\n    Dictionary with time, altitude, velocity, and range arrays"
      }
    ]
  },
  {
    "id": "astrophysics_lab.py",
    "name": "Astrophysics",
    "description": "Advanced astrophysics calculations for stellar evolution and cosmology",
    "capabilities": [
      {
        "tool_name": "lane_emden_solver",
        "args": [
          "n",
          "xi_max"
        ],
        "doc": "Solve Lane-Emden equation for polytropic stellar structure\nd\u00b2\u03b8/d\u03be\u00b2 + (2/\u03be)d\u03b8/d\u03be + \u03b8\u207f = 0\n\nArgs:\n    n: Polytropic index (1.5 for convective, 3 for radiative)\n    xi_max: Maximum dimensionless radius\n\nReturns:\n    Dictionary with xi, theta, and derivatives"
      },
      {
        "tool_name": "stellar_structure_integration",
        "args": [
          "M_star",
          "composition"
        ],
        "doc": "Integrate stellar structure equations from center to surface\n\nArgs:\n    M_star: Stellar mass in solar masses\n    composition: {'X': H fraction, 'Y': He fraction, 'Z': metallicity}\n\nReturns:\n    Radial profiles of mass, pressure, temperature, luminosity"
      },
      {
        "tool_name": "nbody_gravitational_dynamics",
        "args": [
          "masses",
          "positions",
          "velocities",
          "dt",
          "steps"
        ],
        "doc": "N-body gravitational simulation using Verlet integration\n\nArgs:\n    masses: Array of masses (kg)\n    positions: Initial positions (m) shape (n_bodies, 3)\n    velocities: Initial velocities (m/s) shape (n_bodies, 3)\n    dt: Time step (s)\n    steps: Number of integration steps\n\nReturns:\n    Trajectories and energies over time"
      },
      {
        "tool_name": "hubble_flow_cosmology",
        "args": [
          "z"
        ],
        "doc": "Calculate cosmological distances and times for given redshift\n\nArgs:\n    z: Redshift\n\nReturns:\n    Cosmological parameters at redshift z"
      },
      {
        "tool_name": "spectral_classification",
        "args": [
          "temperature",
          "luminosity"
        ],
        "doc": "Stellar spectral classification and HR diagram position\n\nArgs:\n    temperature: Effective temperature (K)\n    luminosity: Luminosity (solar units)\n\nReturns:\n    Spectral class and stellar parameters"
      },
      {
        "tool_name": "gravitational_lensing",
        "args": [
          "M_lens",
          "D_l",
          "D_s"
        ],
        "doc": "Calculate gravitational lensing parameters\n\nArgs:\n    M_lens: Mass of lens (solar masses)\n    D_l: Distance to lens (Mpc)\n    D_s: Distance to source (Mpc)\n\nReturns:\n    Einstein radius and lensing parameters"
      },
      {
        "tool_name": "schwarzschild_metric",
        "args": [
          "M",
          "r"
        ],
        "doc": "Calculate Schwarzschild metric components around black hole\n\nArgs:\n    M: Black hole mass (solar masses)\n    r: Radial coordinates (Schwarzschild radii)\n\nReturns:\n    Metric components and orbital parameters"
      },
      {
        "tool_name": "cepheid_period_luminosity",
        "args": [
          "period_days",
          "metallicity"
        ],
        "doc": "Cepheid variable period-luminosity relation for distance measurement\n\nArgs:\n    period_days: Pulsation period in days\n    metallicity: Metallicity (Z)\n\nReturns:\n    Absolute magnitude"
      },
      {
        "tool_name": "type_ia_supernova_luminosity",
        "args": [
          "stretch_factor"
        ],
        "doc": "Type Ia supernova standardizable candle luminosity\n\nArgs:\n    stretch_factor: Light curve stretch parameter\n\nReturns:\n    Peak absolute magnitude"
      },
      {
        "tool_name": "tidal_disruption_radius",
        "args": [
          "M_bh",
          "M_star",
          "R_star"
        ],
        "doc": "Calculate tidal disruption radius for a star near a black hole\n\nArgs:\n    M_bh: Black hole mass (solar masses)\n    M_star: Star mass (solar masses)\n    R_star: Star radius (solar radii)\n\nReturns:\n    Tidal disruption radius in solar radii"
      },
      {
        "tool_name": "virial_theorem_cluster",
        "args": [
          "velocity_dispersion",
          "radius"
        ],
        "doc": "Calculate cluster mass using virial theorem\n\nArgs:\n    velocity_dispersion: RMS velocity (m/s)\n    radius: Cluster radius (Mpc)\n\nReturns:\n    Total mass in solar masses"
      },
      {
        "tool_name": "demonstrate",
        "args": [],
        "doc": "Demonstrate all astrophysics calculations"
      }
    ]
  },
  {
    "id": "medical_imaging_lab.py",
    "name": "Medical Imaging",
    "description": "Advanced medical imaging simulation laboratory.\n\nFeatures:\n- CT: Radon transform, filtered backprojection, beam hardening\n- MRI: Bloch equations, T1/T2 relaxation, k-space sampling\n- Ultrasound: Wave propagation, beamforming, Doppler\n- Image quality metrics: SNR, CNR, MTF, NPS\n- Artifact simulation and correction",
    "capabilities": [
      {
        "tool_name": "generate_phantom",
        "args": [
          "size",
          "phantom_type"
        ],
        "doc": "Generate standard imaging phantom for testing.\n\nArgs:\n    size: Image size\n    phantom_type: Type of phantom\n\nReturns:\n    2D phantom array"
      },
      {
        "tool_name": "ct_forward_projection",
        "args": [
          "image",
          "angles"
        ],
        "doc": "Compute Radon transform (CT forward projection).\n\nBased on: Kak & Slaney (1988) \"Principles of Computerized Tomographic Imaging\"\n\nArgs:\n    image: 2D image\n    angles: Projection angles in degrees\n\nReturns:\n    Sinogram (projections x detectors)"
      },
      {
        "tool_name": "ct_filtered_backprojection",
        "args": [
          "sinogram",
          "angles",
          "filter_type"
        ],
        "doc": "Filtered backprojection reconstruction.\n\nStandard CT reconstruction algorithm.\n\nArgs:\n    sinogram: Projection data\n    angles: Projection angles\n    filter_type: Reconstruction filter\n\nReturns:\n    Reconstructed image"
      },
      {
        "tool_name": "ct_simulate_scan",
        "args": [
          "phantom",
          "params"
        ],
        "doc": "Simulate complete CT scan with artifacts.\n\nArgs:\n    phantom: Input phantom\n    params: CT parameters\n\nReturns:\n    Dictionary with sinogram and reconstructed image"
      },
      {
        "tool_name": "mri_bloch_equation_solver",
        "args": [
          "M0",
          "T1",
          "T2",
          "time",
          "B1"
        ],
        "doc": "Solve Bloch equations for MRI signal evolution.\n\nBloch equations describe nuclear magnetization dynamics.\n\nArgs:\n    M0: Equilibrium magnetization\n    T1: Longitudinal relaxation time (ms)\n    T2: Transverse relaxation time (ms)\n    time: Time points (ms)\n    B1: RF pulse amplitude (\u03bcT)\n\nReturns:\n    Magnetization vector over time"
      },
      {
        "tool_name": "mri_generate_kspace",
        "args": [
          "image",
          "params"
        ],
        "doc": "Generate k-space data from image.\n\nk-space is the Fourier domain of the MR image.\n\nArgs:\n    image: Spatial domain image\n    params: MRI parameters\n\nReturns:\n    Complex k-space data"
      },
      {
        "tool_name": "mri_reconstruct_from_kspace",
        "args": [
          "kspace"
        ],
        "doc": "Reconstruct image from k-space data.\n\nArgs:\n    kspace: Complex k-space data\n\nReturns:\n    Magnitude image"
      },
      {
        "tool_name": "mri_simulate_scan",
        "args": [
          "phantom",
          "tissue_params",
          "params"
        ],
        "doc": "Simulate MRI acquisition with tissue contrast.\n\nArgs:\n    phantom: Tissue type map\n    tissue_params: T1/T2 values for each tissue\n    params: MRI parameters\n\nReturns:\n    Dictionary with k-space and images"
      },
      {
        "tool_name": "ultrasound_wave_propagation",
        "args": [
          "medium",
          "frequency",
          "speed_of_sound"
        ],
        "doc": "Simulate ultrasound wave propagation.\n\nBased on: Szabo (2014) \"Diagnostic Ultrasound Imaging\"\n\nArgs:\n    medium: Acoustic impedance map\n    frequency: Ultrasound frequency (MHz)\n    speed_of_sound: m/s\n\nReturns:\n    RF signal"
      },
      {
        "tool_name": "ultrasound_beamforming",
        "args": [
          "rf_data",
          "num_elements",
          "focus_depth"
        ],
        "doc": "Apply delay-and-sum beamforming.\n\nStandard ultrasound image formation technique.\n\nArgs:\n    rf_data: Raw RF data\n    num_elements: Number of transducer elements\n    focus_depth: Focus depth in mm\n\nReturns:\n    Beamformed image"
      },
      {
        "tool_name": "ultrasound_doppler_processing",
        "args": [
          "rf_data",
          "prf",
          "angle"
        ],
        "doc": "Process Doppler ultrasound for flow measurement.\n\nArgs:\n    rf_data: RF data from multiple pulses\n    prf: Pulse repetition frequency (Hz)\n    angle: Doppler angle (degrees)\n\nReturns:\n    Dictionary with Doppler measurements"
      },
      {
        "tool_name": "calculate_snr",
        "args": [
          "image",
          "signal_roi",
          "noise_roi"
        ],
        "doc": "Calculate signal-to-noise ratio.\n\nArgs:\n    image: Input image\n    signal_roi: Signal region (x, y, width, height)\n    noise_roi: Noise region\n\nReturns:\n    SNR in dB"
      },
      {
        "tool_name": "calculate_cnr",
        "args": [
          "image",
          "roi1",
          "roi2"
        ],
        "doc": "Calculate contrast-to-noise ratio.\n\nArgs:\n    image: Input image\n    roi1: First region\n    roi2: Second region\n\nReturns:\n    CNR"
      },
      {
        "tool_name": "calculate_mtf",
        "args": [
          "edge_image"
        ],
        "doc": "Calculate modulation transfer function from edge image.\n\nMTF measures spatial resolution.\n\nArgs:\n    edge_image: Image of sharp edge\n\nReturns:\n    Spatial frequencies and MTF values"
      },
      {
        "tool_name": "simulate_artifacts",
        "args": [
          "image",
          "artifact_type"
        ],
        "doc": "Simulate common imaging artifacts.\n\nArgs:\n    image: Input image\n    artifact_type: Type of artifact\n\nReturns:\n    Image with artifact"
      },
      {
        "tool_name": "demo",
        "args": [],
        "doc": "Demonstrate medical imaging simulations."
      }
    ]
  },
  {
    "id": "climate_modeling_lab.py",
    "name": "Climate Modeling",
    "description": "Advanced climate system modeling laboratory.\nImplements simplified GCM physics, carbon cycle, and climate projections.",
    "capabilities": [
      {
        "tool_name": "calculate_radiative_forcing",
        "args": [
          "co2_ppm",
          "ch4_ppb",
          "n2o_ppb"
        ],
        "doc": "Calculate total radiative forcing from greenhouse gases.\nUses Myhre et al. (1998) expressions."
      },
      {
        "tool_name": "energy_balance_model",
        "args": [
          "forcing",
          "temperature",
          "dt"
        ],
        "doc": "Simple energy balance model with ocean heat uptake.\ndT/dt = (F - \u03bbT - H) / C"
      },
      {
        "tool_name": "carbon_cycle_model",
        "args": [
          "emissions",
          "temperature",
          "dt"
        ],
        "doc": "Box model of global carbon cycle with temperature feedbacks.\nTracks atmosphere, ocean, vegetation, and soil carbon pools."
      },
      {
        "tool_name": "ice_sheet_dynamics",
        "args": [
          "temperature"
        ],
        "doc": "Simple ice sheet model for Greenland and Antarctica.\nReturns melt rates and sea level contribution."
      },
      {
        "tool_name": "cloud_feedback_parameterization",
        "args": [
          "temperature"
        ],
        "doc": "Parameterized cloud feedback based on CMIP6 models.\nReturns change in cloud radiative effect (W/m\u00b2)."
      },
      {
        "tool_name": "extreme_weather_frequency",
        "args": [
          "temperature"
        ],
        "doc": "Statistical model for extreme weather event frequency.\nBased on shifted probability distributions."
      },
      {
        "tool_name": "tipping_point_assessment",
        "args": [
          "temperature"
        ],
        "doc": "Assess proximity to climate tipping points.\nReturns risk levels and probabilities."
      },
      {
        "tool_name": "run_projection",
        "args": [
          "scenario",
          "years",
          "dt"
        ],
        "doc": "Run climate projection for given scenario.\nReturns time series of key climate variables."
      },
      {
        "tool_name": "climate_sensitivity_analysis",
        "args": [
          "co2_doubling"
        ],
        "doc": "Analyze climate sensitivity to CO2 doubling.\nIncludes fast and slow feedbacks."
      },
      {
        "tool_name": "demo",
        "args": [],
        "doc": "Demonstrate climate modeling capabilities"
      }
    ]
  },
  {
    "id": "developmental_biology_lab.py",
    "name": "Developmental Biology",
    "description": "Production-ready developmental biology simulation laboratory.",
    "capabilities": [
      {
        "tool_name": "initialize_embryo",
        "args": [
          "initial_cells"
        ],
        "doc": "Initialize embryonic tissue with stem cells."
      },
      {
        "tool_name": "create_morphogen_gradient",
        "args": [
          "source_position",
          "morphogen_name",
          "production_rate",
          "decay_rate"
        ],
        "doc": "Create morphogen gradient from source."
      },
      {
        "tool_name": "reaction_diffusion_step",
        "args": [
          "u",
          "v",
          "Du",
          "Dv",
          "F",
          "k"
        ],
        "doc": "Gray-Scott reaction-diffusion system for pattern formation."
      },
      {
        "tool_name": "turing_pattern_formation",
        "args": [
          "iterations"
        ],
        "doc": "Generate Turing patterns for skin/fur patterns."
      },
      {
        "tool_name": "cell_differentiation",
        "args": [
          "cell_position",
          "morphogen_concentrations"
        ],
        "doc": "Determine cell fate based on morphogen concentrations."
      },
      {
        "tool_name": "simulate_gastrulation",
        "args": [],
        "doc": "Simulate gastrulation - formation of three germ layers."
      },
      {
        "tool_name": "simulate_neurulation",
        "args": [
          "ectoderm_mask"
        ],
        "doc": "Simulate neural tube formation from ectoderm."
      },
      {
        "tool_name": "simulate_somitogenesis",
        "args": [
          "num_somites"
        ],
        "doc": "Simulate somite formation (segmentation clock)."
      },
      {
        "tool_name": "simulate_angiogenesis",
        "args": [
          "vegf_source",
          "iterations"
        ],
        "doc": "Simulate blood vessel formation through sprouting angiogenesis."
      },
      {
        "tool_name": "simulate_organogenesis",
        "args": [
          "organ_type"
        ],
        "doc": "Simulate organ development."
      },
      {
        "tool_name": "calculate_tissue_mechanics",
        "args": [
          "cell_positions",
          "k_spring",
          "rest_length"
        ],
        "doc": "Calculate mechanical forces between cells."
      },
      {
        "tool_name": "simulate_morphogen_dynamics",
        "args": [
          "production_sites",
          "decay_rate"
        ],
        "doc": "Simulate morphogen diffusion and decay over time."
      },
      {
        "tool_name": "track_cell_lineage",
        "args": [
          "parent_id",
          "daughter_ids",
          "division_time"
        ],
        "doc": "Track cell division and lineage."
      },
      {
        "tool_name": "gene_regulatory_network",
        "args": [
          "current_expression",
          "signals"
        ],
        "doc": "Simulate gene regulatory network dynamics."
      },
      {
        "tool_name": "run_comprehensive_simulation",
        "args": [],
        "doc": "Run complete developmental biology simulation."
      }
    ]
  },
  {
    "id": "autonomous_algorithm_improvement_lab.py",
    "name": "Autonomous Algorithm Improvement",
    "description": "Autonomous Algorithm Improvement Laboratory\n\nThis lab autonomously:\n1. Generates novel algorithms through genetic programming\n2. Tests and benchmarks performance\n3. Evolves algorithms across generations\n4. Discovers optimizations and improvements\n5. Self-modifies to improve the improvement process itself",
    "capabilities": [
      {
        "tool_name": "generate_initial_population",
        "args": [],
        "doc": "Generate initial population of algorithm organisms"
      },
      {
        "tool_name": "evaluate_fitness",
        "args": [
          "organism"
        ],
        "doc": "Evaluate fitness of an algorithm organism"
      },
      {
        "tool_name": "tournament_selection",
        "args": [
          "population",
          "fitness_scores"
        ],
        "doc": "Tournament selection for parent selection"
      },
      {
        "tool_name": "evolve_generation",
        "args": [],
        "doc": "Evolve one generation of algorithms"
      },
      {
        "tool_name": "meta_learn_from_history",
        "args": [],
        "doc": "Learn from improvement history to optimize the improvement process"
      },
      {
        "tool_name": "self_modify_improvement_process",
        "args": [],
        "doc": "Modify own improvement parameters based on meta-learnings"
      },
      {
        "tool_name": "run_autonomous_improvement",
        "args": [
          "max_runtime_seconds"
        ],
        "doc": "Run fully autonomous improvement process\n\nThe system will:\n1. Generate initial population\n2. Evolve algorithms for multiple generations\n3. Learn from its own performance\n4. Self-modify to improve the improvement process\n5. Archive innovations\n6. Report findings"
      }
    ]
  },
  {
    "id": "protein_folding_lab_lab.py",
    "name": "Protein Folding Lab",
    "description": "",
    "capabilities": [
      {
        "tool_name": "calculate_total_energy",
        "args": [],
        "doc": "Calculate the total potential energy of the protein."
      },
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Run a basic simulation."
      }
    ]
  },
  {
    "id": "proteomics_lab.py",
    "name": "Proteomics",
    "description": "Production-ready proteomics analysis laboratory.",
    "capabilities": [
      {
        "tool_name": "calculate_peptide_mass",
        "args": [
          "sequence",
          "charge",
          "modifications"
        ],
        "doc": "Calculate theoretical m/z for a peptide."
      },
      {
        "tool_name": "digest_protein",
        "args": [
          "protein_sequence",
          "enzyme"
        ],
        "doc": "In silico protein digestion."
      },
      {
        "tool_name": "generate_theoretical_spectrum",
        "args": [
          "peptide"
        ],
        "doc": "Generate theoretical b and y ion series for a peptide."
      },
      {
        "tool_name": "score_peptide_spectrum_match",
        "args": [
          "experimental_mz",
          "experimental_intensity",
          "peptide",
          "charge"
        ],
        "doc": "Score peptide-spectrum match using XCorr algorithm."
      },
      {
        "tool_name": "database_search",
        "args": [
          "spectrum_mz",
          "spectrum_intensity",
          "precursor_mz",
          "precursor_charge",
          "protein_database"
        ],
        "doc": "Search MS/MS spectrum against protein database."
      },
      {
        "tool_name": "detect_modifications",
        "args": [
          "peptide",
          "experimental_mz",
          "experimental_intensity"
        ],
        "doc": "Detect post-translational modifications in peptide."
      },
      {
        "tool_name": "quantify_proteins_labelfree",
        "args": [
          "peptide_intensities"
        ],
        "doc": "Label-free quantification using spectral counting or intensity-based."
      },
      {
        "tool_name": "quantify_proteins_itraq",
        "args": [
          "reporter_intensities",
          "channel_labels"
        ],
        "doc": "iTRAQ/TMT quantification using reporter ions."
      },
      {
        "tool_name": "calculate_protein_coverage",
        "args": [
          "protein_sequence",
          "identified_peptides"
        ],
        "doc": "Calculate sequence coverage of protein."
      },
      {
        "tool_name": "calculate_fdr",
        "args": [
          "target_scores",
          "decoy_scores",
          "threshold"
        ],
        "doc": "Calculate False Discovery Rate using target-decoy approach."
      },
      {
        "tool_name": "deisotope_spectrum",
        "args": [
          "mz_array",
          "intensity_array"
        ],
        "doc": "Remove isotopic peaks from spectrum."
      },
      {
        "tool_name": "detect_charge_state",
        "args": [
          "mz_array",
          "intensity_array"
        ],
        "doc": "Detect charge states of peaks using isotope spacing."
      },
      {
        "tool_name": "perform_peak_picking",
        "args": [
          "mz_array",
          "intensity_array",
          "snr_threshold"
        ],
        "doc": "Advanced peak picking with noise estimation."
      },
      {
        "tool_name": "align_retention_times",
        "args": [
          "rt_sample1",
          "rt_sample2",
          "mz_common"
        ],
        "doc": "Align retention times between samples using dynamic time warping."
      },
      {
        "tool_name": "run_comprehensive_analysis",
        "args": [
          "proteins",
          "spectra"
        ],
        "doc": "Run complete proteomics analysis pipeline."
      }
    ]
  },
  {
    "id": "materials_lab.py",
    "name": "Materials",
    "description": "Main Materials Science Laboratory API\n\nProvides unified interface for:\n- Material database access (1000+ materials)\n- Material testing simulations\n- Material design and optimization\n- Property prediction with ML",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a materials science experiment.\n\nArgs:\n    experiment_spec: Dictionary specifying the experiment.\n        Required keys:\n        - 'experiment_type': str (e.g., 'tensile', 'compression', 'hardness')\n        - 'material_name': str\n        Other keys are passed as kwargs to the respective test method.\n\nReturns:\n    A dictionary containing the experiment results."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get the current status of the Materials Lab.\nFor MaterialsLab, this returns the database statistics."
      },
      {
        "tool_name": "validate_material_properties",
        "args": [
          "material_name",
          "properties"
        ],
        "doc": "Validate a material's tabulated properties against reference data.\n\nArgs:\n    material_name: Name used in the materials database.\n    properties: Optional iterable of property names to validate. If\n        omitted, all mapped properties for the material are checked.\n    raise_on_missing: When True, raise a ValueError if the material or\n        requested property does not have a configured reference datum.\n\nReturns:\n    Mapping of property name to ValidationResult."
      },
      {
        "tool_name": "validate_accuracy_suite",
        "args": [],
        "doc": "Run the configured accuracy suite for all mapped materials.\n\nReturns:\n    Nested mapping of material -> property -> ValidationResult."
      },
      {
        "tool_name": "get_material",
        "args": [
          "name"
        ],
        "doc": "Get material by name"
      },
      {
        "tool_name": "search_materials",
        "args": [],
        "doc": "Search materials by criteria"
      },
      {
        "tool_name": "list_categories",
        "args": [],
        "doc": "List all material categories"
      },
      {
        "tool_name": "list_materials",
        "args": [
          "category"
        ],
        "doc": "List material names, optionally filtered by category."
      },
      {
        "tool_name": "get_statistics",
        "args": [],
        "doc": "Get database statistics"
      },
      {
        "tool_name": "get_material_profile",
        "args": [
          "material_name"
        ],
        "doc": "Generate a detailed property profile with curves and metadata."
      },
      {
        "tool_name": "get_material_safety",
        "args": [
          "material_name"
        ],
        "doc": "Return MSDS-style safety information if available."
      },
      {
        "tool_name": "register_calibration",
        "args": [
          "material_name",
          "test_type",
          "property_name",
          "reference_value",
          "measured_value"
        ],
        "doc": "Register calibration measurement."
      },
      {
        "tool_name": "get_calibration_summary",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "simulate_ice_growth",
        "args": [
          "material_name",
          "temperature_k",
          "relative_humidity",
          "duration_hours"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "run_batch_experiments",
        "args": [
          "batch_specs"
        ],
        "doc": "Run multiple experiments and return serialisable summaries."
      },
      {
        "tool_name": "tensile_test",
        "args": [
          "material_name"
        ],
        "doc": "Run tensile test"
      },
      {
        "tool_name": "compression_test",
        "args": [
          "material_name"
        ],
        "doc": "Run compression test"
      },
      {
        "tool_name": "fatigue_test",
        "args": [
          "material_name"
        ],
        "doc": "Run fatigue test"
      },
      {
        "tool_name": "impact_test",
        "args": [
          "material_name"
        ],
        "doc": "Run impact test"
      },
      {
        "tool_name": "hardness_test",
        "args": [
          "material_name"
        ],
        "doc": "Run hardness test"
      },
      {
        "tool_name": "thermal_test",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "Run thermal test"
      },
      {
        "tool_name": "corrosion_test",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "Run corrosion test"
      },
      {
        "tool_name": "environmental_test",
        "args": [
          "material_name"
        ],
        "doc": "Run environmental test"
      },
      {
        "tool_name": "optimize_alloy",
        "args": [
          "base_elements",
          "target_properties"
        ],
        "doc": "Optimize alloy composition"
      },
      {
        "tool_name": "design_composite",
        "args": [
          "fiber_name",
          "matrix_name"
        ],
        "doc": "Design composite material"
      },
      {
        "tool_name": "add_nanoparticles",
        "args": [
          "base_material_name"
        ],
        "doc": "Add nanoparticles to material"
      },
      {
        "tool_name": "apply_coating",
        "args": [
          "base_material_name"
        ],
        "doc": "Apply surface coating"
      },
      {
        "tool_name": "design_lattice",
        "args": [
          "base_material_name"
        ],
        "doc": "Design lattice structure for AM"
      },
      {
        "tool_name": "predict_from_composition",
        "args": [
          "composition",
          "properties"
        ],
        "doc": "Predict properties from composition"
      },
      {
        "tool_name": "predict_from_structure",
        "args": [
          "crystal_structure",
          "bonding_type",
          "properties"
        ],
        "doc": "Predict properties from structure"
      },
      {
        "tool_name": "predict_by_similarity",
        "args": [
          "reference_material_name",
          "property_name"
        ],
        "doc": "Predict property by similarity"
      },
      {
        "tool_name": "compare_materials",
        "args": [
          "material_names",
          "properties"
        ],
        "doc": "Compare multiple materials"
      },
      {
        "tool_name": "find_best_material",
        "args": [
          "category",
          "optimize_for",
          "constraints"
        ],
        "doc": "Find best material for application\n\nArgs:\n    category: Material category to search\n    optimize_for: Property to maximize\n    constraints: Dict of property constraints (min/max values)"
      }
    ]
  },
  {
    "id": "molecular_biology_lab.py",
    "name": "Molecular Biology",
    "description": "Main molecular biology laboratory interface",
    "capabilities": [
      {
        "tool_name": "analyze_sequence",
        "args": [
          "sequence",
          "sequence_type"
        ],
        "doc": "Comprehensive sequence analysis"
      },
      {
        "tool_name": "design_primers",
        "args": [
          "template",
          "target_tm",
          "primer_length_range"
        ],
        "doc": "Design optimal PCR primers"
      },
      {
        "tool_name": "simulate_pcr",
        "args": [
          "template",
          "forward_primer",
          "reverse_primer",
          "cycles"
        ],
        "doc": "Simulate PCR amplification"
      },
      {
        "tool_name": "design_crispr_guides",
        "args": [
          "target",
          "top_n"
        ],
        "doc": "Design and score CRISPR guide RNAs"
      },
      {
        "tool_name": "model_gene_expression",
        "args": [
          "promoter_strength",
          "rbs_strength",
          "duration_hours"
        ],
        "doc": "Model gene expression dynamics"
      },
      {
        "tool_name": "enzyme_kinetics",
        "args": [
          "substrate_conc",
          "vmax",
          "km"
        ],
        "doc": "Calculate Michaelis-Menten enzyme kinetics"
      },
      {
        "tool_name": "calculate_molecular_weight",
        "args": [
          "sequence",
          "molecule_type"
        ],
        "doc": "Calculate molecular weight of DNA, RNA, or protein"
      }
    ]
  },
  {
    "id": "quantum_lab.py",
    "name": "Quantum",
    "description": "Unified quantum laboratory simulator.\n\nFeatures:\n- 30-qubit exact statevector simulation\n- Tensor network approximation for >30 qubits\n- Quantum chemistry integration\n- Materials science quantum calculations\n- Quantum sensor modeling\n- Cognition-inspired algorithms\n\nIntegration:\n- Wraps existing CircuitSimulator (30-qubit exact)\n- Wraps QuantumCognition (quantum-inspired)\n- Extends with chemistry, materials, sensors\n\nECH0 Usage Examples:\n```python\n# Basic circuit simulation\nlab = QuantumLabSimulator(num_qubits=5)\nlab.h(0)  # Hadamard on qubit 0\nlab.cnot(0, 1)  # Entangle qubits\nresults = lab.measure_all()\n\n# Chemistry calculation\nfrom quantum_chemistry import Molecule\nh2 = Molecule.hydrogen_molecule(bond_length=0.74)\nenergy = lab.chemistry.compute_ground_state_energy(h2)\n\n# Materials property\nenergy_gap = lab.materials.compute_band_gap(\"silicon\")\n\n# Quantum sensing\nsensitivity = lab.sensors.magnetometry_sensitivity(num_qubits=10)\n```",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a quantum experiment.\n\nExample spec:\n{\n    \"experiment_type\": \"bell_pair\",\n}\n{\n    \"experiment_type\": \"ghz_state\",\n    \"num_qubits\": 4\n}\n{\n    \"experiment_type\": \"custom_circuit\",\n    \"operations\": [\n        {\"gate\": \"h\", \"qubit\": 0},\n        {\"gate\": \"cnot\", \"control\": 0, \"target\": 1}\n    ]\n}"
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get information about current backend and state."
      },
      {
        "tool_name": "h",
        "args": [
          "qubit"
        ],
        "doc": "Apply Hadamard gate"
      },
      {
        "tool_name": "x",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-X gate"
      },
      {
        "tool_name": "y",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-Y gate"
      },
      {
        "tool_name": "z",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-Z gate"
      },
      {
        "tool_name": "rx",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RX rotation"
      },
      {
        "tool_name": "ry",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RY rotation"
      },
      {
        "tool_name": "rz",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RZ rotation"
      },
      {
        "tool_name": "cnot",
        "args": [
          "control",
          "target"
        ],
        "doc": "Apply CNOT gate"
      },
      {
        "tool_name": "cz",
        "args": [
          "control",
          "target"
        ],
        "doc": "Apply CZ gate"
      },
      {
        "tool_name": "measure",
        "args": [
          "qubit"
        ],
        "doc": "Measure single qubit"
      },
      {
        "tool_name": "measure_all",
        "args": [],
        "doc": "Measure all qubits"
      },
      {
        "tool_name": "get_probabilities",
        "args": [],
        "doc": "Get probability distribution"
      },
      {
        "tool_name": "expectation_value",
        "args": [
          "observable"
        ],
        "doc": "Compute expectation value of observable.\n\nArgs:\n    observable: Pauli string like 'Z0' or 'X0Y1Z2'\n\nReturns:\n    Expectation value <\u03c8|O|\u03c8>"
      },
      {
        "tool_name": "fidelity",
        "args": [
          "target_state"
        ],
        "doc": "Compute fidelity with target state.\n\nF = |<\u03c8|\u03c6>|\u00b2"
      },
      {
        "tool_name": "chemistry",
        "args": [],
        "doc": "Access quantum chemistry module"
      },
      {
        "tool_name": "materials",
        "args": [],
        "doc": "Access quantum materials module"
      },
      {
        "tool_name": "sensors",
        "args": [],
        "doc": "Access quantum sensors module"
      },
      {
        "tool_name": "reset",
        "args": [],
        "doc": "Reset quantum state to |0\u27e9^n"
      },
      {
        "tool_name": "print_state",
        "args": [
          "top_n"
        ],
        "doc": "Print quantum state"
      },
      {
        "tool_name": "get_backend_info",
        "args": [],
        "doc": "Get information about current backend"
      }
    ]
  },
  {
    "id": "biological_quantum_lab.py",
    "name": "Biological Quantum",
    "description": "QuLabInfinite interface to biological quantum computing.\n\nProvides high-level API for:\n- Quantum state manipulation\n- Algorithm execution (VQE, QAOA, annealing)\n- Biological system simulation (FMO)\n- Hardware control (coherence protection)\n- Experimental validation (2D spectroscopy)\n- Cross-platform benchmarking",
    "capabilities": [
      {
        "tool_name": "create_quantum_state",
        "args": [
          "n_qubits"
        ],
        "doc": "Create quantum state with n qubits."
      },
      {
        "tool_name": "create_bell_state",
        "args": [
          "state_type"
        ],
        "doc": "Create Bell state (maximally entangled 2-qubit state)."
      },
      {
        "tool_name": "create_ghz_state",
        "args": [
          "n_qubits"
        ],
        "doc": "Create GHZ state (maximally entangled n-qubit state)."
      },
      {
        "tool_name": "run_vqe",
        "args": [
          "hamiltonian",
          "n_qubits",
          "depth",
          "max_iterations"
        ],
        "doc": "Run Variational Quantum Eigensolver.\n\nArgs:\n    hamiltonian: Hamiltonian function H(state) -> energy\n    n_qubits: Number of qubits\n    depth: Circuit depth\n    max_iterations: Maximum optimization iterations\n\nReturns:\n    (ground_energy, optimal_parameters)"
      },
      {
        "tool_name": "run_qaoa",
        "args": [
          "cost_function",
          "n_qubits",
          "p",
          "num_samples",
          "max_iterations"
        ],
        "doc": "Run Quantum Approximate Optimization Algorithm.\n\nArgs:\n    cost_function: Classical cost function to minimize\n    n_qubits: Number of qubits\n    p: QAOA depth (number of alternating layers)\n    num_samples: Measurement samples per iteration\n    max_iterations: Maximum iterations\n\nReturns:\n    (best_cost, best_solution, optimal_parameters)"
      },
      {
        "tool_name": "run_quantum_annealing",
        "args": [
          "hamiltonian",
          "n_qubits",
          "annealing_time_fs",
          "temperature_K"
        ],
        "doc": "Run Quantum Annealing.\n\nArgs:\n    hamiltonian: Problem Hamiltonian\n    n_qubits: Number of qubits\n    annealing_time_fs: Total annealing time (femtoseconds)\n    temperature_K: Operating temperature\n\nReturns:\n    (solution_bitstring, energy)"
      },
      {
        "tool_name": "simulate_fmo",
        "args": [
          "initial_site",
          "final_site",
          "time_fs"
        ],
        "doc": "Simulate FMO complex energy transfer.\n\nArgs:\n    initial_site: Starting chromophore (1-7)\n    final_site: Target chromophore\n    time_fs: Simulation time (femtoseconds)\n\nReturns:\n    Transfer efficiency (probability)"
      },
      {
        "tool_name": "activate_ai_controlled_fmo",
        "args": [],
        "doc": "Activate AI-controlled FMO biological quantum computer.\n\nReturns:\n    AIControlledFMO instance"
      },
      {
        "tool_name": "activate_coherence_protection",
        "args": [],
        "doc": "Activate multi-material coherence protection system.\n\nReturns:\n    Protection status dictionary"
      },
      {
        "tool_name": "run_2d_spectroscopy",
        "args": [
          "population_time_fs"
        ],
        "doc": "Run 2D electronic spectroscopy on FMO complex.\n\nArgs:\n    population_time_fs: Population time (waiting time)\n\nReturns:\n    (omega1_axis, omega3_axis, spectrum_2d)"
      },
      {
        "tool_name": "benchmark",
        "args": [
          "platforms"
        ],
        "doc": "Run comprehensive benchmarks.\n\nArgs:\n    platforms: List of platforms to benchmark\n\nReturns:\n    Benchmark results dictionary"
      },
      {
        "tool_name": "thermal_noise_sampling",
        "args": [
          "n_qubits",
          "num_samples",
          "coherence_time_us"
        ],
        "doc": "Quantum random sampling using thermal noise.\n\nArgs:\n    n_qubits: Number of qubits\n    num_samples: Number of samples\n    coherence_time_us: Coherence time (microseconds)\n\nReturns:\n    Array of samples"
      },
      {
        "tool_name": "monte_carlo_integration",
        "args": [
          "function",
          "bounds",
          "num_samples",
          "n_qubits"
        ],
        "doc": "Quantum Monte Carlo integration.\n\nArgs:\n    function: Function to integrate\n    bounds: Integration bounds (a, b)\n    num_samples: Number of quantum samples\n    n_qubits: Number of qubits for sampling\n\nReturns:\n    (estimate, error)"
      }
    ]
  },
  {
    "id": "materials_chemistry_lab.py",
    "name": "Materials Chemistry",
    "description": "Advanced materials chemistry laboratory for comprehensive materials simulations.",
    "capabilities": [
      {
        "tool_name": "generate_lattice_vectors",
        "args": [
          "crystal"
        ],
        "doc": "Generate lattice vectors from crystallographic parameters.\nReturns 3x3 matrix where rows are lattice vectors."
      },
      {
        "tool_name": "generate_unit_cell",
        "args": [
          "crystal",
          "nx",
          "ny",
          "nz"
        ],
        "doc": "Generate atomic positions for a crystal unit cell.\nCan create supercells with nx, ny, nz repetitions."
      },
      {
        "tool_name": "calculate_volume",
        "args": [
          "crystal"
        ],
        "doc": "Calculate unit cell volume."
      },
      {
        "tool_name": "calculate_density",
        "args": [
          "material"
        ],
        "doc": "Calculate theoretical density from crystal structure."
      },
      {
        "tool_name": "binary_phase_diagram",
        "args": [
          "component1",
          "component2",
          "T_range",
          "eutectic_point"
        ],
        "doc": "Generate binary phase diagram data.\nSimplified model for eutectic systems."
      },
      {
        "tool_name": "lever_rule",
        "args": [
          "overall_composition",
          "T",
          "phase1_comp",
          "phase2_comp"
        ],
        "doc": "Apply lever rule to calculate phase fractions.\n\nReturns fraction of phase 1 and phase 2."
      },
      {
        "tool_name": "clausius_clapeyron",
        "args": [
          "T",
          "dH",
          "dV"
        ],
        "doc": "Calculate pressure change for phase transition using Clausius-Clapeyron equation.\n\ndP/dT = \u0394H / (T * \u0394V)"
      },
      {
        "tool_name": "vacancy_concentration",
        "args": [
          "formation_energy",
          "temperature"
        ],
        "doc": "Calculate equilibrium vacancy concentration.\n\nn_v/N = exp(-E_f / kT)"
      },
      {
        "tool_name": "schottky_defect_concentration",
        "args": [
          "formation_energy",
          "temperature"
        ],
        "doc": "Calculate Schottky defect concentration (cation-anion vacancy pair)."
      },
      {
        "tool_name": "frenkel_defect_concentration",
        "args": [
          "formation_energy",
          "temperature"
        ],
        "doc": "Calculate Frenkel defect concentration (vacancy-interstitial pair)."
      },
      {
        "tool_name": "kroger_vink_notation",
        "args": [
          "defect"
        ],
        "doc": "Generate Kr\u00f6ger-Vink notation for a defect.\n\nExamples: V_O^\u2022\u2022 (oxygen vacancy), Al_Si^\u2022 (Al on Si site)"
      },
      {
        "tool_name": "band_gap_temperature",
        "args": [
          "Eg0",
          "alpha",
          "beta",
          "temperature"
        ],
        "doc": "Calculate temperature-dependent band gap using Varshni equation.\n\nEg(T) = Eg0 - \u03b1*T\u00b2/(T + \u03b2)"
      },
      {
        "tool_name": "carrier_concentration",
        "args": [
          "band_gap",
          "effective_mass_e",
          "effective_mass_h",
          "temperature"
        ],
        "doc": "Calculate intrinsic carrier concentration.\n\nn_i = sqrt(N_c * N_v) * exp(-Eg/2kT)"
      },
      {
        "tool_name": "fermi_level",
        "args": [
          "E_c",
          "E_v",
          "n",
          "p",
          "N_c",
          "N_v",
          "temperature"
        ],
        "doc": "Calculate Fermi level position.\n\nFor intrinsic: E_F = (E_c + E_v)/2 + kT/2 * ln(N_v/N_c)"
      },
      {
        "tool_name": "bragg_angle",
        "args": [
          "d_spacing",
          "wavelength",
          "order"
        ],
        "doc": "Calculate Bragg angle for X-ray diffraction.\n\nn\u03bb = 2d*sin(\u03b8)"
      },
      {
        "tool_name": "d_spacing",
        "args": [
          "crystal",
          "h",
          "k",
          "l"
        ],
        "doc": "Calculate d-spacing for (hkl) plane.\n\nFor cubic: 1/d\u00b2 = (h\u00b2 + k\u00b2 + l\u00b2)/a\u00b2"
      },
      {
        "tool_name": "structure_factor",
        "args": [
          "atoms",
          "h",
          "k",
          "l"
        ],
        "doc": "Calculate structure factor F(hkl).\n\nF = \u03a3 f_j * exp(2\u03c0i(hx_j + ky_j + lz_j))"
      },
      {
        "tool_name": "powder_pattern",
        "args": [
          "material",
          "two_theta_range",
          "wavelength"
        ],
        "doc": "Simulate powder X-ray diffraction pattern."
      },
      {
        "tool_name": "bulk_modulus_voigt_reuss",
        "args": [
          "elastic_constants"
        ],
        "doc": "Calculate bulk modulus using Voigt and Reuss bounds.\n\nFor cubic: K = (C11 + 2*C12)/3"
      },
      {
        "tool_name": "hardness_estimation",
        "args": [
          "bulk_modulus",
          "shear_modulus"
        ],
        "doc": "Estimate Vickers hardness using Chen's model.\n\nH_v = 2(k\u00b2G)^0.585 - 3\nwhere k = G/B (Pugh's ratio)"
      },
      {
        "tool_name": "theoretical_strength",
        "args": [
          "young_modulus",
          "surface_energy",
          "lattice_parameter"
        ],
        "doc": "Estimate theoretical strength using Griffith criterion.\n\n\u03c3_th \u2248 sqrt(E*\u03b3/a)"
      },
      {
        "tool_name": "debye_temperature",
        "args": [
          "bulk_modulus",
          "molar_mass",
          "density",
          "n_atoms"
        ],
        "doc": "Estimate Debye temperature.\n\n\u03b8_D = (h/k) * v_s * (3n*N_A*\u03c1/4\u03c0M)^(1/3)"
      },
      {
        "tool_name": "heat_capacity_debye",
        "args": [
          "temperature",
          "debye_temp"
        ],
        "doc": "Calculate heat capacity using Debye model.\n\nC_v = 9R * (T/\u03b8_D)\u00b3 * \u222b[0 to \u03b8_D/T] x\u2074e^x/(e^x-1)\u00b2 dx"
      },
      {
        "tool_name": "thermal_expansion_coefficient",
        "args": [
          "gruneisen",
          "bulk_modulus",
          "heat_capacity",
          "molar_volume"
        ],
        "doc": "Calculate thermal expansion coefficient using Gr\u00fcneisen relation.\n\n\u03b1 = \u03b3 * C_v / (B * V_m)"
      },
      {
        "tool_name": "diffusion_coefficient",
        "args": [
          "D0",
          "activation_energy",
          "temperature"
        ],
        "doc": "Calculate diffusion coefficient using Arrhenius equation.\n\nD = D0 * exp(-E_a / RT)"
      },
      {
        "tool_name": "diffusion_profile",
        "args": [
          "x",
          "time",
          "D",
          "initial_conc"
        ],
        "doc": "Calculate concentration profile for diffusion (Fick's second law).\n\nSemi-infinite medium with constant surface concentration."
      },
      {
        "tool_name": "parabolic_growth",
        "args": [
          "time",
          "rate_constant"
        ],
        "doc": "Model parabolic growth law for oxidation/reaction layers.\n\nx\u00b2 = k*t (Wagner's theory)"
      },
      {
        "tool_name": "nanoparticle_melting_point",
        "args": [
          "bulk_melting",
          "particle_size",
          "surface_energy",
          "latent_heat"
        ],
        "doc": "Calculate melting point depression for nanoparticles (Gibbs-Thomson).\n\n\u0394T/T_m = 2\u03c3V_m / (\u0394H_f * r)"
      },
      {
        "tool_name": "nucleation_rate",
        "args": [
          "supersaturation",
          "surface_energy",
          "temperature"
        ],
        "doc": "Calculate homogeneous nucleation rate.\n\nJ = A * exp(-\u0394G*/kT)\nwhere \u0394G* = 16\u03c0\u03c3\u00b3v\u00b2/3(kT*ln(S))\u00b2"
      },
      {
        "tool_name": "ostwald_ripening",
        "args": [
          "initial_size",
          "time",
          "rate_constant"
        ],
        "doc": "Model Ostwald ripening (LSW theory).\n\nr\u00b3 - r0\u00b3 = K*t"
      },
      {
        "tool_name": "run_comprehensive_demo",
        "args": [],
        "doc": "Run comprehensive demonstration of materials chemistry capabilities."
      }
    ]
  },
  {
    "id": "metamaterial_electromagnetic_simulator_lab.py",
    "name": "Metamaterial Electromagnetic Simulator",
    "description": "Metamaterial Electromagnetic Simulator\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "cardiology_lab.py",
    "name": "Cardiology",
    "description": "Advanced cardiology simulation laboratory implementing real medical algorithms.\n\nFeatures:\n- ECG signal synthesis using physiological models\n- Arrhythmia detection via HRV and morphology analysis\n- Hemodynamic modeling with 3-element Windkessel model\n- Cardiac output and ejection fraction calculations\n- Spectral analysis for autonomic function",
    "capabilities": [
      {
        "tool_name": "generate_ecg_waveform",
        "args": [
          "duration",
          "params"
        ],
        "doc": "Generate realistic ECG waveform using sum of Gaussian functions.\n\nBased on: McSharry et al. (2003) \"A dynamical model for generating synthetic ECG signals\"\n\nArgs:\n    duration: Recording duration in seconds\n    params: ECG parameters or use defaults\n\nReturns:\n    time_array, ecg_signal in mV"
      },
      {
        "tool_name": "detect_r_peaks",
        "args": [
          "ecg_signal",
          "threshold_factor"
        ],
        "doc": "Detect R peaks using Pan-Tompkins algorithm.\n\nReference: Pan & Tompkins (1985) \"A Real-Time QRS Detection Algorithm\"\n\nArgs:\n    ecg_signal: ECG signal in mV\n    threshold_factor: Detection threshold as fraction of max\n\nReturns:\n    Array of R peak indices"
      },
      {
        "tool_name": "calculate_heart_rate_variability",
        "args": [
          "r_peaks"
        ],
        "doc": "Calculate HRV metrics from R peak positions.\n\nImplements time-domain and frequency-domain HRV analysis per\nTask Force guidelines (1996).\n\nArgs:\n    r_peaks: Indices of R peaks\n\nReturns:\n    Dictionary with HRV metrics"
      },
      {
        "tool_name": "detect_arrhythmias",
        "args": [
          "ecg_signal",
          "r_peaks"
        ],
        "doc": "Detect common arrhythmias using morphology and rhythm analysis.\n\nImplements detection for:\n- Atrial fibrillation (irregular RR intervals)\n- Premature ventricular contractions (wide QRS)\n- Bradycardia/Tachycardia\n\nArgs:\n    ecg_signal: ECG signal\n    r_peaks: R peak positions\n\nReturns:\n    Dictionary with detected arrhythmias"
      },
      {
        "tool_name": "windkessel_model",
        "args": [
          "time",
          "params"
        ],
        "doc": "3-element Windkessel model for arterial hemodynamics.\n\nModels arterial system as electrical circuit analog:\n- Compliance (capacitance)\n- Resistance\n- Characteristic impedance\n\nReference: Westerhof et al. (2009) \"The arterial Windkessel\"\n\nArgs:\n    time: Time array in seconds\n    params: Hemodynamic parameters\n\nReturns:\n    Dictionary with pressure and flow waveforms"
      },
      {
        "tool_name": "calculate_cardiac_output",
        "args": [
          "stroke_volume",
          "heart_rate"
        ],
        "doc": "Calculate cardiac output using standard formula.\n\nCO = SV \u00d7 HR\n\nArgs:\n    stroke_volume: mL per beat\n    heart_rate: Beats per minute\n\nReturns:\n    Cardiac output in L/min"
      },
      {
        "tool_name": "calculate_ejection_fraction",
        "args": [
          "end_diastolic_volume",
          "end_systolic_volume"
        ],
        "doc": "Calculate left ventricular ejection fraction.\n\nEF = (EDV - ESV) / EDV \u00d7 100\n\nNormal range: 55-70%\n\nArgs:\n    end_diastolic_volume: mL\n    end_systolic_volume: mL\n\nReturns:\n    Ejection fraction as percentage"
      },
      {
        "tool_name": "assess_cardiac_function",
        "args": [
          "ecg_signal",
          "blood_pressure"
        ],
        "doc": "Comprehensive cardiac function assessment.\n\nArgs:\n    ecg_signal: ECG recording\n    blood_pressure: (systolic, diastolic) in mmHg\n\nReturns:\n    Dictionary with cardiac metrics and interpretation"
      },
      {
        "tool_name": "simulate_exercise_response",
        "args": [
          "rest_hr",
          "max_hr_age",
          "exercise_duration"
        ],
        "doc": "Simulate cardiovascular response to exercise.\n\nModels HR, stroke volume, and cardiac output changes during exercise.\n\nArgs:\n    rest_hr: Resting heart rate (BPM)\n    max_hr_age: Age for max HR calculation\n    exercise_duration: Exercise duration in seconds\n\nReturns:\n    Dictionary with time series of cardiovascular parameters"
      },
      {
        "tool_name": "analyze_qt_interval",
        "args": [
          "ecg_signal",
          "r_peaks"
        ],
        "doc": "Analyze QT interval for Long QT Syndrome risk.\n\nCalculates QT, QTc (Bazett's formula), and risk assessment.\n\nArgs:\n    ecg_signal: ECG signal\n    r_peaks: R peak positions\n\nReturns:\n    Dictionary with QT metrics"
      },
      {
        "tool_name": "demo",
        "args": [],
        "doc": "Demonstrate comprehensive cardiology analysis."
      }
    ]
  },
  {
    "id": "oncology_lab.py",
    "name": "Oncology",
    "description": "Advanced oncology simulation laboratory",
    "capabilities": [
      {
        "tool_name": "gompertz_growth",
        "args": [
          "t",
          "v0",
          "alpha",
          "beta"
        ],
        "doc": "Gompertz tumor growth model - most accurate for solid tumors\ndV/dt = \u03b1 * V * ln(\u03b2/V)\n\nReference: Laird, A.K. (1964) British Journal of Cancer 18(3):490-502"
      },
      {
        "tool_name": "logistic_growth",
        "args": [
          "t",
          "v0",
          "r",
          "k"
        ],
        "doc": "Logistic tumor growth model\ndV/dt = r * V * (1 - V/K)\n\nReference: Verhulst, P.F. (1838) Correspondance math\u00e9matique et physique 10:113-121"
      },
      {
        "tool_name": "exponential_growth",
        "args": [
          "t",
          "v0",
          "r"
        ],
        "doc": "Simple exponential growth - early stage tumors only\ndV/dt = r * V\n\nReference: Skipper, H.E. (1964) Cancer Chemotherapy Reports 45:5-28"
      },
      {
        "tool_name": "bertalanffy_growth",
        "args": [
          "t",
          "v0",
          "a",
          "b"
        ],
        "doc": "Von Bertalanffy growth model - accounts for metabolism\ndV/dt = a * V^(2/3) - b * V\n\nReference: von Bertalanffy, L. (1957) Quarterly Review of Biology 32(3):217-231"
      },
      {
        "tool_name": "hill_drug_response",
        "args": [
          "concentration",
          "drug"
        ],
        "doc": "Hill equation for drug dose-response\nE = Emax * C^n / (IC50^n + C^n)\n\nReference: Hill, A.V. (1910) Journal of Physiology 40:190-224"
      },
      {
        "tool_name": "emax_model",
        "args": [
          "concentration",
          "emax",
          "ec50",
          "gamma"
        ],
        "doc": "Emax pharmacodynamic model\nE = Emax * C^\u03b3 / (EC50^\u03b3 + C^\u03b3)\n\nReference: Holford, N.H. & Sheiner, L.B. (1981) Clinical Pharmacokinetics 6(6):429-453"
      },
      {
        "tool_name": "bliss_independence",
        "args": [
          "drug1_effect",
          "drug2_effect"
        ],
        "doc": "Bliss independence model for drug combination\nE_combo = E1 + E2 - E1*E2\n\nReference: Bliss, C.I. (1939) Annals of Applied Biology 26(3):585-615"
      },
      {
        "tool_name": "loewe_additivity",
        "args": [
          "drug1_conc",
          "drug1_ic50",
          "drug2_conc",
          "drug2_ic50"
        ],
        "doc": "Loewe additivity model for drug synergy\nCI = (D1/IC50_1) + (D2/IC50_2)\nCI < 1: synergy, CI = 1: additivity, CI > 1: antagonism\n\nReference: Loewe, S. (1953) Arzneimittel-Forschung 3:285-290"
      },
      {
        "tool_name": "simulate_resistance_evolution",
        "args": [
          "initial_sensitive_fraction",
          "treatment_pressure",
          "mutation_rate",
          "generations"
        ],
        "doc": "Model evolution of drug resistance using branching process\n\nReference: Iwasa, Y. et al. (2006) Genetics 172(4):2557-2566"
      },
      {
        "tool_name": "calculate_biomarker_score",
        "args": [
          "biomarkers",
          "weights"
        ],
        "doc": "Calculate composite biomarker score for treatment selection\n\nReference: Ballman, K.V. (2015) Journal of Clinical Oncology 33(33):3968-3971"
      },
      {
        "tool_name": "predict_survival_probability",
        "args": [
          "time_months",
          "median_survival",
          "shape_param"
        ],
        "doc": "Weibull survival model for cancer patients\nS(t) = exp(-(t/\u03bb)^k)\n\nReference: Weibull, W. (1951) Journal of Applied Mechanics 18(3):293-297"
      },
      {
        "tool_name": "calculate_response_rate",
        "args": [
          "tumor_type",
          "drug_class"
        ],
        "doc": "Clinical response rates based on real trial data\n\nReferences: Multiple phase III trials from JCO, NEJM, Lancet Oncology"
      },
      {
        "tool_name": "simulate_tumor_heterogeneity",
        "args": [
          "num_clones",
          "time_points"
        ],
        "doc": "Simulate clonal evolution and tumor heterogeneity\n\nReference: Nowell, P.C. (1976) Science 194(4260):23-28"
      },
      {
        "tool_name": "calculate_toxicity_score",
        "args": [
          "drug",
          "dose"
        ],
        "doc": "Calculate organ-specific toxicity scores\n\nReference: Common Terminology Criteria for Adverse Events (CTCAE) v5.0"
      }
    ]
  },
  {
    "id": "atmospheric_chemistry_lab.py",
    "name": "Atmospheric Chemistry",
    "description": "Advanced atmospheric chemistry laboratory.\nImplements photochemistry, aerosol dynamics, and dispersion modeling.",
    "capabilities": [
      {
        "tool_name": "calculate_photolysis_rate",
        "args": [
          "species",
          "quantum_yield"
        ],
        "doc": "Calculate photolysis rate J-value for a species.\nJ = \u222b \u03c3(\u03bb) \u00d7 \u03a6(\u03bb) \u00d7 F(\u03bb) d\u03bb"
      },
      {
        "tool_name": "chapman_cycle",
        "args": [
          "initial_o3",
          "time_hours"
        ],
        "doc": "Simulate the Chapman ozone cycle.\nSimplified O-O2-O3 system in the stratosphere."
      },
      {
        "tool_name": "nox_hox_chemistry",
        "args": [
          "initial_conditions",
          "time_hours"
        ],
        "doc": "Coupled NOx-HOx chemistry simulation.\nKey tropospheric radical chemistry."
      },
      {
        "tool_name": "aerosol_size_distribution",
        "args": [
          "mode"
        ],
        "doc": "Generate aerosol size distributions for different environments.\nUses lognormal distributions for different modes."
      },
      {
        "tool_name": "aerosol_optical_properties",
        "args": [
          "aerosol",
          "wavelength"
        ],
        "doc": "Calculate aerosol optical properties using Mie theory (simplified)."
      },
      {
        "tool_name": "gas_phase_diffusion",
        "args": [
          "species",
          "distance",
          "time"
        ],
        "doc": "Calculate gas-phase molecular diffusion using Fick's law."
      },
      {
        "tool_name": "gaussian_plume_model",
        "args": [
          "emission_rate",
          "stack_height",
          "wind_speed",
          "x",
          "y",
          "z"
        ],
        "doc": "Gaussian plume dispersion model for point source emissions.\nReturns concentration in \u00b5g/m\u00b3."
      },
      {
        "tool_name": "box_model_simulation",
        "args": [
          "emissions",
          "box_height",
          "box_area",
          "wind_speed",
          "days"
        ],
        "doc": "Box model for urban/regional air quality."
      },
      {
        "tool_name": "acid_rain_chemistry",
        "args": [
          "so2_ppb",
          "nox_ppb",
          "nh3_ppb"
        ],
        "doc": "Calculate acid rain formation and pH."
      },
      {
        "tool_name": "photochemical_smog_index",
        "args": [
          "no2",
          "voc",
          "temperature",
          "solar_radiation"
        ],
        "doc": "Calculate photochemical smog formation potential."
      },
      {
        "tool_name": "stratospheric_ozone_depletion",
        "args": [
          "cfc_ppt",
          "temperature",
          "latitude"
        ],
        "doc": "Model stratospheric ozone depletion by CFCs and polar chemistry."
      },
      {
        "tool_name": "demo",
        "args": [],
        "doc": "Demonstrate atmospheric chemistry capabilities"
      }
    ]
  },
  {
    "id": "novel_algorithm_generator_lab.py",
    "name": "Novel Algorithm Generator",
    "description": "Novel Algorithm Generator Laboratory\n\nThis lab autonomously generates novel algorithms through:\n1. Mathematical reasoning and optimization theory\n2. Symbolic manipulation and theorem proving\n3. Neural architecture search\n4. Quantum algorithm synthesis\n5. Hybrid classical-quantum approaches",
    "capabilities": [
      {
        "tool_name": "initialize_mathematical_toolkit",
        "args": [],
        "doc": "Initialize mathematical foundations for algorithm generation"
      },
      {
        "tool_name": "symbolic_algorithm_synthesis",
        "args": [
          "domain"
        ],
        "doc": "Generate algorithm through symbolic reasoning and mathematical derivation"
      },
      {
        "tool_name": "neural_architecture_search",
        "args": [],
        "doc": "Generate algorithm structure using neural architecture search principles"
      },
      {
        "tool_name": "self_assembling_code_synthesis",
        "args": [
          "blueprint"
        ],
        "doc": "Generate executable code from algorithm blueprint"
      },
      {
        "tool_name": "autonomous_novel_algorithm_generation",
        "args": [
          "num_algorithms"
        ],
        "doc": "Autonomously generate multiple novel algorithms"
      }
    ]
  },
  {
    "id": "particle_physics_lab.py",
    "name": "Particle Physics",
    "description": "Advanced particle physics simulation laboratory.",
    "capabilities": [
      {
        "tool_name": "calculate_cross_section",
        "args": [
          "process",
          "s",
          "cos_theta"
        ],
        "doc": "Calculate cross-section for various processes.\n\nArgs:\n    process: Process name (e.g., 'ee_to_mumu', 'pp_elastic')\n    s: Center-of-mass energy squared (GeV\u00b2)\n    cos_theta: Cosine of scattering angle (for differential cross-section)\n\nReturns:\n    Cross-section in millibarns (mb)"
      },
      {
        "tool_name": "calculate_decay_rate",
        "args": [
          "parent",
          "products"
        ],
        "doc": "Calculate decay rate for particle decays.\n\nArgs:\n    parent: Parent particle name\n    products: List of decay product names\n\nReturns:\n    Decay rate in GeV"
      },
      {
        "tool_name": "calculate_mandelstam_variables",
        "args": [
          "p1",
          "p2",
          "p3",
          "p4"
        ],
        "doc": "Calculate Mandelstam variables for 2\u21922 scattering.\n\nArgs:\n    p1, p2: Initial state four-momenta\n    p3, p4: Final state four-momenta\n\nReturns:\n    Tuple of (s, t, u) Mandelstam variables in GeV\u00b2"
      },
      {
        "tool_name": "feynman_amplitude",
        "args": [
          "process",
          "s",
          "t"
        ],
        "doc": "Calculate Feynman amplitude for simple processes.\n\nArgs:\n    process: Process name\n    s: Mandelstam s (GeV\u00b2)\n    t: Mandelstam t (GeV\u00b2)\n\nReturns:\n    Complex amplitude"
      },
      {
        "tool_name": "calculate_branching_ratio",
        "args": [
          "parent",
          "decay_channel"
        ],
        "doc": "Calculate branching ratio for a decay channel.\n\nArgs:\n    parent: Parent particle name\n    decay_channel: Specific decay products\n\nReturns:\n    Branching ratio (0 to 1)"
      },
      {
        "tool_name": "parton_distribution_function",
        "args": [
          "x",
          "Q2",
          "parton"
        ],
        "doc": "Simple parametrization of parton distribution functions.\n\nArgs:\n    x: Bjorken x (momentum fraction)\n    Q2: Momentum transfer squared (GeV\u00b2)\n    parton: Parton type ('u', 'd', 's', 'g')\n\nReturns:\n    PDF value"
      },
      {
        "tool_name": "invariant_mass_spectrum",
        "args": [
          "particles"
        ],
        "doc": "Calculate invariant mass of a system of particles.\n\nArgs:\n    particles: List of four-vectors\n\nReturns:\n    Invariant mass in GeV"
      },
      {
        "tool_name": "rapidity",
        "args": [
          "p"
        ],
        "doc": "Calculate rapidity of a particle.\n\nArgs:\n    p: Four-vector\n\nReturns:\n    Rapidity"
      },
      {
        "tool_name": "pseudorapidity",
        "args": [
          "px",
          "py",
          "pz"
        ],
        "doc": "Calculate pseudorapidity from momentum components.\n\nArgs:\n    px, py, pz: Momentum components\n\nReturns:\n    Pseudorapidity \u03b7"
      },
      {
        "tool_name": "transverse_momentum",
        "args": [
          "px",
          "py"
        ],
        "doc": "Calculate transverse momentum."
      },
      {
        "tool_name": "missing_transverse_energy",
        "args": [
          "visible_particles"
        ],
        "doc": "Calculate missing transverse energy (for neutrinos, etc.).\n\nArgs:\n    visible_particles: List of visible particle four-vectors\n\nReturns:\n    Tuple of (missing ET, missing phi)"
      },
      {
        "tool_name": "jet_clustering",
        "args": [
          "particles",
          "R",
          "algorithm"
        ],
        "doc": "Simple jet clustering algorithm.\n\nArgs:\n    particles: List of particle four-vectors\n    R: Jet radius parameter\n    algorithm: 'kt', 'antikt', or 'cambridge'\n\nReturns:\n    List of jets (each jet is a list of particles)"
      },
      {
        "tool_name": "luminosity",
        "args": [
          "n1",
          "n2",
          "f",
          "A"
        ],
        "doc": "Calculate instantaneous luminosity for collider.\n\nArgs:\n    n1: Number of particles in bunch 1\n    n2: Number of particles in bunch 2\n    f: Collision frequency (Hz)\n    A: Cross-sectional area (m\u00b2)\n\nReturns:\n    Luminosity in cm\u207b\u00b2s\u207b\u00b9"
      }
    ]
  },
  {
    "id": "tabu_search_navigator_lab.py",
    "name": "Tabu Search Navigator",
    "description": "Tabu Search Navigator\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "optical_waveguide_designer_lab.py",
    "name": "Optical Waveguide Designer",
    "description": "Optical Waveguide Designer\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "physical_chemistry_lab.py",
    "name": "Physical Chemistry",
    "description": "Production-ready physical chemistry laboratory",
    "capabilities": [
      {
        "tool_name": "calculate_state_functions",
        "args": [
          "state"
        ],
        "doc": "Calculate all thermodynamic state functions"
      },
      {
        "tool_name": "carnot_cycle_analysis",
        "args": [
          "T_hot",
          "T_cold",
          "V1",
          "V2"
        ],
        "doc": "Analyze Carnot cycle efficiency and work"
      },
      {
        "tool_name": "calculate_equilibrium_constant",
        "args": [
          "delta_G",
          "temperature"
        ],
        "doc": "Calculate equilibrium constant from Gibbs energy"
      },
      {
        "tool_name": "van_der_waals_equation",
        "args": [
          "n",
          "V",
          "T",
          "a",
          "b"
        ],
        "doc": "Van der Waals equation of state\n\nArgs:\n    n: moles\n    V: volume (m\u00b3)\n    T: temperature (K)\n    a: Van der Waals a parameter (Pa\u00b7m\u2076/mol\u00b2)\n    b: Van der Waals b parameter (m\u00b3/mol)"
      },
      {
        "tool_name": "phase_transition_analysis",
        "args": [
          "substance"
        ],
        "doc": "Analyze phase transitions and critical points"
      },
      {
        "tool_name": "maxwell_boltzmann_distribution",
        "args": [
          "mass",
          "v"
        ],
        "doc": "Maxwell-Boltzmann speed distribution"
      },
      {
        "tool_name": "calculate_mean_free_path",
        "args": [
          "diameter",
          "n_density"
        ],
        "doc": "Calculate mean free path of molecules"
      },
      {
        "tool_name": "calculate_collision_frequency",
        "args": [
          "diameter",
          "mass",
          "n_density"
        ],
        "doc": "Calculate collision frequency"
      },
      {
        "tool_name": "transport_properties",
        "args": [
          "mass",
          "diameter",
          "n_density"
        ],
        "doc": "Calculate transport properties: viscosity, diffusion, thermal conductivity"
      },
      {
        "tool_name": "particle_in_box_energies",
        "args": [
          "L",
          "mass",
          "n_max"
        ],
        "doc": "Calculate energy levels for particle in a box"
      },
      {
        "tool_name": "harmonic_oscillator_energies",
        "args": [
          "frequency",
          "n_max"
        ],
        "doc": "Calculate quantum harmonic oscillator energy levels"
      },
      {
        "tool_name": "hydrogen_atom_energies",
        "args": [
          "n_max"
        ],
        "doc": "Calculate hydrogen atom energy levels"
      },
      {
        "tool_name": "calculate_tunneling_probability",
        "args": [
          "E",
          "V0",
          "width",
          "mass"
        ],
        "doc": "Calculate quantum tunneling probability through rectangular barrier"
      },
      {
        "tool_name": "partition_function",
        "args": [
          "energies",
          "degeneracies"
        ],
        "doc": "Calculate canonical partition function"
      },
      {
        "tool_name": "thermodynamic_from_partition",
        "args": [
          "Q",
          "energies"
        ],
        "doc": "Calculate thermodynamic properties from partition function"
      },
      {
        "tool_name": "molecular_dynamics_step",
        "args": [
          "molecules",
          "dt",
          "box_size"
        ],
        "doc": "Single molecular dynamics time step (simplified)"
      },
      {
        "tool_name": "rotational_spectrum",
        "args": [
          "I_moment",
          "J_max"
        ],
        "doc": "Calculate rotational spectrum energy levels"
      },
      {
        "tool_name": "vibrational_spectrum",
        "args": [
          "k_force",
          "reduced_mass",
          "v_max"
        ],
        "doc": "Calculate vibrational spectrum"
      },
      {
        "tool_name": "electronic_transition_selection_rules",
        "args": [
          "initial_state",
          "final_state"
        ],
        "doc": "Check selection rules for electronic transitions"
      },
      {
        "tool_name": "arrhenius_rate_constant",
        "args": [
          "A",
          "Ea",
          "temperature"
        ],
        "doc": "Calculate rate constant using Arrhenius equation"
      },
      {
        "tool_name": "transition_state_theory",
        "args": [
          "delta_H_activation",
          "delta_S_activation"
        ],
        "doc": "Calculate rate using transition state theory"
      },
      {
        "tool_name": "integrated_rate_laws",
        "args": [
          "order",
          "k",
          "C0",
          "time"
        ],
        "doc": "Calculate concentration vs time for different reaction orders"
      },
      {
        "tool_name": "michaelis_menten_kinetics",
        "args": [
          "S",
          "Vmax",
          "Km"
        ],
        "doc": "Michaelis-Menten enzyme kinetics"
      },
      {
        "tool_name": "langmuir_isotherm",
        "args": [
          "pressure",
          "K_ads"
        ],
        "doc": "Langmuir adsorption isotherm"
      },
      {
        "tool_name": "bet_isotherm",
        "args": [
          "pressure",
          "P0",
          "C"
        ],
        "doc": "BET (Brunauer-Emmett-Teller) adsorption isotherm"
      },
      {
        "tool_name": "surface_tension_young_laplace",
        "args": [
          "gamma",
          "r1",
          "r2"
        ],
        "doc": "Young-Laplace equation for pressure difference across curved interface"
      }
    ]
  },
  {
    "id": "quantum_mechanics_lab.py",
    "name": "Quantum Mechanics",
    "description": "Advanced quantum mechanics simulation laboratory.",
    "capabilities": [
      {
        "tool_name": "solve_schrodinger_1d",
        "args": [
          "potential",
          "x_range",
          "n_points",
          "n_states",
          "mass"
        ],
        "doc": "Solve the time-independent Schrodinger equation in 1D.\n\nArgs:\n    potential: Potential energy function V(x)\n    x_range: Tuple of (x_min, x_max)\n    n_points: Number of spatial grid points\n    n_states: Number of energy eigenstates to find\n    mass: Particle mass (default: electron mass)\n\nReturns:\n    Tuple of (x_grid, energies, wavefunctions)"
      },
      {
        "tool_name": "solve_schrodinger_2d",
        "args": [
          "potential",
          "x_range",
          "y_range",
          "n_points",
          "n_states",
          "mass"
        ],
        "doc": "Solve the time-independent Schrodinger equation in 2D.\n\nArgs:\n    potential: Potential energy function V(x, y)\n    x_range: Tuple of (x_min, x_max)\n    y_range: Tuple of (y_min, y_max)\n    n_points: Number of grid points in each dimension\n    n_states: Number of energy eigenstates to find\n    mass: Particle mass\n\nReturns:\n    Tuple of ((X, Y) meshgrid, energies, wavefunctions)"
      },
      {
        "tool_name": "harmonic_oscillator_eigenstates",
        "args": [
          "n_max",
          "omega",
          "mass",
          "x_range",
          "n_points"
        ],
        "doc": "Calculate quantum harmonic oscillator eigenstates analytically.\n\nArgs:\n    n_max: Maximum quantum number\n    omega: Angular frequency (rad/s)\n    mass: Particle mass\n    x_range: Spatial range for wavefunction evaluation\n    n_points: Number of spatial points\n\nReturns:\n    Tuple of (x_grid, energies, wavefunctions)"
      },
      {
        "tool_name": "hydrogen_wavefunction",
        "args": [
          "n",
          "l",
          "m",
          "r_max",
          "n_points"
        ],
        "doc": "Calculate hydrogen atom wavefunctions.\n\nArgs:\n    n: Principal quantum number (n >= 1)\n    l: Orbital angular momentum quantum number (0 <= l < n)\n    m: Magnetic quantum number (-l <= m <= l)\n    r_max: Maximum radius\n    n_points: Number of grid points in each dimension\n\nReturns:\n    Tuple of ((R, Theta, Phi) grids, wavefunction)"
      },
      {
        "tool_name": "quantum_tunneling_probability",
        "args": [
          "barrier_height",
          "barrier_width",
          "particle_energy",
          "mass"
        ],
        "doc": "Calculate transmission probability through a rectangular potential barrier.\n\nArgs:\n    barrier_height: Height of potential barrier (J)\n    barrier_width: Width of barrier (m)\n    particle_energy: Energy of incident particle (J)\n    mass: Particle mass\n\nReturns:\n    Transmission probability (0 to 1)"
      },
      {
        "tool_name": "perturbation_theory_first_order",
        "args": [
          "H0",
          "V",
          "n_states"
        ],
        "doc": "Calculate first-order perturbation theory corrections.\n\nArgs:\n    H0: Unperturbed Hamiltonian matrix\n    V: Perturbation potential matrix\n    n_states: Number of states to calculate\n\nReturns:\n    Tuple of (energy corrections, state corrections)"
      },
      {
        "tool_name": "time_evolution_schrodinger",
        "args": [
          "psi0",
          "H",
          "t_max",
          "n_steps"
        ],
        "doc": "Evolve a quantum state in time using the time-dependent Schrodinger equation.\n\nArgs:\n    psi0: Initial state vector\n    H: Hamiltonian matrix\n    t_max: Maximum evolution time (s)\n    n_steps: Number of time steps\n\nReturns:\n    Array of state vectors at each time step"
      },
      {
        "tool_name": "expectation_value",
        "args": [
          "psi",
          "operator"
        ],
        "doc": "Calculate expectation value of an operator in a given state.\n\nArgs:\n    psi: Quantum state vector\n    operator: Operator matrix\n\nReturns:\n    Expectation value <psi|operator|psi>"
      },
      {
        "tool_name": "uncertainty_relation",
        "args": [
          "psi",
          "A",
          "B"
        ],
        "doc": "Calculate uncertainty relation for two operators.\n\nArgs:\n    psi: Quantum state vector\n    A: First operator\n    B: Second operator\n\nReturns:\n    Tuple of (\u0394A, \u0394B, \u0394A\u00b7\u0394B)"
      },
      {
        "tool_name": "coherent_state",
        "args": [
          "alpha",
          "n_max"
        ],
        "doc": "Create a coherent state (quantum harmonic oscillator).\n\nArgs:\n    alpha: Complex amplitude\n    n_max: Maximum Fock state number\n\nReturns:\n    Coherent state vector in Fock basis"
      },
      {
        "tool_name": "berry_phase",
        "args": [
          "H_func",
          "params_path",
          "state_idx"
        ],
        "doc": "Calculate geometric (Berry) phase for adiabatic evolution.\n\nArgs:\n    H_func: Function that returns Hamiltonian for given parameter\n    params_path: Array of parameters defining closed path\n    state_idx: Which eigenstate to track (0 = ground state)\n\nReturns:\n    Berry phase (radians)"
      }
    ]
  },
  {
    "id": "rd_engineering_lab.py",
    "name": "Rd Engineering",
    "description": "Main R&D Engineering Lab",
    "capabilities": [
      {
        "tool_name": "create_pcb_project",
        "args": [
          "name",
          "width",
          "height",
          "layers"
        ],
        "doc": "Create new PCB project"
      },
      {
        "tool_name": "create_housing",
        "args": [
          "name",
          "material",
          "width",
          "height",
          "depth"
        ],
        "doc": "Create new housing design"
      },
      {
        "tool_name": "get_pcb_project",
        "args": [
          "name"
        ],
        "doc": "Get existing PCB project"
      },
      {
        "tool_name": "get_housing_design",
        "args": [
          "name"
        ],
        "doc": "Get existing housing design"
      },
      {
        "tool_name": "reverse_engineer_from_image",
        "args": [
          "image_path"
        ],
        "doc": "Start reverse engineering from image"
      },
      {
        "tool_name": "create_3d_viewer",
        "args": [],
        "doc": "Create 3D viewer for visualization"
      },
      {
        "tool_name": "export_project",
        "args": [
          "name",
          "format"
        ],
        "doc": "Export project in various formats"
      }
    ]
  },
  {
    "id": "genetic_algorithm_optimizer_lab.py",
    "name": "Genetic Algorithm Optimizer",
    "description": "Genetic Algorithm Optimizer\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "machine_learning_lab.py",
    "name": "Machine Learning",
    "description": "Production-ready machine learning algorithms implemented from scratch.",
    "capabilities": [
      {
        "tool_name": "gradient_descent",
        "args": [
          "X",
          "y",
          "theta_init"
        ],
        "doc": "Implement gradient descent optimization from scratch.\n\nArgs:\n    X: Feature matrix (n_samples, n_features)\n    y: Target values (n_samples,)\n    theta_init: Initial parameters\n\nReturns:\n    Optimized parameters"
      },
      {
        "tool_name": "stochastic_gradient_descent",
        "args": [
          "X",
          "y",
          "theta_init"
        ],
        "doc": "Implement stochastic gradient descent with mini-batches.\n\nArgs:\n    X: Feature matrix\n    y: Target values\n    theta_init: Initial parameters\n\nReturns:\n    Optimized parameters"
      },
      {
        "tool_name": "cross_validation",
        "args": [
          "X",
          "y",
          "k_folds",
          "model_fn"
        ],
        "doc": "Implement k-fold cross-validation from scratch.\n\nArgs:\n    X: Feature matrix\n    y: Target values\n    k_folds: Number of folds\n    model_fn: Model training function\n\nReturns:\n    Dictionary with validation metrics"
      },
      {
        "tool_name": "feature_selection_rfe",
        "args": [
          "X",
          "y",
          "n_features_to_select"
        ],
        "doc": "Recursive Feature Elimination for feature selection.\n\nArgs:\n    X: Feature matrix\n    y: Target values\n    n_features_to_select: Number of features to keep\n\nReturns:\n    Boolean mask of selected features"
      },
      {
        "tool_name": "lasso_coordinate_descent",
        "args": [
          "X",
          "y",
          "alpha"
        ],
        "doc": "Implement LASSO regression using coordinate descent.\n\nArgs:\n    X: Feature matrix\n    y: Target values\n    alpha: L1 regularization strength\n\nReturns:\n    Sparse coefficient vector"
      },
      {
        "tool_name": "ridge_regression",
        "args": [
          "X",
          "y",
          "alpha"
        ],
        "doc": "Implement Ridge regression with closed-form solution.\n\nArgs:\n    X: Feature matrix\n    y: Target values\n    alpha: L2 regularization strength\n\nReturns:\n    Coefficient vector"
      },
      {
        "tool_name": "elastic_net",
        "args": [
          "X",
          "y",
          "alpha",
          "l1_ratio"
        ],
        "doc": "Implement Elastic Net regression combining L1 and L2 penalties.\n\nArgs:\n    X: Feature matrix\n    y: Target values\n    alpha: Total regularization strength\n    l1_ratio: Balance between L1 (1.0) and L2 (0.0)\n\nReturns:\n    Coefficient vector"
      },
      {
        "tool_name": "random_forest_regressor",
        "args": [
          "X",
          "y",
          "n_trees",
          "max_depth"
        ],
        "doc": "Implement Random Forest regressor from scratch.\n\nArgs:\n    X: Feature matrix\n    y: Target values\n    n_trees: Number of trees\n    max_depth: Maximum tree depth\n\nReturns:\n    Trained random forest model"
      },
      {
        "tool_name": "gradient_boosting_regressor",
        "args": [
          "X",
          "y",
          "n_estimators",
          "learning_rate"
        ],
        "doc": "Implement Gradient Boosting regressor from scratch.\n\nArgs:\n    X: Feature matrix\n    y: Target values\n    n_estimators: Number of boosting rounds\n    learning_rate: Boosting learning rate\n\nReturns:\n    List of weak learner predictions"
      },
      {
        "tool_name": "hyperparameter_optimization",
        "args": [
          "X",
          "y",
          "param_grid"
        ],
        "doc": "Grid search for hyperparameter optimization.\n\nArgs:\n    X: Feature matrix\n    y: Target values\n    param_grid: Dictionary of parameters to search\n\nReturns:\n    Best parameters and score"
      },
      {
        "tool_name": "compute_metrics",
        "args": [
          "y_true",
          "y_pred"
        ],
        "doc": "Compute comprehensive evaluation metrics.\n\nArgs:\n    y_true: True values\n    y_pred: Predicted values\n\nReturns:\n    Dictionary of metrics"
      },
      {
        "tool_name": "polynomial_features",
        "args": [
          "X",
          "degree"
        ],
        "doc": "Generate polynomial features for non-linear modeling.\n\nArgs:\n    X: Feature matrix\n    degree: Polynomial degree\n\nReturns:\n    Extended feature matrix with polynomial terms"
      }
    ]
  },
  {
    "id": "solar_flare_predictor_lab.py",
    "name": "Solar Flare Predictor",
    "description": "Solar Flare Predictor\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "genetics_lab.py",
    "name": "Genetics",
    "description": "Main genetics laboratory interface",
    "capabilities": [
      {
        "tool_name": "analyze_cross",
        "args": [
          "parent1",
          "parent2",
          "cross_type"
        ],
        "doc": "Analyze genetic cross"
      },
      {
        "tool_name": "test_hwe",
        "args": [
          "genotype_counts"
        ],
        "doc": "Test for Hardy-Weinberg equilibrium"
      },
      {
        "tool_name": "map_qtl",
        "args": [
          "markers",
          "phenotypes"
        ],
        "doc": "Map quantitative trait loci"
      },
      {
        "tool_name": "simulate_evolution",
        "args": [
          "initial_freq",
          "pop_size",
          "generations",
          "selection"
        ],
        "doc": "Simulate allele frequency evolution"
      },
      {
        "tool_name": "estimate_mutation_rate",
        "args": [
          "n_mutations",
          "n_sites",
          "n_generations"
        ],
        "doc": "Estimate mutation rate"
      },
      {
        "tool_name": "population_structure_analysis",
        "args": [
          "subpop_freqs"
        ],
        "doc": "Analyze population structure"
      }
    ]
  },
  {
    "id": "hydrology_lab.py",
    "name": "Hydrology",
    "description": "Comprehensive hydrology laboratory\nImplements real-world hydrologic modeling algorithms",
    "capabilities": [
      {
        "tool_name": "scs_runoff_model",
        "args": [
          "rainfall",
          "catchment"
        ],
        "doc": "SCS Curve Number method for rainfall-runoff estimation\nUSDA-NRCS standard methodology"
      },
      {
        "tool_name": "darcy_groundwater_flow",
        "args": [
          "gw_params",
          "head_gradient",
          "flow_area"
        ],
        "doc": "Darcy's law for groundwater flow calculation\nFundamental equation for porous media flow"
      },
      {
        "tool_name": "theis_well_solution",
        "args": [
          "gw_params",
          "pumping_rate",
          "distance",
          "time"
        ],
        "doc": "Theis solution for transient flow to a well in confined aquifer\nClassic analytical solution for well hydraulics"
      },
      {
        "tool_name": "penman_monteith_evapotranspiration",
        "args": [
          "temperature",
          "humidity",
          "wind_speed",
          "solar_radiation",
          "crop_coefficient"
        ],
        "doc": "FAO-56 Penman-Monteith equation for evapotranspiration\nStandard method for ET calculation"
      },
      {
        "tool_name": "rational_method_peak_flow",
        "args": [
          "intensity",
          "catchment"
        ],
        "doc": "Rational method for peak discharge estimation\nQ = CIA, commonly used for small urban catchments"
      },
      {
        "tool_name": "gumbel_flood_frequency",
        "args": [
          "annual_maxima",
          "return_periods"
        ],
        "doc": "Gumbel distribution for flood frequency analysis\nStandard method for extreme value analysis"
      },
      {
        "tool_name": "muskingum_routing",
        "args": [
          "inflow",
          "K",
          "X",
          "dt"
        ],
        "doc": "Muskingum method for flood routing through river reaches\nLinear reservoir routing model"
      },
      {
        "tool_name": "unit_hydrograph_convolution",
        "args": [
          "rainfall",
          "unit_hydrograph"
        ],
        "doc": "Convolution of rainfall with unit hydrograph\nLinear systems approach to rainfall-runoff modeling"
      },
      {
        "tool_name": "green_ampt_infiltration",
        "args": [
          "rainfall_rate",
          "time",
          "soil_type",
          "initial_moisture"
        ],
        "doc": "Green-Ampt infiltration model\nPhysically-based infiltration calculation"
      },
      {
        "tool_name": "synthetic_unit_hydrograph",
        "args": [
          "catchment",
          "duration"
        ],
        "doc": "Snyder's synthetic unit hydrograph\nGenerate UH for ungauged basins"
      },
      {
        "tool_name": "stream_flow_statistics",
        "args": [
          "daily_flows"
        ],
        "doc": "Calculate comprehensive streamflow statistics\nFlow duration curves, baseflow index, etc."
      }
    ]
  },
  {
    "id": "computer_vision_lab.py",
    "name": "Computer Vision",
    "description": "Production-ready computer vision algorithms implemented from scratch.",
    "capabilities": [
      {
        "tool_name": "convolution2d",
        "args": [
          "image",
          "kernel",
          "stride",
          "padding"
        ],
        "doc": "Perform 2D convolution operation from scratch.\n\nArgs:\n    image: Input image (H, W) or (H, W, C)\n    kernel: Convolution kernel\n    stride: Stride for convolution\n    padding: Padding size\n\nReturns:\n    Convolved image"
      },
      {
        "tool_name": "max_pooling2d",
        "args": [
          "image",
          "pool_size",
          "stride"
        ],
        "doc": "Perform max pooling operation.\n\nArgs:\n    image: Input image\n    pool_size: Size of pooling window\n    stride: Stride (defaults to pool_size)\n\nReturns:\n    Pooled image"
      },
      {
        "tool_name": "average_pooling2d",
        "args": [
          "image",
          "pool_size",
          "stride"
        ],
        "doc": "Perform average pooling operation."
      },
      {
        "tool_name": "gaussian_kernel",
        "args": [
          "size",
          "sigma"
        ],
        "doc": "Generate Gaussian kernel for blurring."
      },
      {
        "tool_name": "gaussian_blur",
        "args": [
          "image",
          "kernel_size",
          "sigma"
        ],
        "doc": "Apply Gaussian blur to image."
      },
      {
        "tool_name": "sobel_edge_detection",
        "args": [
          "image"
        ],
        "doc": "Perform Sobel edge detection.\n\nArgs:\n    image: Input grayscale image\n\nReturns:\n    Gradient magnitude, gradient direction, edge map"
      },
      {
        "tool_name": "canny_edge_detection",
        "args": [
          "image",
          "low_threshold",
          "high_threshold"
        ],
        "doc": "Implement Canny edge detection algorithm.\n\nArgs:\n    image: Input grayscale image\n    low_threshold: Low threshold for edge linking\n    high_threshold: High threshold for edge detection\n\nReturns:\n    Binary edge map"
      },
      {
        "tool_name": "harris_corner_detection",
        "args": [
          "image",
          "k",
          "threshold"
        ],
        "doc": "Implement Harris corner detection.\n\nArgs:\n    image: Input grayscale image\n    k: Harris detector parameter\n    threshold: Threshold for corner detection\n\nReturns:\n    Corner response map"
      },
      {
        "tool_name": "sift_like_features",
        "args": [
          "image"
        ],
        "doc": "Extract SIFT-like features (simplified version).\n\nArgs:\n    image: Input grayscale image\n\nReturns:\n    Dictionary with keypoints and descriptors"
      },
      {
        "tool_name": "image_augmentation",
        "args": [
          "image",
          "augmentation_type"
        ],
        "doc": "Apply various image augmentation techniques.\n\nArgs:\n    image: Input image\n    augmentation_type: Type of augmentation\n\nReturns:\n    Augmented image"
      },
      {
        "tool_name": "intersection_over_union",
        "args": [
          "box1",
          "box2"
        ],
        "doc": "Calculate Intersection over Union (IoU) for bounding boxes.\n\nArgs:\n    box1: [x1, y1, x2, y2]\n    box2: [x1, y1, x2, y2]\n\nReturns:\n    IoU score"
      },
      {
        "tool_name": "non_max_suppression",
        "args": [
          "boxes",
          "scores",
          "threshold"
        ],
        "doc": "Apply Non-Maximum Suppression to bounding boxes.\n\nArgs:\n    boxes: Array of boxes [N, 4] (x1, y1, x2, y2)\n    scores: Confidence scores [N]\n    threshold: IoU threshold\n\nReturns:\n    Indices of kept boxes"
      },
      {
        "tool_name": "mean_average_precision",
        "args": [
          "predictions",
          "ground_truth",
          "iou_threshold"
        ],
        "doc": "Calculate mean Average Precision (mAP) for object detection.\n\nArgs:\n    predictions: List of predicted boxes with scores and classes\n    ground_truth: List of ground truth boxes with classes\n    iou_threshold: IoU threshold for matching\n\nReturns:\n    mAP score"
      },
      {
        "tool_name": "semantic_segmentation_metrics",
        "args": [
          "pred_mask",
          "true_mask",
          "n_classes"
        ],
        "doc": "Calculate metrics for semantic segmentation.\n\nArgs:\n    pred_mask: Predicted segmentation mask\n    true_mask: Ground truth mask\n    n_classes: Number of classes\n\nReturns:\n    Dictionary with IoU, Dice coefficient, and pixel accuracy"
      },
      {
        "tool_name": "histogram_equalization",
        "args": [
          "image"
        ],
        "doc": "Apply histogram equalization for contrast enhancement."
      },
      {
        "tool_name": "template_matching",
        "args": [
          "image",
          "template"
        ],
        "doc": "Perform template matching using normalized cross-correlation.\n\nArgs:\n    image: Input image\n    template: Template to find\n\nReturns:\n    Correlation map and best match location"
      }
    ]
  },
  {
    "id": "catalysis_lab.py",
    "name": "Catalysis",
    "description": "Advanced catalysis laboratory for comprehensive reaction simulations.",
    "capabilities": [
      {
        "tool_name": "turnover_frequency",
        "args": [
          "rate",
          "active_sites"
        ],
        "doc": "Calculate turnover frequency (TOF).\n\nTOF = reaction rate / number of active sites\nUnits: s\u207b\u00b9"
      },
      {
        "tool_name": "turnover_number",
        "args": [
          "moles_product",
          "active_sites"
        ],
        "doc": "Calculate turnover number (TON).\n\nTON = moles of product / moles of active sites"
      },
      {
        "tool_name": "site_time_yield",
        "args": [
          "production_rate",
          "active_sites",
          "catalyst_mass"
        ],
        "doc": "Calculate site-time yield (STY).\n\nSTY = production rate / (active sites \u00d7 catalyst mass)\nUnits: mol/(mol_sites\u00b7kg\u00b7s)"
      },
      {
        "tool_name": "sabatier_volcano_plot",
        "args": [
          "binding_energies",
          "reaction_energy"
        ],
        "doc": "Generate Sabatier volcano plot data.\n\nThe optimal catalyst has intermediate binding energy.\nToo weak: low coverage\nToo strong: poisoning"
      },
      {
        "tool_name": "optimal_binding_energy",
        "args": [
          "reaction_energy",
          "temperature"
        ],
        "doc": "Calculate optimal binding energy using Sabatier principle.\n\nOptimal when d(rate)/d(BE) = 0"
      },
      {
        "tool_name": "microkinetic_model",
        "args": [
          "reactions",
          "initial_coverages",
          "conditions",
          "time_span"
        ],
        "doc": "Solve microkinetic model for reaction network.\n\nUses mean-field approximation for surface coverages."
      },
      {
        "tool_name": "langmuir_hinshelwood_rate",
        "args": [
          "partial_pressures",
          "adsorption_constants",
          "rate_constant",
          "mechanism"
        ],
        "doc": "Calculate reaction rate using Langmuir-Hinshelwood mechanism.\n\nBoth reactants adsorb on surface before reaction."
      },
      {
        "tool_name": "eley_rideal_rate",
        "args": [
          "partial_pressure_gas",
          "coverage_adsorbed",
          "rate_constant"
        ],
        "doc": "Calculate rate for Eley-Rideal mechanism.\n\nGas phase molecule reacts directly with adsorbed species.\nA(g) + B* \u2192 Products"
      },
      {
        "tool_name": "deactivation_model",
        "args": [
          "time",
          "deactivation_order",
          "deactivation_constant",
          "regeneration_constant"
        ],
        "doc": "Model catalyst deactivation over time.\n\nda/dt = -k_d * a^n + k_r * (1-a)\nwhere a is catalyst activity (0 to 1)"
      },
      {
        "tool_name": "fouling_resistance",
        "args": [
          "time",
          "fouling_rate",
          "initial_resistance"
        ],
        "doc": "Calculate fouling resistance over time.\n\nR_f = R_f0 + k_f * t"
      },
      {
        "tool_name": "sintering_model",
        "args": [
          "temperature",
          "time",
          "initial_size"
        ],
        "doc": "Model catalyst particle sintering (Ostwald ripening).\n\nd^n - d0^n = k*t where n \u2248 3 for Ostwald ripening"
      },
      {
        "tool_name": "tpd_simulation",
        "args": [
          "adsorbate",
          "heating_rate",
          "temp_range",
          "initial_coverage"
        ],
        "doc": "Simulate Temperature-Programmed Desorption (TPD).\n\nRedhead equation for first-order desorption."
      },
      {
        "tool_name": "tpd_peak_temperature",
        "args": [
          "desorption_energy",
          "heating_rate"
        ],
        "doc": "Calculate TPD peak temperature using Redhead equation.\n\nFor first-order desorption: E_d/(R*T_p\u00b2) = (\u03bd/\u03b2)*exp(-E_d/(R*T_p))"
      },
      {
        "tool_name": "thiele_modulus",
        "args": [
          "rate_constant",
          "catalyst_particle_size",
          "effective_diffusivity",
          "concentration",
          "reaction_order"
        ],
        "doc": "Calculate Thiele modulus for internal diffusion limitations.\n\n\u03c6 = L\u221a(k*C^(n-1)/D_eff) for nth order reaction"
      },
      {
        "tool_name": "effectiveness_factor",
        "args": [
          "thiele_modulus",
          "geometry"
        ],
        "doc": "Calculate effectiveness factor for catalyst pellet.\n\n\u03b7 = (actual rate) / (rate without diffusion limitations)"
      },
      {
        "tool_name": "weisz_prater_criterion",
        "args": [
          "observed_rate",
          "concentration_surface",
          "particle_radius",
          "effective_diffusivity"
        ],
        "doc": "Calculate Weisz-Prater criterion for diffusion limitations.\n\nIf Cwp < 1: no internal diffusion limitations\nIf Cwp > 1: significant internal diffusion limitations"
      },
      {
        "tool_name": "optimize_catalyst_design",
        "args": [
          "target_conversion",
          "feed_conditions",
          "constraints"
        ],
        "doc": "Optimize catalyst design for target conversion.\n\nVariables: metal loading, particle size, support properties"
      },
      {
        "tool_name": "reaction_network_analysis",
        "args": [
          "reactions",
          "species"
        ],
        "doc": "Analyze reaction network connectivity and pathways."
      },
      {
        "tool_name": "run_comprehensive_demo",
        "args": [],
        "doc": "Run comprehensive demonstration of catalysis capabilities."
      }
    ]
  },
  {
    "id": "plasma_physics_lab.py",
    "name": "Plasma Physics",
    "description": "Advanced plasma physics simulation laboratory.",
    "capabilities": [
      {
        "tool_name": "debye_length",
        "args": [
          "electron_density",
          "electron_temp",
          "ion_density",
          "ion_temp"
        ],
        "doc": "Calculate Debye length for plasma shielding.\n\nArgs:\n    electron_density: Electron density (m^-3)\n    electron_temp: Electron temperature (K)\n    ion_density: Ion density (m^-3), defaults to electron_density\n    ion_temp: Ion temperature (K), defaults to electron_temp\n\nReturns:\n    Debye length in meters"
      },
      {
        "tool_name": "plasma_frequency",
        "args": [
          "density",
          "mass",
          "charge"
        ],
        "doc": "Calculate plasma frequency.\n\nArgs:\n    density: Particle density (m^-3)\n    mass: Particle mass (kg)\n    charge: Particle charge (C)\n\nReturns:\n    Plasma frequency in rad/s"
      },
      {
        "tool_name": "cyclotron_frequency",
        "args": [
          "B",
          "mass",
          "charge"
        ],
        "doc": "Calculate cyclotron (Larmor) frequency.\n\nArgs:\n    B: Magnetic field strength (T)\n    mass: Particle mass (kg)\n    charge: Particle charge (C)\n\nReturns:\n    Cyclotron frequency in rad/s"
      },
      {
        "tool_name": "thermal_velocity",
        "args": [
          "temperature",
          "mass"
        ],
        "doc": "Calculate thermal velocity of particles.\n\nArgs:\n    temperature: Temperature (K)\n    mass: Particle mass (kg)\n\nReturns:\n    Thermal velocity in m/s"
      },
      {
        "tool_name": "collision_frequency",
        "args": [
          "density",
          "temperature",
          "charge1",
          "charge2",
          "mass1",
          "mass2"
        ],
        "doc": "Calculate Coulomb collision frequency.\n\nArgs:\n    density: Particle density (m^-3)\n    temperature: Temperature (K)\n    charge1, charge2: Charges of colliding particles (C)\n    mass1, mass2: Masses of colliding particles (kg)\n\nReturns:\n    Collision frequency in Hz"
      },
      {
        "tool_name": "plasma_beta",
        "args": [
          "density",
          "temperature",
          "B"
        ],
        "doc": "Calculate plasma beta (ratio of thermal to magnetic pressure).\n\nArgs:\n    density: Particle density (m^-3)\n    temperature: Temperature (K)\n    B: Magnetic field strength (T)\n\nReturns:\n    Plasma beta (dimensionless)"
      },
      {
        "tool_name": "alfven_velocity",
        "args": [
          "B",
          "density",
          "mass"
        ],
        "doc": "Calculate Alfv\u00e9n wave velocity.\n\nArgs:\n    B: Magnetic field strength (T)\n    density: Mass density (kg/m^3) or number density with mass\n    mass: Particle mass if density is number density\n\nReturns:\n    Alfv\u00e9n velocity in m/s"
      },
      {
        "tool_name": "mhd_equations",
        "args": [
          "rho",
          "v",
          "B",
          "p",
          "J"
        ],
        "doc": "Calculate MHD equation terms (ideal MHD).\n\nArgs:\n    rho: Mass density (kg/m^3)\n    v: Velocity field (m/s)\n    B: Magnetic field (T)\n    p: Pressure (Pa)\n    J: Current density (A/m^2)\n\nReturns:\n    Dictionary of MHD equation terms"
      },
      {
        "tool_name": "dispersion_relation_waves",
        "args": [
          "k",
          "omega",
          "plasma_params"
        ],
        "doc": "Calculate dispersion relation for plasma waves.\n\nArgs:\n    k: Wave number (1/m)\n    omega: Wave frequency (rad/s)\n    plasma_params: Dictionary with plasma parameters\n\nReturns:\n    Dispersion relation value (should be zero for valid modes)"
      },
      {
        "tool_name": "landau_damping_rate",
        "args": [
          "k",
          "omega",
          "temperature",
          "density",
          "mass"
        ],
        "doc": "Calculate Landau damping rate for plasma waves.\n\nArgs:\n    k: Wave number (1/m)\n    omega: Wave frequency (rad/s)\n    temperature: Particle temperature (K)\n    density: Particle density (m^-3)\n    mass: Particle mass (kg)\n\nReturns:\n    Landau damping rate (1/s)"
      },
      {
        "tool_name": "two_stream_instability",
        "args": [
          "v_drift",
          "density",
          "temperature",
          "mass"
        ],
        "doc": "Analyze two-stream instability.\n\nArgs:\n    v_drift: Drift velocity between streams (m/s)\n    density: Density of each stream (m^-3)\n    temperature: Temperature (K)\n    mass: Particle mass (kg)\n\nReturns:\n    Dictionary with instability analysis"
      },
      {
        "tool_name": "fusion_reaction_rate",
        "args": [
          "T",
          "n1",
          "n2",
          "reaction"
        ],
        "doc": "Calculate fusion reaction rate.\n\nArgs:\n    T: Temperature (keV)\n    n1: Density of species 1 (m^-3)\n    n2: Density of species 2 (m^-3)\n    reaction: Type of reaction ('DT', 'DD', 'DHe3')\n\nReturns:\n    Reaction rate (reactions/m^3/s)"
      },
      {
        "tool_name": "lawson_criterion",
        "args": [
          "n",
          "tau",
          "T"
        ],
        "doc": "Calculate Lawson criterion for fusion ignition.\n\nArgs:\n    n: Plasma density (m^-3)\n    tau: Energy confinement time (s)\n    T: Temperature (keV)\n\nReturns:\n    n*tau*T product (m^-3 * s * keV)"
      },
      {
        "tool_name": "ignition_condition",
        "args": [
          "n",
          "T",
          "reaction"
        ],
        "doc": "Calculate required confinement time for ignition.\n\nArgs:\n    n: Plasma density (m^-3)\n    T: Temperature (keV)\n    reaction: Fusion reaction type\n\nReturns:\n    Required confinement time (s)"
      },
      {
        "tool_name": "particle_in_cell_step",
        "args": [
          "particles",
          "velocities",
          "E_field",
          "B_field",
          "dt",
          "charge",
          "mass"
        ],
        "doc": "Single step of particle-in-cell (PIC) simulation.\n\nArgs:\n    particles: Particle positions (N x 3 array)\n    velocities: Particle velocities (N x 3 array)\n    E_field: Electric field at particle positions (N x 3)\n    B_field: Magnetic field at particle positions (N x 3)\n    dt: Time step (s)\n    charge: Particle charge (C)\n    mass: Particle mass (kg)\n\nReturns:\n    Updated positions and velocities"
      },
      {
        "tool_name": "magnetic_confinement_time",
        "args": [
          "R",
          "a",
          "B",
          "T",
          "n"
        ],
        "doc": "Estimate confinement time in tokamak (simplified scaling).\n\nArgs:\n    R: Major radius (m)\n    a: Minor radius (m)\n    B: Toroidal field (T)\n    T: Temperature (keV)\n    n: Density (10^20 m^-3)\n\nReturns:\n    Energy confinement time (s)"
      },
      {
        "tool_name": "plasma_instability_analysis",
        "args": [
          "plasma_params"
        ],
        "doc": "Analyze various plasma instabilities.\n\nArgs:\n    plasma_params: Dictionary of plasma parameters\n\nReturns:\n    Dictionary of instability analysis results"
      }
    ]
  },
  {
    "id": "cell_biology_lab.py",
    "name": "Cell Biology",
    "description": "Main cell biology laboratory interface",
    "capabilities": [
      {
        "tool_name": "run_cell_cycle_analysis",
        "args": [
          "cell_type",
          "duration"
        ],
        "doc": "Analyze cell cycle progression"
      },
      {
        "tool_name": "run_signaling_analysis",
        "args": [
          "pathway",
          "stimulus"
        ],
        "doc": "Analyze signaling pathway dynamics"
      },
      {
        "tool_name": "run_apoptosis_analysis",
        "args": [
          "death_signal",
          "stress"
        ],
        "doc": "Analyze apoptosis induction"
      },
      {
        "tool_name": "run_migration_analysis",
        "args": [
          "substrate",
          "n_cells"
        ],
        "doc": "Analyze cell migration patterns"
      },
      {
        "tool_name": "run_proliferation_analysis",
        "args": [
          "model",
          "initial_cells"
        ],
        "doc": "Analyze cell proliferation"
      },
      {
        "tool_name": "run_metabolism_analysis",
        "args": [
          "warburg_factor"
        ],
        "doc": "Analyze metabolic flux"
      },
      {
        "tool_name": "integrate_cellular_response",
        "args": [
          "stimulus_type",
          "stimulus_strength"
        ],
        "doc": "Integrate multiple cellular responses to stimulus"
      }
    ]
  },
  {
    "id": "portfolio_optimization_markowitz_lab.py",
    "name": "Portfolio Optimization Markowitz",
    "description": "Portfolio Optimization Markowitz\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "quantum_computing_lab.py",
    "name": "Quantum Computing",
    "description": "Advanced quantum computing simulation laboratory.",
    "capabilities": [
      {
        "tool_name": "create_quantum_state",
        "args": [
          "n_qubits",
          "initial_state"
        ],
        "doc": "Create a quantum state vector.\n\nArgs:\n    n_qubits: Number of qubits\n    initial_state: Either a binary string like '101' or state vector\n\nReturns:\n    Quantum state vector"
      },
      {
        "tool_name": "apply_gate",
        "args": [
          "state",
          "gate_matrix",
          "target_qubits"
        ],
        "doc": "Apply a quantum gate to specific qubits in the state.\n\nArgs:\n    state: Current quantum state vector\n    gate_matrix: Matrix representation of the gate\n    target_qubits: List of qubit indices to apply gate to\n\nReturns:\n    New quantum state after gate application"
      },
      {
        "tool_name": "hadamard_gate",
        "args": [
          "state",
          "qubit"
        ],
        "doc": "Apply Hadamard gate to a qubit."
      },
      {
        "tool_name": "pauli_x_gate",
        "args": [
          "state",
          "qubit"
        ],
        "doc": "Apply Pauli-X (NOT) gate to a qubit."
      },
      {
        "tool_name": "pauli_y_gate",
        "args": [
          "state",
          "qubit"
        ],
        "doc": "Apply Pauli-Y gate to a qubit."
      },
      {
        "tool_name": "pauli_z_gate",
        "args": [
          "state",
          "qubit"
        ],
        "doc": "Apply Pauli-Z gate to a qubit."
      },
      {
        "tool_name": "cnot_gate",
        "args": [
          "state",
          "control",
          "target"
        ],
        "doc": "Apply CNOT gate with given control and target qubits."
      },
      {
        "tool_name": "toffoli_gate",
        "args": [
          "state",
          "control1",
          "control2",
          "target"
        ],
        "doc": "Apply Toffoli (CCNOT) gate."
      },
      {
        "tool_name": "rotation_gate",
        "args": [
          "state",
          "qubit",
          "axis",
          "angle"
        ],
        "doc": "Apply rotation gate around given axis.\n\nArgs:\n    state: Quantum state\n    qubit: Target qubit\n    axis: Rotation axis ('x', 'y', or 'z')\n    angle: Rotation angle in radians\n\nReturns:\n    Rotated state"
      },
      {
        "tool_name": "phase_gate",
        "args": [
          "state",
          "qubit",
          "phase"
        ],
        "doc": "Apply phase gate with given phase."
      },
      {
        "tool_name": "measure",
        "args": [
          "state",
          "qubits"
        ],
        "doc": "Measure qubits in computational basis.\n\nArgs:\n    state: Quantum state to measure\n    qubits: List of qubits to measure (None = all)\n\nReturns:\n    Tuple of (measurement result as binary string, collapsed state)"
      },
      {
        "tool_name": "quantum_circuit_simulate",
        "args": [
          "gates",
          "n_qubits",
          "initial_state"
        ],
        "doc": "Simulate a quantum circuit defined by a sequence of gates.\n\nArgs:\n    gates: List of QuantumGate objects\n    n_qubits: Number of qubits in circuit\n    initial_state: Initial state (default |0...0>)\n\nReturns:\n    Final quantum state"
      },
      {
        "tool_name": "grovers_algorithm",
        "args": [
          "oracle",
          "n_qubits",
          "n_iterations"
        ],
        "doc": "Implement Grover's quantum search algorithm.\n\nArgs:\n    oracle: Function that marks target states (returns True for targets)\n    n_qubits: Number of qubits\n    n_iterations: Number of Grover iterations (auto-calculated if None)\n\nReturns:\n    Tuple of (found state as binary string, success probability)"
      },
      {
        "tool_name": "quantum_fourier_transform",
        "args": [
          "state",
          "qubits"
        ],
        "doc": "Apply Quantum Fourier Transform to specified qubits.\n\nArgs:\n    state: Input quantum state\n    qubits: Qubits to apply QFT to (default: all)\n\nReturns:\n    State after QFT"
      },
      {
        "tool_name": "quantum_error_correction_3qubit",
        "args": [
          "state",
          "error_type"
        ],
        "doc": "Implement 3-qubit error correction code.\n\nArgs:\n    state: Single qubit state to protect\n    error_type: 'bit_flip' or 'phase_flip'\n\nReturns:\n    Corrected state"
      },
      {
        "tool_name": "calculate_fidelity",
        "args": [
          "state1",
          "state2"
        ],
        "doc": "Calculate fidelity between two quantum states.\n\nArgs:\n    state1: First quantum state\n    state2: Second quantum state\n\nReturns:\n    Fidelity (0 to 1)"
      },
      {
        "tool_name": "calculate_entanglement_entropy",
        "args": [
          "state",
          "partition"
        ],
        "doc": "Calculate entanglement entropy for bipartite system.\n\nArgs:\n    state: Quantum state vector\n    partition: List of qubit indices for first partition\n\nReturns:\n    Von Neumann entropy of reduced density matrix"
      },
      {
        "tool_name": "bell_state_preparation",
        "args": [
          "bell_type"
        ],
        "doc": "Prepare a Bell state (maximally entangled 2-qubit state).\n\nArgs:\n    bell_type: Type of Bell state ('phi_plus', 'phi_minus', 'psi_plus', 'psi_minus')\n\nReturns:\n    Bell state vector"
      },
      {
        "tool_name": "quantum_teleportation",
        "args": [
          "state_to_teleport"
        ],
        "doc": "Simulate quantum teleportation protocol.\n\nArgs:\n    state_to_teleport: Single qubit state to teleport\n\nReturns:\n    Tuple of (measurement results, Bob's final state)"
      }
    ]
  },
  {
    "id": "optics_and_photonics_lab.py",
    "name": "Optics And Photonics",
    "description": "Advanced optics and photonics calculations for wave propagation and nonlinear effects",
    "capabilities": [
      {
        "tool_name": "gaussian_beam_propagation",
        "args": [
          "z",
          "w0",
          "wavelength",
          "n"
        ],
        "doc": "Calculate Gaussian beam parameters during propagation\n\nArgs:\n    z: Propagation distances (m)\n    w0: Beam waist radius (m)\n    wavelength: Wavelength (m)\n    n: Refractive index\n\nReturns:\n    Beam parameters vs distance"
      },
      {
        "tool_name": "fresnel_diffraction",
        "args": [
          "x",
          "aperture_width",
          "distance",
          "wavelength"
        ],
        "doc": "Calculate Fresnel diffraction pattern\n\nArgs:\n    x: Observation points (m)\n    aperture_width: Slit width (m)\n    distance: Propagation distance (m)\n    wavelength: Wavelength (m)\n\nReturns:\n    Intensity distribution"
      },
      {
        "tool_name": "fabry_perot_transmission",
        "args": [
          "wavelengths",
          "cavity_length",
          "R1",
          "R2",
          "n"
        ],
        "doc": "Calculate Fabry-Perot cavity transmission spectrum\n\nArgs:\n    wavelengths: Array of wavelengths (m)\n    cavity_length: Cavity length (m)\n    R1, R2: Mirror reflectivities\n    n: Refractive index in cavity\n\nReturns:\n    Transmission spectrum"
      },
      {
        "tool_name": "mach_zehnder_interference",
        "args": [
          "phase_diff",
          "visibility"
        ],
        "doc": "Calculate Mach-Zehnder interferometer output\n\nArgs:\n    phase_diff: Phase difference between arms (rad)\n    visibility: Fringe visibility (0-1)\n\nReturns:\n    Output intensities at both ports"
      },
      {
        "tool_name": "fiber_mode_propagation",
        "args": [
          "wavelength",
          "core_radius",
          "n_core",
          "n_cladding"
        ],
        "doc": "Calculate fiber optic mode parameters\n\nArgs:\n    wavelength: Wavelength (m)\n    core_radius: Core radius (m)\n    n_core: Core refractive index\n    n_cladding: Cladding refractive index\n\nReturns:\n    Fiber parameters and mode information"
      },
      {
        "tool_name": "nonlinear_spm_phase",
        "args": [
          "power",
          "length",
          "n2",
          "wavelength",
          "area_eff"
        ],
        "doc": "Calculate self-phase modulation in nonlinear medium\n\nArgs:\n    power: Optical power (W)\n    length: Propagation length (m)\n    n2: Nonlinear refractive index (m\u00b2/W)\n    wavelength: Wavelength (m)\n    area_eff: Effective mode area (m\u00b2)\n\nReturns:\n    Nonlinear phase shift (rad)"
      },
      {
        "tool_name": "second_harmonic_generation",
        "args": [
          "fundamental_power",
          "crystal_length",
          "d_eff",
          "wavelength",
          "beam_radius"
        ],
        "doc": "Calculate second harmonic generation efficiency\n\nArgs:\n    fundamental_power: Input power (W)\n    crystal_length: Crystal length (m)\n    d_eff: Effective nonlinear coefficient (m/V)\n    wavelength: Fundamental wavelength (m)\n    beam_radius: Beam radius (m)\n\nReturns:\n    Second harmonic power (W)"
      },
      {
        "tool_name": "bragg_grating_reflection",
        "args": [
          "wavelengths",
          "period",
          "n_eff",
          "delta_n",
          "length"
        ],
        "doc": "Calculate fiber Bragg grating reflection spectrum\n\nArgs:\n    wavelengths: Array of wavelengths (m)\n    period: Grating period (m)\n    n_eff: Effective refractive index\n    delta_n: Index modulation amplitude\n    length: Grating length (m)\n\nReturns:\n    Reflection spectrum"
      },
      {
        "tool_name": "optical_cavity_modes",
        "args": [
          "L",
          "R1",
          "R2",
          "wavelength",
          "n_modes"
        ],
        "doc": "Calculate optical cavity resonator modes\n\nArgs:\n    L: Cavity length (m)\n    R1, R2: Mirror radii of curvature (m)\n    wavelength: Wavelength (m)\n    n_modes: Number of modes to calculate\n\nReturns:\n    Mode frequencies and beam parameters"
      },
      {
        "tool_name": "photonic_bandgap",
        "args": [
          "n1",
          "n2",
          "d1",
          "d2",
          "wavelengths"
        ],
        "doc": "Calculate 1D photonic crystal transmission\n\nArgs:\n    n1, n2: Refractive indices of layers\n    d1, d2: Layer thicknesses (m)\n    wavelengths: Array of wavelengths (m)\n\nReturns:\n    Transmission spectrum"
      },
      {
        "tool_name": "kerr_lens_mode_locking",
        "args": [
          "peak_power",
          "n2",
          "beam_radius",
          "crystal_length"
        ],
        "doc": "Calculate Kerr lens mode-locking parameters\n\nArgs:\n    peak_power: Peak power (W)\n    n2: Nonlinear refractive index (m\u00b2/W)\n    beam_radius: Beam radius (m)\n    crystal_length: Crystal length (m)\n\nReturns:\n    Mode-locking parameters"
      },
      {
        "tool_name": "soliton_propagation",
        "args": [
          "power",
          "beta2",
          "gamma",
          "pulse_width"
        ],
        "doc": "Calculate optical soliton parameters\n\nArgs:\n    power: Peak power (W)\n    beta2: Group velocity dispersion (s\u00b2/m)\n    gamma: Nonlinear coefficient (1/(W\u00b7m))\n    pulse_width: Pulse duration FWHM (s)\n\nReturns:\n    Soliton parameters"
      },
      {
        "tool_name": "demonstrate",
        "args": [],
        "doc": "Demonstrate all optics and photonics calculations"
      }
    ]
  },
  {
    "id": "chemistry_lab.py",
    "name": "Chemistry",
    "description": "Unified chemistry laboratory interface.\n\nProvides access to:\n1. Molecular Dynamics (100k atoms @ 1fs)\n2. Reaction Simulation (TST, NEB, catalysis)\n3. Synthesis Planning (retrosynthesis, optimization)\n4. Spectroscopy Prediction (NMR, IR, UV-Vis, MS, XRD)\n5. Solvation Models (PCM, COSMO, SMD, pH effects)\n6. Quantum Chemistry (DFT, HF, MP2, CCSD(T))\n\nTarget accuracy: <5% error on reaction energetics, <10% on spectroscopy",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a chemistry experiment."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Returns a summary of the lab's configuration and capabilities."
      },
      {
        "tool_name": "create_md_simulation",
        "args": [
          "atoms",
          "box_size",
          "force_field",
          "ensemble",
          "timestep"
        ],
        "doc": "Create molecular dynamics simulation."
      },
      {
        "tool_name": "run_md_simulation",
        "args": [
          "n_steps",
          "temperature",
          "output_interval"
        ],
        "doc": "Run MD simulation."
      },
      {
        "tool_name": "simulate_reaction",
        "args": [
          "reactants",
          "products",
          "conditions",
          "reaction_name",
          "materials_lab",
          "environment_simulator"
        ],
        "doc": "Simulate chemical reaction and predict kinetics."
      },
      {
        "tool_name": "get_reaction_metadata",
        "args": [
          "reaction_name"
        ],
        "doc": "Expose reaction metadata summary."
      },
      {
        "tool_name": "plan_synthesis",
        "args": [
          "target",
          "max_depth"
        ],
        "doc": "Plan synthesis route to target compound."
      },
      {
        "tool_name": "analyze_synthesis_safety",
        "args": [
          "route"
        ],
        "doc": "Analyze safety of synthesis route."
      },
      {
        "tool_name": "predict_nmr",
        "args": [
          "molecule",
          "nucleus"
        ],
        "doc": "Predict NMR spectrum."
      },
      {
        "tool_name": "predict_ir",
        "args": [
          "molecule"
        ],
        "doc": "Predict IR spectrum."
      },
      {
        "tool_name": "predict_uv_vis",
        "args": [
          "molecule"
        ],
        "doc": "Predict UV-Vis spectrum."
      },
      {
        "tool_name": "predict_mass_spectrum",
        "args": [
          "molecule"
        ],
        "doc": "Predict mass spectrum."
      },
      {
        "tool_name": "calculate_solvation_energy",
        "args": [
          "solute",
          "solvent_name",
          "model"
        ],
        "doc": "Calculate solvation free energy."
      },
      {
        "tool_name": "predict_logP",
        "args": [
          "solute"
        ],
        "doc": "Predict octanol-water partition coefficient."
      },
      {
        "tool_name": "calculate_pH_effect",
        "args": [
          "solute",
          "pH",
          "pKa"
        ],
        "doc": "Calculate pH effects on ionization."
      },
      {
        "tool_name": "quantum_calculation",
        "args": [
          "molecule",
          "method",
          "basis_set"
        ],
        "doc": "Perform quantum chemistry calculation."
      },
      {
        "tool_name": "optimize_geometry",
        "args": [
          "molecule",
          "method"
        ],
        "doc": "Optimize molecular geometry."
      },
      {
        "tool_name": "calculate_vibrational_frequencies",
        "args": [
          "molecule"
        ],
        "doc": "Calculate vibrational frequencies."
      },
      {
        "tool_name": "complete_molecule_characterization",
        "args": [
          "molecule"
        ],
        "doc": "Complete characterization of molecule:\n- Spectroscopy (NMR, IR, UV-Vis, MS)\n- Solvation (logP, solubility)\n- Quantum properties (HOMO-LUMO, dipole)"
      },
      {
        "tool_name": "reaction_optimization_workflow",
        "args": [
          "reactants",
          "products",
          "catalysts"
        ],
        "doc": "Optimize reaction conditions:\n- Find optimal catalyst\n- Determine best temperature/pressure\n- Predict yields"
      }
    ]
  },
  {
    "id": "materials_science_lab.py",
    "name": "Materials Science",
    "description": "Comprehensive materials science laboratory",
    "capabilities": [
      {
        "tool_name": "tensile_test",
        "args": [
          "material",
          "max_strain",
          "num_points",
          "temperature"
        ],
        "doc": "Simulate tensile test with elastic and plastic deformation"
      },
      {
        "tool_name": "compression_test",
        "args": [
          "material",
          "max_strain",
          "num_points"
        ],
        "doc": "Simulate compression test with barreling effect"
      },
      {
        "tool_name": "fatigue_analysis",
        "args": [
          "material",
          "stress_amplitude",
          "mean_stress",
          "frequency"
        ],
        "doc": "Fatigue life prediction using S-N curve and Goodman diagram"
      },
      {
        "tool_name": "fracture_toughness",
        "args": [
          "material",
          "crack_length",
          "specimen_width"
        ],
        "doc": "Calculate fracture toughness and critical stress"
      },
      {
        "tool_name": "creep_analysis",
        "args": [
          "material",
          "stress",
          "temperature",
          "time_hours"
        ],
        "doc": "Creep deformation analysis using power law creep"
      },
      {
        "tool_name": "failure_criterion",
        "args": [
          "stress_state",
          "material",
          "criterion"
        ],
        "doc": "Apply failure criteria to multi-axial stress state\nstress_state: [\u03c3_xx, \u03c3_yy, \u03c3_zz, \u03c4_xy, \u03c4_yz, \u03c4_xz]"
      },
      {
        "tool_name": "weibull_analysis",
        "args": [
          "strength_data"
        ],
        "doc": "Weibull statistical analysis for brittle material strength"
      },
      {
        "tool_name": "phase_diagram",
        "args": [
          "component1",
          "component2",
          "temperature_range",
          "composition_range"
        ],
        "doc": "Generate binary phase diagram (simplified)"
      },
      {
        "tool_name": "ttt_diagram",
        "args": [
          "material",
          "carbon_content"
        ],
        "doc": "Time-Temperature-Transformation diagram for steel"
      },
      {
        "tool_name": "precipitation_kinetics",
        "args": [
          "temperature",
          "time",
          "activation_energy"
        ],
        "doc": "Johnson-Mehl-Avrami-Kolmogorov (JMAK) equation for precipitation"
      },
      {
        "tool_name": "rule_of_mixtures",
        "args": [
          "composite"
        ],
        "doc": "Calculate effective properties using rule of mixtures"
      },
      {
        "tool_name": "laminate_analysis",
        "args": [
          "ply_angles",
          "ply_thickness",
          "material_properties"
        ],
        "doc": "Classical Laminate Theory (CLT) analysis"
      },
      {
        "tool_name": "crystal_structure_analysis",
        "args": [
          "structure_type",
          "lattice_parameter"
        ],
        "doc": "Analyze crystal structure properties"
      },
      {
        "tool_name": "bragg_diffraction",
        "args": [
          "lattice_parameter",
          "wavelength",
          "miller_indices"
        ],
        "doc": "Calculate Bragg diffraction angles for given Miller indices"
      },
      {
        "tool_name": "defect_concentration",
        "args": [
          "temperature",
          "formation_energy"
        ],
        "doc": "Calculate equilibrium vacancy concentration"
      }
    ]
  },
  {
    "id": "interest_rate_swap_valuer_lab.py",
    "name": "Interest Rate Swap Valuer",
    "description": "Interest Rate Swap Valuer\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "meteorology_lab.py",
    "name": "Meteorology",
    "description": "Comprehensive meteorology laboratory\nImplements real atmospheric physics and weather prediction algorithms",
    "capabilities": [
      {
        "tool_name": "richardson_number",
        "args": [
          "profile",
          "z1",
          "z2"
        ],
        "doc": "Calculate Richardson number for atmospheric stability\nRi = (g/\u03b8)(\u2202\u03b8/\u2202z) / (\u2202u/\u2202z)\u00b2"
      },
      {
        "tool_name": "marshall_palmer_distribution",
        "args": [
          "rain_rate",
          "diameter_range",
          "n_bins"
        ],
        "doc": "Marshall-Palmer raindrop size distribution\nN(D) = N\u2080 * exp(-\u039b * D)"
      },
      {
        "tool_name": "logarithmic_wind_profile",
        "args": [
          "z_ref",
          "u_ref",
          "z0",
          "heights",
          "stability"
        ],
        "doc": "Logarithmic wind profile in atmospheric boundary layer\nu(z) = (u*/\u03ba) * ln(z/z\u2080) with stability corrections"
      },
      {
        "tool_name": "convective_available_potential_energy",
        "args": [
          "profile",
          "parcel_start"
        ],
        "doc": "Calculate CAPE (Convective Available Potential Energy)\nMeasure of atmospheric instability"
      },
      {
        "tool_name": "lifted_index",
        "args": [
          "temperature_surface",
          "dewpoint_surface",
          "temperature_500mb"
        ],
        "doc": "Calculate Lifted Index for thunderstorm potential\nLI = T\u2085\u2080\u2080 - T_parcel\u2085\u2080\u2080"
      },
      {
        "tool_name": "k_index",
        "args": [
          "T_850",
          "T_500",
          "Td_850",
          "T_700",
          "Td_700"
        ],
        "doc": "Calculate K-Index for thunderstorm potential\nK = (T\u2088\u2085\u2080 - T\u2085\u2080\u2080) + Td\u2088\u2085\u2080 - (T\u2087\u2080\u2080 - Td\u2087\u2080\u2080)"
      },
      {
        "tool_name": "supercell_composite_parameter",
        "args": [
          "storm"
        ],
        "doc": "Calculate Supercell Composite Parameter\nCombines CAPE, shear, and helicity for severe storm prediction"
      },
      {
        "tool_name": "cloud_base_height",
        "args": [
          "temperature",
          "dewpoint"
        ],
        "doc": "Calculate cloud base height using various methods"
      },
      {
        "tool_name": "precipitation_rate_from_radar",
        "args": [
          "reflectivity_dbz",
          "precip_type"
        ],
        "doc": "Convert radar reflectivity to precipitation rate\nUsing Z-R relationships"
      },
      {
        "tool_name": "wet_bulb_temperature",
        "args": [
          "temperature",
          "humidity",
          "pressure"
        ],
        "doc": "Calculate wet bulb temperature\nImportant for heat stress and weather modification"
      },
      {
        "tool_name": "hurricane_intensity_estimation",
        "args": [
          "max_wind_speed",
          "central_pressure",
          "eye_diameter"
        ],
        "doc": "Estimate hurricane intensity and category\nBased on Saffir-Simpson scale and empirical relationships"
      },
      {
        "tool_name": "atmospheric_optical_depth",
        "args": [
          "wavelength",
          "altitude",
          "aerosol_type"
        ],
        "doc": "Calculate atmospheric optical depth for radiation transfer\nImportant for solar energy and visibility calculations"
      }
    ]
  },
  {
    "id": "genomics_lab.py",
    "name": "Genomics",
    "description": "Main genomics laboratory interface",
    "capabilities": [
      {
        "tool_name": "align_sequences",
        "args": [
          "seq1",
          "seq2",
          "mode"
        ],
        "doc": "Align two sequences"
      },
      {
        "tool_name": "call_variants",
        "args": [
          "reference",
          "reads"
        ],
        "doc": "Call variants from sequencing reads"
      },
      {
        "tool_name": "run_gwas",
        "args": [
          "genotype_matrix",
          "phenotypes"
        ],
        "doc": "Run genome-wide association study"
      },
      {
        "tool_name": "pathway_analysis",
        "args": [
          "gene_list",
          "background_size"
        ],
        "doc": "Perform pathway enrichment analysis"
      },
      {
        "tool_name": "cluster_expression",
        "args": [
          "expression_matrix",
          "method"
        ],
        "doc": "Cluster gene expression data"
      },
      {
        "tool_name": "detect_cnvs",
        "args": [
          "coverage_data"
        ],
        "doc": "Detect copy number variations"
      }
    ]
  },
  {
    "id": "electrochemistry_lab.py",
    "name": "Electrochemistry",
    "description": "Production-ready electrochemistry laboratory",
    "capabilities": [
      {
        "tool_name": "nernst_potential",
        "args": [
          "E0",
          "n",
          "activity_ox",
          "activity_red"
        ],
        "doc": "Calculate Nernst potential"
      },
      {
        "tool_name": "calculate_gibbs_energy",
        "args": [
          "E_cell",
          "n"
        ],
        "doc": "Calculate Gibbs free energy from cell potential"
      },
      {
        "tool_name": "calculate_equilibrium_constant",
        "args": [
          "E0_cell",
          "n"
        ],
        "doc": "Calculate equilibrium constant from standard potential"
      },
      {
        "tool_name": "pourbaix_diagram_point",
        "args": [
          "pH",
          "E0",
          "n_electrons",
          "n_protons"
        ],
        "doc": "Calculate potential for Pourbaix diagram at given pH"
      },
      {
        "tool_name": "butler_volmer_current",
        "args": [
          "E",
          "redox"
        ],
        "doc": "Calculate current using Butler-Volmer equation"
      },
      {
        "tool_name": "tafel_analysis",
        "args": [
          "overpotential",
          "current"
        ],
        "doc": "Perform Tafel analysis to extract kinetic parameters"
      },
      {
        "tool_name": "simulate_cyclic_voltammetry",
        "args": [
          "redox",
          "E_initial",
          "E_vertex1",
          "E_vertex2",
          "scan_rate",
          "n_cycles"
        ],
        "doc": "Simulate cyclic voltammogram for reversible system"
      },
      {
        "tool_name": "analyze_cv_peaks",
        "args": [
          "voltammogram"
        ],
        "doc": "Extract peak parameters from cyclic voltammogram"
      },
      {
        "tool_name": "randles_sevcik_analysis",
        "args": [
          "peak_currents",
          "scan_rates",
          "n_electrons"
        ],
        "doc": "Analyze scan rate dependence using Randles-Sevcik equation"
      },
      {
        "tool_name": "simulate_eis_spectrum",
        "args": [
          "frequencies",
          "R_s",
          "R_ct",
          "C_dl",
          "W_coefficient"
        ],
        "doc": "Simulate electrochemical impedance spectrum"
      },
      {
        "tool_name": "fit_randles_circuit",
        "args": [
          "Z_real",
          "Z_imag",
          "frequencies"
        ],
        "doc": "Fit impedance data to Randles equivalent circuit"
      },
      {
        "tool_name": "calculate_exchange_current_from_eis",
        "args": [
          "R_ct",
          "n"
        ],
        "doc": "Calculate exchange current density from charge transfer resistance"
      },
      {
        "tool_name": "cottrell_equation",
        "args": [
          "time",
          "n",
          "concentration",
          "D"
        ],
        "doc": "Calculate current using Cottrell equation"
      },
      {
        "tool_name": "simulate_chronoamperometry",
        "args": [
          "E_step",
          "redox",
          "duration",
          "n_points"
        ],
        "doc": "Simulate chronoamperometric response"
      },
      {
        "tool_name": "analyze_cottrell_plot",
        "args": [
          "time",
          "current",
          "n_electrons",
          "concentration"
        ],
        "doc": "Analyze Cottrell plot to extract diffusion coefficient"
      },
      {
        "tool_name": "battery_capacity",
        "args": [
          "n_electrons",
          "mass_active",
          "molecular_weight"
        ],
        "doc": "Calculate theoretical battery capacity"
      },
      {
        "tool_name": "battery_energy_density",
        "args": [
          "voltage",
          "capacity"
        ],
        "doc": "Calculate energy density"
      },
      {
        "tool_name": "simulate_battery_discharge",
        "args": [
          "capacity",
          "current",
          "internal_resistance",
          "nominal_voltage",
          "cutoff_voltage"
        ],
        "doc": "Simulate battery discharge curve"
      },
      {
        "tool_name": "battery_internal_resistance",
        "args": [
          "ocv",
          "load_voltage",
          "current"
        ],
        "doc": "Calculate internal resistance from load test"
      },
      {
        "tool_name": "corrosion_rate",
        "args": [
          "i_corr",
          "n",
          "molecular_weight",
          "density"
        ],
        "doc": "Calculate corrosion rate from corrosion current"
      },
      {
        "tool_name": "evans_diagram",
        "args": [
          "E_range",
          "metal_redox",
          "oxidant_redox"
        ],
        "doc": "Generate Evans diagram for corrosion analysis"
      },
      {
        "tool_name": "passivation_analysis",
        "args": [
          "potential",
          "current"
        ],
        "doc": "Analyze passivation behavior from polarization curve"
      }
    ]
  },
  {
    "id": "robotics_lab.py",
    "name": "Robotics",
    "description": "Comprehensive robotics laboratory with kinematics, dynamics, and planning",
    "capabilities": [
      {
        "tool_name": "dh_matrix",
        "args": [
          "theta",
          "d",
          "a",
          "alpha"
        ],
        "doc": "Compute Denavit-Hartenberg transformation matrix\ntheta: joint angle\nd: link offset\na: link length\nalpha: link twist"
      },
      {
        "tool_name": "forward_kinematics",
        "args": [
          "robot",
          "joint_angles"
        ],
        "doc": "Calculate end-effector position and orientation using DH parameters\nReturns: (end_effector_pose, all_link_poses)"
      },
      {
        "tool_name": "jacobian",
        "args": [
          "robot",
          "joint_angles"
        ],
        "doc": "Compute manipulator Jacobian matrix\nMaps joint velocities to end-effector velocities"
      },
      {
        "tool_name": "inverse_kinematics_numerical",
        "args": [
          "robot",
          "target_pose",
          "initial_guess",
          "max_iterations",
          "tolerance"
        ],
        "doc": "Numerical inverse kinematics using Jacobian pseudo-inverse"
      },
      {
        "tool_name": "inverse_kinematics_analytical_2dof",
        "args": [
          "l1",
          "l2",
          "x",
          "y"
        ],
        "doc": "Analytical inverse kinematics for 2-DOF planar arm"
      },
      {
        "tool_name": "rrt",
        "args": [
          "start",
          "goal",
          "obstacles",
          "max_iterations",
          "step_size",
          "goal_tolerance"
        ],
        "doc": "Rapidly-exploring Random Tree (RRT) path planning\nobstacles: list of (center, radius) for spherical obstacles"
      },
      {
        "tool_name": "astar_grid",
        "args": [
          "grid",
          "start",
          "goal"
        ],
        "doc": "A* path planning on 2D grid\ngrid: 2D array where 0 is free, 1 is obstacle"
      },
      {
        "tool_name": "trajectory_generation",
        "args": [
          "waypoints",
          "total_time",
          "method"
        ],
        "doc": "Generate smooth trajectory through waypoints\nmethod: \"cubic\" or \"quintic\" spline"
      },
      {
        "tool_name": "mass_matrix",
        "args": [
          "robot",
          "joint_angles"
        ],
        "doc": "Compute manipulator mass/inertia matrix M(q)\nUsed in dynamics equation: M(q)q\u0308 + C(q,q\u0307)q\u0307 + G(q) = \u03c4"
      },
      {
        "tool_name": "coriolis_matrix",
        "args": [
          "robot",
          "joint_angles",
          "joint_velocities"
        ],
        "doc": "Compute Coriolis and centrifugal terms C(q,q\u0307)"
      },
      {
        "tool_name": "gravity_vector",
        "args": [
          "robot",
          "joint_angles"
        ],
        "doc": "Compute gravity compensation torques G(q)"
      },
      {
        "tool_name": "forward_dynamics",
        "args": [
          "robot",
          "joint_angles",
          "joint_velocities",
          "joint_torques"
        ],
        "doc": "Compute joint accelerations from torques\nq\u0308 = M\u207b\u00b9(\u03c4 - C*q\u0307 - G)"
      },
      {
        "tool_name": "inverse_dynamics",
        "args": [
          "robot",
          "joint_angles",
          "joint_velocities",
          "joint_accelerations"
        ],
        "doc": "Compute required torques for desired motion\n\u03c4 = M*q\u0308 + C*q\u0307 + G"
      },
      {
        "tool_name": "ekf_slam",
        "args": [
          "robot_pose",
          "landmarks",
          "measurement",
          "motion",
          "P",
          "Q",
          "R"
        ],
        "doc": "Extended Kalman Filter SLAM update\nrobot_pose: [x, y, theta]\nlandmarks: {id: [x, y]}\nmeasurement: (landmark_id, range, bearing)\nmotion: (linear_vel, angular_vel)"
      },
      {
        "tool_name": "particle_filter_localization",
        "args": [
          "particles",
          "weights",
          "motion",
          "measurements",
          "landmark_map"
        ],
        "doc": "Particle filter for robot localization\nparticles: Nx3 array of [x, y, theta] poses\nmeasurements: list of (range, bearing) to landmarks"
      },
      {
        "tool_name": "computed_torque_control",
        "args": [
          "robot",
          "desired_angles",
          "desired_velocities",
          "desired_accelerations",
          "current_angles",
          "current_velocities",
          "Kp",
          "Kv"
        ],
        "doc": "Computed torque control for trajectory tracking"
      },
      {
        "tool_name": "impedance_control",
        "args": [
          "robot",
          "joint_angles",
          "joint_velocities",
          "desired_position",
          "external_force",
          "M_d",
          "B_d",
          "K_d"
        ],
        "doc": "Impedance control for compliant behavior\nM_d, B_d, K_d: desired mass, damping, stiffness matrices"
      },
      {
        "tool_name": "workspace_analysis",
        "args": [
          "robot",
          "samples"
        ],
        "doc": "Analyze robot workspace through Monte Carlo sampling\nReturns: (reachable_points, joint_configurations)"
      }
    ]
  },
  {
    "id": "seismology_lab.py",
    "name": "Seismology",
    "description": "Comprehensive seismology laboratory\nImplements real seismic wave propagation and hazard analysis",
    "capabilities": [
      {
        "tool_name": "p_wave_propagation",
        "args": [
          "source",
          "station",
          "earth_model"
        ],
        "doc": "Calculate P-wave propagation characteristics\nUsing ray theory and travel time tables"
      },
      {
        "tool_name": "s_wave_propagation",
        "args": [
          "source",
          "station"
        ],
        "doc": "Calculate S-wave propagation characteristics\nS-waves are slower and don't travel through liquid"
      },
      {
        "tool_name": "richter_magnitude",
        "args": [
          "amplitude",
          "distance",
          "station_correction"
        ],
        "doc": "Calculate Richter (Local) Magnitude ML\nML = log10(A) + distance_correction + station_correction"
      },
      {
        "tool_name": "moment_magnitude",
        "args": [
          "moment"
        ],
        "doc": "Calculate Moment Magnitude (Mw)\nMw = (2/3) * log10(M0) - 10.7\nwhere M0 is seismic moment in dyne\u00b7cm"
      },
      {
        "tool_name": "site_amplification",
        "args": [
          "input_motion",
          "frequency",
          "soil_class",
          "depth_to_bedrock"
        ],
        "doc": "Calculate site amplification effects\nBased on NEHRP provisions and Vs30"
      },
      {
        "tool_name": "seismic_hazard_curve",
        "args": [
          "site_lat",
          "site_lon",
          "return_periods"
        ],
        "doc": "Calculate probabilistic seismic hazard curve\nSimplified PSHA calculation"
      },
      {
        "tool_name": "ground_motion_prediction",
        "args": [
          "magnitude",
          "distance",
          "site_class",
          "gmpe_model"
        ],
        "doc": "Ground Motion Prediction Equation (GMPE)\nEstimates PGA, PGV, and response spectra"
      },
      {
        "tool_name": "earthquake_early_warning",
        "args": [
          "p_arrival_time",
          "s_arrival_time",
          "p_amplitude",
          "frequency"
        ],
        "doc": "Earthquake Early Warning calculations\nBased on P-wave parameters to estimate magnitude and intensity"
      },
      {
        "tool_name": "fault_rupture_model",
        "args": [
          "magnitude",
          "fault_type"
        ],
        "doc": "Empirical fault rupture scaling relationships\nWells and Coppersmith (1994) relations"
      },
      {
        "tool_name": "surface_wave_dispersion",
        "args": [
          "periods",
          "layer_model"
        ],
        "doc": "Calculate surface wave dispersion curves\nFor Rayleigh and Love waves"
      }
    ]
  },
  {
    "id": "optimization_theory_lab.py",
    "name": "Optimization Theory",
    "description": "Comprehensive optimization laboratory with classical and modern algorithms",
    "capabilities": [
      {
        "tool_name": "gradient_descent",
        "args": [
          "f",
          "grad_f",
          "x0",
          "learning_rate",
          "max_iter",
          "tol"
        ],
        "doc": "Basic gradient descent optimization"
      },
      {
        "tool_name": "momentum_gradient_descent",
        "args": [
          "f",
          "grad_f",
          "x0",
          "learning_rate",
          "momentum",
          "max_iter",
          "tol"
        ],
        "doc": "Gradient descent with momentum (accelerated)"
      },
      {
        "tool_name": "adam_optimizer",
        "args": [
          "f",
          "grad_f",
          "x0",
          "learning_rate",
          "beta1",
          "beta2",
          "epsilon",
          "max_iter",
          "tol"
        ],
        "doc": "Adam (Adaptive Moment Estimation) optimizer"
      },
      {
        "tool_name": "newton_method",
        "args": [
          "f",
          "grad_f",
          "hess_f",
          "x0",
          "max_iter",
          "tol"
        ],
        "doc": "Newton's method for optimization (requires Hessian)"
      },
      {
        "tool_name": "bfgs",
        "args": [
          "f",
          "grad_f",
          "x0",
          "max_iter",
          "tol"
        ],
        "doc": "BFGS quasi-Newton method"
      },
      {
        "tool_name": "conjugate_gradient",
        "args": [
          "f",
          "grad_f",
          "x0",
          "max_iter",
          "tol"
        ],
        "doc": "Nonlinear conjugate gradient method (Fletcher-Reeves)"
      },
      {
        "tool_name": "simplex_method",
        "args": [
          "c",
          "A_ub",
          "b_ub",
          "A_eq",
          "b_eq",
          "bounds"
        ],
        "doc": "Simplex method for linear programming\nMinimize: c^T x\nSubject to: A_ub x <= b_ub, A_eq x = b_eq, bounds on x"
      },
      {
        "tool_name": "interior_point_method",
        "args": [
          "f",
          "grad_f",
          "constraints",
          "x0",
          "barrier_param",
          "max_iter",
          "tol"
        ],
        "doc": "Interior point method for constrained optimization"
      },
      {
        "tool_name": "genetic_algorithm",
        "args": [
          "f",
          "bounds",
          "population_size",
          "generations",
          "crossover_rate",
          "mutation_rate"
        ],
        "doc": "Genetic algorithm for global optimization"
      },
      {
        "tool_name": "simulated_annealing",
        "args": [
          "f",
          "x0",
          "bounds",
          "T0",
          "cooling_rate",
          "max_iter"
        ],
        "doc": "Simulated annealing for global optimization"
      },
      {
        "tool_name": "particle_swarm",
        "args": [
          "f",
          "bounds",
          "n_particles",
          "max_iter",
          "w",
          "c1",
          "c2"
        ],
        "doc": "Particle Swarm Optimization (PSO)"
      },
      {
        "tool_name": "differential_evolution",
        "args": [
          "f",
          "bounds",
          "population_size",
          "F",
          "CR",
          "max_iter"
        ],
        "doc": "Differential Evolution algorithm"
      },
      {
        "tool_name": "penalty_method",
        "args": [
          "f",
          "constraints",
          "x0",
          "penalty_param",
          "max_iter"
        ],
        "doc": "Penalty method for constrained optimization"
      },
      {
        "tool_name": "augmented_lagrangian",
        "args": [
          "f",
          "grad_f",
          "constraints",
          "x0",
          "max_iter"
        ],
        "doc": "Augmented Lagrangian method for constrained optimization"
      },
      {
        "tool_name": "pareto_front",
        "args": [
          "objectives",
          "bounds",
          "n_points"
        ],
        "doc": "Find Pareto front for multi-objective optimization"
      },
      {
        "tool_name": "weighted_sum_method",
        "args": [
          "objectives",
          "weights",
          "bounds"
        ],
        "doc": "Weighted sum method for multi-objective optimization"
      },
      {
        "tool_name": "benchmark_algorithms",
        "args": [
          "function_name",
          "dimension",
          "algorithms"
        ],
        "doc": "Benchmark multiple algorithms on a test function"
      }
    ]
  },
  {
    "id": "neural_architecture_search_space_lab.py",
    "name": "Neural Architecture Search Space",
    "description": "Neural Architecture Search Space\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "thermodynamics_lab.py",
    "name": "Thermodynamics",
    "description": "Advanced thermodynamics laboratory for comprehensive thermodynamic simulations.",
    "capabilities": [
      {
        "tool_name": "ideal_gas_pressure",
        "args": [
          "n",
          "V",
          "T"
        ],
        "doc": "Calculate pressure using ideal gas law.\nPV = nRT"
      },
      {
        "tool_name": "ideal_gas_volume",
        "args": [
          "n",
          "P",
          "T"
        ],
        "doc": "Calculate volume using ideal gas law."
      },
      {
        "tool_name": "van_der_waals",
        "args": [
          "n",
          "V",
          "T",
          "a",
          "b"
        ],
        "doc": "Calculate pressure using van der Waals equation.\n\n(P + a*n\u00b2/V\u00b2)(V - nb) = nRT\nwhere a accounts for intermolecular attraction\nand b accounts for molecular volume"
      },
      {
        "tool_name": "van_der_waals_volume",
        "args": [
          "n",
          "P",
          "T",
          "a",
          "b"
        ],
        "doc": "Solve van der Waals equation for volume."
      },
      {
        "tool_name": "peng_robinson",
        "args": [
          "T",
          "P",
          "component",
          "solve_for"
        ],
        "doc": "Peng-Robinson equation of state.\n\nP = RT/(V-b) - a(T)/(V(V+b) + b(V-b))"
      },
      {
        "tool_name": "redlich_kwong_soave",
        "args": [
          "T",
          "P",
          "component"
        ],
        "doc": "Soave-Redlich-Kwong equation of state.\n\nP = RT/(V-b) - a(T)/(V(V+b))"
      },
      {
        "tool_name": "compressibility_factor",
        "args": [
          "T",
          "P",
          "V",
          "n"
        ],
        "doc": "Calculate compressibility factor Z = PV/(nRT)"
      },
      {
        "tool_name": "fugacity_coefficient_ideal",
        "args": [],
        "doc": "Fugacity coefficient for ideal gas (always 1)."
      },
      {
        "tool_name": "fugacity_coefficient_virial",
        "args": [
          "T",
          "P",
          "B"
        ],
        "doc": "Calculate fugacity coefficient using second virial coefficient.\n\nln(\u03c6) = B*P/(RT)"
      },
      {
        "tool_name": "fugacity_coefficient_pr",
        "args": [
          "T",
          "P",
          "component"
        ],
        "doc": "Calculate fugacity coefficient using Peng-Robinson EOS."
      },
      {
        "tool_name": "activity_coefficient_margules",
        "args": [
          "x1",
          "A12",
          "A21"
        ],
        "doc": "Calculate activity coefficients using Margules equation.\n\nln(\u03b31) = x2\u00b2 * (A12 + 2*(A21 - A12)*x1)"
      },
      {
        "tool_name": "activity_coefficient_wilson",
        "args": [
          "x1",
          "T",
          "Lambda12",
          "Lambda21"
        ],
        "doc": "Calculate activity coefficients using Wilson equation."
      },
      {
        "tool_name": "activity_coefficient_nrtl",
        "args": [
          "x1",
          "T",
          "tau12",
          "tau21",
          "alpha"
        ],
        "doc": "Calculate activity coefficients using NRTL equation."
      },
      {
        "tool_name": "vapor_pressure_antoine",
        "args": [
          "T",
          "A",
          "B",
          "C"
        ],
        "doc": "Calculate vapor pressure using Antoine equation.\n\nlog10(P) = A - B/(C + T)\nP in mmHg, T in \u00b0C"
      },
      {
        "tool_name": "vapor_pressure_clausius_clapeyron",
        "args": [
          "T",
          "T_ref",
          "P_ref",
          "delta_H_vap"
        ],
        "doc": "Calculate vapor pressure using Clausius-Clapeyron equation.\n\nln(P/P_ref) = -\u0394Hvap/R * (1/T - 1/T_ref)"
      },
      {
        "tool_name": "bubble_point_calculation",
        "args": [
          "mixture",
          "P"
        ],
        "doc": "Calculate bubble point temperature and vapor composition."
      },
      {
        "tool_name": "dew_point_calculation",
        "args": [
          "mixture",
          "P"
        ],
        "doc": "Calculate dew point temperature and liquid composition."
      },
      {
        "tool_name": "flash_calculation",
        "args": [
          "mixture",
          "T",
          "P"
        ],
        "doc": "Perform isothermal flash calculation.\nReturns vapor fraction and compositions."
      },
      {
        "tool_name": "equilibrium_constant",
        "args": [
          "delta_G",
          "T"
        ],
        "doc": "Calculate equilibrium constant from Gibbs energy.\n\n\u0394G\u00b0 = -RT*ln(K)"
      },
      {
        "tool_name": "van_t_hoff_equation",
        "args": [
          "K1",
          "T1",
          "T2",
          "delta_H"
        ],
        "doc": "Calculate equilibrium constant at different temperature.\n\nln(K2/K1) = -\u0394H/R * (1/T2 - 1/T1)"
      },
      {
        "tool_name": "reaction_gibbs_energy",
        "args": [
          "products",
          "reactants",
          "stoich_products",
          "stoich_reactants",
          "T"
        ],
        "doc": "Calculate Gibbs energy of reaction.\n\n\u0394G_rxn = \u03a3(\u03bd_products * G_products) - \u03a3(\u03bd_reactants * G_reactants)"
      },
      {
        "tool_name": "reaction_enthalpy",
        "args": [
          "products",
          "reactants",
          "stoich_products",
          "stoich_reactants"
        ],
        "doc": "Calculate enthalpy of reaction.\n\n\u0394H_rxn = \u03a3(\u03bd_products * H_products) - \u03a3(\u03bd_reactants * H_reactants)"
      },
      {
        "tool_name": "chemical_equilibrium_composition",
        "args": [
          "initial_moles",
          "stoichiometry",
          "K"
        ],
        "doc": "Calculate equilibrium composition for reaction.\n\naA + bB \u21cc cC + dD"
      },
      {
        "tool_name": "heat_capacity_polynomial",
        "args": [
          "T",
          "coeffs"
        ],
        "doc": "Calculate heat capacity using polynomial correlation.\n\nCp = a + b*T + c*T\u00b2 + d*T\u00b3 + ..."
      },
      {
        "tool_name": "heat_capacity_shomate",
        "args": [
          "T",
          "params"
        ],
        "doc": "Calculate heat capacity using Shomate equation.\n\nCp = A + B*t + C*t\u00b2 + D*t\u00b3 + E/t\u00b2\nwhere t = T/1000"
      },
      {
        "tool_name": "heat_capacity_integration",
        "args": [
          "T1",
          "T2",
          "cp_function"
        ],
        "doc": "Integrate heat capacity to get enthalpy change.\n\n\u0394H = \u222bCp dT from T1 to T2"
      },
      {
        "tool_name": "entropy_ideal_gas",
        "args": [
          "T",
          "P",
          "component"
        ],
        "doc": "Calculate absolute entropy of ideal gas.\n\nS = S\u00b0 + Cp*ln(T/T\u00b0) - R*ln(P/P\u00b0)"
      },
      {
        "tool_name": "entropy_mixing",
        "args": [
          "mole_fractions"
        ],
        "doc": "Calculate entropy of mixing for ideal mixture.\n\n\u0394S_mix = -R * \u03a3(xi * ln(xi))"
      },
      {
        "tool_name": "gibbs_energy",
        "args": [
          "H",
          "T",
          "S"
        ],
        "doc": "Calculate Gibbs energy.\n\nG = H - T*S"
      },
      {
        "tool_name": "helmholtz_energy",
        "args": [
          "U",
          "T",
          "S"
        ],
        "doc": "Calculate Helmholtz energy.\n\nA = U - T*S"
      },
      {
        "tool_name": "joule_thomson_coefficient_ideal",
        "args": [],
        "doc": "Joule-Thomson coefficient for ideal gas (always 0)."
      },
      {
        "tool_name": "joule_thomson_coefficient_vdw",
        "args": [
          "T",
          "P",
          "a",
          "b",
          "Cp"
        ],
        "doc": "Calculate Joule-Thomson coefficient for van der Waals gas.\n\n\u03bc_JT = (\u2202T/\u2202P)_H = (1/Cp) * (T*(\u2202V/\u2202T)_P - V)"
      },
      {
        "tool_name": "inversion_temperature",
        "args": [
          "a",
          "b"
        ],
        "doc": "Calculate Joule-Thomson inversion temperature.\n\nFor van der Waals gas: T_inv = 2a/(Rb)"
      },
      {
        "tool_name": "carnot_efficiency",
        "args": [
          "T_hot",
          "T_cold"
        ],
        "doc": "Calculate Carnot cycle efficiency.\n\n\u03b7 = 1 - T_cold/T_hot"
      },
      {
        "tool_name": "rankine_cycle",
        "args": [
          "T_boiler",
          "T_condenser",
          "P_boiler",
          "P_condenser",
          "efficiency_turbine",
          "efficiency_pump"
        ],
        "doc": "Calculate Rankine cycle performance."
      },
      {
        "tool_name": "refrigeration_cycle",
        "args": [
          "T_evaporator",
          "T_condenser",
          "refrigerant"
        ],
        "doc": "Calculate vapor-compression refrigeration cycle."
      },
      {
        "tool_name": "run_comprehensive_demo",
        "args": [],
        "doc": "Run comprehensive demonstration of thermodynamics capabilities."
      }
    ]
  },
  {
    "id": "organic_chemistry_lab.py",
    "name": "Organic Chemistry",
    "description": "Production-ready organic chemistry laboratory with comprehensive algorithms",
    "capabilities": [
      {
        "tool_name": "predict_reaction_mechanism",
        "args": [
          "reactants",
          "conditions"
        ],
        "doc": "Predict reaction mechanism based on reactants and conditions"
      },
      {
        "tool_name": "retrosynthesis_planning",
        "args": [
          "target",
          "max_steps"
        ],
        "doc": "Plan retrosynthetic route to target molecule"
      },
      {
        "tool_name": "stereochemistry_analysis",
        "args": [
          "molecule"
        ],
        "doc": "Analyze stereochemistry of molecule"
      },
      {
        "tool_name": "predict_pka",
        "args": [
          "molecule",
          "functional_group"
        ],
        "doc": "Predict pKa value for functional group in molecule"
      },
      {
        "tool_name": "estimate_reaction_yield",
        "args": [
          "mechanism",
          "conditions",
          "side_reactions"
        ],
        "doc": "Estimate reaction yield based on mechanism and conditions"
      },
      {
        "tool_name": "protecting_group_strategy",
        "args": [
          "molecule",
          "target_group",
          "reaction_conditions"
        ],
        "doc": "Design protecting group strategy for selective reactions"
      },
      {
        "tool_name": "calculate_hammett_parameter",
        "args": [
          "substituent"
        ],
        "doc": "Calculate Hammett sigma parameter for aromatic substituents"
      },
      {
        "tool_name": "predict_nmr_chemical_shift",
        "args": [
          "atom_type",
          "environment"
        ],
        "doc": "Predict NMR chemical shift based on atom environment"
      },
      {
        "tool_name": "orbital_hybridization_analysis",
        "args": [
          "atom"
        ],
        "doc": "Analyze orbital hybridization and geometry"
      },
      {
        "tool_name": "calculate_reaction_rate",
        "args": [
          "mechanism",
          "concentrations"
        ],
        "doc": "Calculate reaction rate based on mechanism and concentrations"
      }
    ]
  },
  {
    "id": "oceanography_lab.py",
    "name": "Oceanography",
    "description": "A class representing an oceanographic laboratory with various functionalities for marine research and analysis.",
    "capabilities": [
      {
        "tool_name": "calculate_density",
        "args": [
          "temperature"
        ],
        "doc": "Calculate the density of seawater using polynomial approximation."
      },
      {
        "tool_name": "calculate_salinity_effects",
        "args": [
          "salinity"
        ],
        "doc": "Calculate the effect of salinity on water density."
      },
      {
        "tool_name": "calculate_pressure_at_depth",
        "args": [],
        "doc": "Calculate pressure at different depths in the ocean."
      },
      {
        "tool_name": "run_simulation",
        "args": [
          "temperature",
          "salinity"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "run_demo",
        "args": [],
        "doc": "Run a demonstration of the OceanographyLab simulation."
      }
    ]
  },
  {
    "id": "cardiovascular_plaque_lab.py",
    "name": "Cardiovascular Plaque",
    "description": "",
    "capabilities": [
      {
        "tool_name": "simulate_plaque_formation",
        "args": [],
        "doc": "Simulates LDL particle accumulation leading to plaque formation.\n\nAddresses Question 1: LDL particle mechanisms in atherosclerotic plaque formation"
      },
      {
        "tool_name": "simulate_endothelial_dysfunction",
        "args": [],
        "doc": "Addresses Question 2: Endothelial dysfunction in systemic hypertension"
      },
      {
        "tool_name": "simulate_platelet_aggregation",
        "args": [],
        "doc": "Addresses Question 3: Protein-protein interactions in platelet aggregation"
      },
      {
        "tool_name": "simulate_ischemic_injury",
        "args": [],
        "doc": "Addresses Question 4: Extracellular vesicles in ischemic injury post-MI"
      },
      {
        "tool_name": "genetic_variants_analysis",
        "args": [],
        "doc": "Addresses Question 5: Genetic variants affecting arterial wall biomechanics"
      },
      {
        "tool_name": "plaque_calcification_prevention",
        "args": [],
        "doc": "Addresses Question 6: Plaque calcification prevention targets"
      },
      {
        "tool_name": "inflammation_effects",
        "args": [],
        "doc": "Addresses Question 7: Chronic inflammation effects on plaque stability"
      },
      {
        "tool_name": "mechanical_stressors_on_smv",
        "args": [],
        "doc": "Addresses Question 8: Mechanical stressors on vascular smooth muscle gene expression"
      },
      {
        "tool_name": "cardiac_fibrosis_inhibition",
        "args": [],
        "doc": "Addresses Question 9: Novel molecules inhibiting cardiac fibrosis"
      },
      {
        "tool_name": "left_ventricular_hypertrophy",
        "args": [],
        "doc": "Addresses Question 10: Biomechanical forces in left ventricular hypertrophy"
      }
    ]
  },
  {
    "id": "bitcoin_lab.py",
    "name": "Bitcoin",
    "description": "Advanced lab for Bitcoin ledger analysis and reclamation.\nImplements the MAOAO (Multiple-Access Optical-Addressed-Optimization) algorithm.",
    "capabilities": [
      {
        "tool_name": "maoao_reclamation_search",
        "args": [
          "target_address",
          "constraints"
        ],
        "doc": "Executes the MAOAO algorithm to optimize the search space for a forgotten private key.\nMAOAO: Multiple-Access Optical-Addressed-Optimization.\n\nArgs:\n    target_address: The Bitcoin address to analyze.\n    constraints: Known partial information (e.g., 'prefix', 'leak_pattern', 'timestamp_range').\n    \nReturns:\n    Dict containing the optimization results and identified search nodes."
      },
      {
        "tool_name": "solve_math_bottleneck",
        "args": [
          "problem_description"
        ],
        "doc": "Solves specific mathematical bottlenecks encountered during BTC reclamation."
      }
    ]
  },
  {
    "id": "computational_neuroscience_lab.py",
    "name": "Computational Neuroscience",
    "description": "Simulate neural dynamics and brain circuits",
    "capabilities": [
      {
        "tool_name": "simulate_spiking_neuron",
        "args": [
          "input_current",
          "duration_ms"
        ],
        "doc": "Leaky integrate-and-fire neuron model"
      },
      {
        "tool_name": "analyze_eeg_rhythm",
        "args": [
          "signal",
          "sampling_rate"
        ],
        "doc": "Analyze EEG frequency bands"
      },
      {
        "tool_name": "simulate_neural_network",
        "args": [
          "n_neurons",
          "simulation_time"
        ],
        "doc": "Simulate recurrent neural network dynamics"
      }
    ]
  },
  {
    "id": "bioinformatics_lab.py",
    "name": "Bioinformatics",
    "description": "Production-ready bioinformatics analysis laboratory.",
    "capabilities": [
      {
        "tool_name": "gc_content",
        "args": [
          "sequence"
        ],
        "doc": "Calculate GC content of a DNA sequence."
      },
      {
        "tool_name": "transcribe",
        "args": [
          "dna_sequence"
        ],
        "doc": "Transcribe DNA to RNA."
      },
      {
        "tool_name": "translate",
        "args": [
          "dna_sequence"
        ],
        "doc": "Translate DNA sequence to protein sequence."
      },
      {
        "tool_name": "find_orfs",
        "args": [
          "sequence",
          "min_length"
        ],
        "doc": "Find all open reading frames in a DNA sequence."
      },
      {
        "tool_name": "needleman_wunsch",
        "args": [
          "seq1",
          "seq2",
          "match",
          "mismatch",
          "gap"
        ],
        "doc": "Perform global sequence alignment using Needleman-Wunsch algorithm."
      },
      {
        "tool_name": "smith_waterman",
        "args": [
          "seq1",
          "seq2",
          "match",
          "mismatch",
          "gap"
        ],
        "doc": "Perform local sequence alignment using Smith-Waterman algorithm."
      },
      {
        "tool_name": "multiple_sequence_alignment",
        "args": [
          "sequences"
        ],
        "doc": "Perform progressive multiple sequence alignment."
      },
      {
        "tool_name": "find_motifs",
        "args": [
          "sequence",
          "motif_pattern"
        ],
        "doc": "Find all occurrences of a motif pattern in a sequence using regex."
      },
      {
        "tool_name": "build_phylogenetic_tree",
        "args": [
          "sequences"
        ],
        "doc": "Build a phylogenetic tree using neighbor-joining method."
      },
      {
        "tool_name": "predict_secondary_structure",
        "args": [
          "protein_sequence"
        ],
        "doc": "Predict protein secondary structure using Chou-Fasman method."
      },
      {
        "tool_name": "calculate_molecular_weight",
        "args": [
          "protein_sequence"
        ],
        "doc": "Calculate molecular weight of a protein sequence."
      },
      {
        "tool_name": "calculate_isoelectric_point",
        "args": [
          "protein_sequence"
        ],
        "doc": "Calculate theoretical isoelectric point (pI) of a protein."
      },
      {
        "tool_name": "hydropathy_profile",
        "args": [
          "protein_sequence",
          "window_size"
        ],
        "doc": "Calculate Kyte-Doolittle hydropathy profile."
      },
      {
        "tool_name": "run_comprehensive_analysis",
        "args": [
          "dna_sequence"
        ],
        "doc": "Run complete bioinformatics analysis pipeline."
      }
    ]
  },
  {
    "id": "chemical_engineering_lab.py",
    "name": "Chemical Engineering",
    "description": "Comprehensive chemical engineering calculations including:\n- Reactor design (CSTR, PFR, Batch)\n- Mass and energy balances\n- Separation processes (distillation, extraction, absorption)\n- Heat exchanger design\n- Reaction kinetics\n- Process optimization",
    "capabilities": [
      {
        "tool_name": "ideal_gas_law",
        "args": [
          "p",
          "v",
          "n",
          "t"
        ],
        "doc": "Calculate missing value using ideal gas law: PV = nRT\n\nArgs:\n    p: Pressure in Pa\n    v: Volume in m\u00b3\n    n: Moles\n    t: Temperature in K\n\nReturns:\n    Dictionary with all four values"
      },
      {
        "tool_name": "reaction_rate",
        "args": [
          "concentration",
          "rate_constant",
          "order",
          "temperature"
        ],
        "doc": "Calculate reaction rate using power law kinetics\n\nRate = k * \u220f(C_i^n_i)\n\nArgs:\n    concentration: Concentration array in mol/m\u00b3\n    rate_constant: Rate constant (units depend on order)\n    order: Reaction order for each component\n    temperature: Temperature in K (for Arrhenius correction)\n\nReturns:\n    Reaction rate in mol/(m\u00b3\u00b7s)"
      },
      {
        "tool_name": "arrhenius_equation",
        "args": [
          "pre_exponential",
          "activation_energy",
          "temperature"
        ],
        "doc": "Calculate rate constant using Arrhenius equation\n\nk = A * exp(-Ea/(RT))\n\nArgs:\n    pre_exponential: Pre-exponential factor (same units as k)\n    activation_energy: Activation energy in J/mol\n    temperature: Temperature in K (default: self.temperature)\n\nReturns:\n    Rate constant"
      },
      {
        "tool_name": "cstr_design",
        "args": [
          "flow_rate",
          "concentration_in",
          "rate_constant",
          "reaction_order",
          "conversion"
        ],
        "doc": "Design Continuous Stirred Tank Reactor (CSTR)\n\nArgs:\n    flow_rate: Volumetric flow rate in m\u00b3/s\n    concentration_in: Inlet concentration in mol/m\u00b3\n    rate_constant: Rate constant (units depend on order)\n    reaction_order: Reaction order\n    conversion: Desired conversion (0-1)\n\nReturns:\n    Dictionary with reactor volume, residence time, outlet concentration"
      },
      {
        "tool_name": "pfr_design",
        "args": [
          "flow_rate",
          "concentration_in",
          "rate_constant",
          "reaction_order",
          "conversion"
        ],
        "doc": "Design Plug Flow Reactor (PFR)\n\nArgs:\n    flow_rate: Volumetric flow rate in m\u00b3/s\n    concentration_in: Inlet concentration in mol/m\u00b3\n    rate_constant: Rate constant (units depend on order)\n    reaction_order: Reaction order\n    conversion: Desired conversion (0-1)\n\nReturns:\n    Dictionary with reactor volume, residence time, outlet concentration"
      },
      {
        "tool_name": "batch_reactor",
        "args": [
          "initial_concentration",
          "rate_constant",
          "reaction_order",
          "time"
        ],
        "doc": "Calculate concentration profile in batch reactor\n\nArgs:\n    initial_concentration: Initial concentration in mol/m\u00b3\n    rate_constant: Rate constant (units depend on order)\n    reaction_order: Reaction order\n    time: Time array in seconds\n\nReturns:\n    Concentration array in mol/m\u00b3"
      },
      {
        "tool_name": "mass_balance",
        "args": [
          "inlet_flow",
          "outlet_flow",
          "generation",
          "consumption"
        ],
        "doc": "Perform component mass balance\n\nAccumulation = In - Out + Generation - Consumption\n\nArgs:\n    inlet_flow: Component inlet flows in kg/s or mol/s\n    outlet_flow: Component outlet flows in kg/s or mol/s\n    generation: Component generation rates (default: 0)\n    consumption: Component consumption rates (default: 0)\n\nReturns:\n    Dictionary with accumulation rates for each component"
      },
      {
        "tool_name": "energy_balance",
        "args": [
          "heat_in",
          "heat_out",
          "work",
          "heat_reaction"
        ],
        "doc": "Perform energy balance\n\nAccumulation = Heat_in - Heat_out - Work + Heat_reaction\n\nArgs:\n    heat_in: Heat input rate in W\n    heat_out: Heat output rate in W\n    work: Work done by system in W\n    heat_reaction: Heat of reaction in W (negative for exothermic)\n\nReturns:\n    Energy accumulation rate in W"
      },
      {
        "tool_name": "mccabe_thiele_stages",
        "args": [
          "x_feed",
          "x_distillate",
          "x_bottoms",
          "reflux_ratio",
          "alpha"
        ],
        "doc": "Calculate number of theoretical stages for binary distillation using McCabe-Thiele\n\nArgs:\n    x_feed: Feed mole fraction of more volatile component\n    x_distillate: Distillate mole fraction\n    x_bottoms: Bottoms mole fraction\n    reflux_ratio: Reflux ratio (L/D)\n    alpha: Relative volatility\n\nReturns:\n    Number of theoretical stages"
      },
      {
        "tool_name": "kremser_equation",
        "args": [
          "y_in",
          "x_in",
          "flow_gas",
          "flow_liquid",
          "henry_constant",
          "n_stages"
        ],
        "doc": "Calculate outlet compositions for gas absorption using Kremser equation\n\nArgs:\n    y_in: Inlet gas mole fraction\n    x_in: Inlet liquid mole fraction\n    flow_gas: Gas flow rate in mol/s\n    flow_liquid: Liquid flow rate in mol/s\n    henry_constant: Henry's law constant (y* = H*x)\n    n_stages: Number of stages\n\nReturns:\n    Tuple of (y_out, x_out) outlet mole fractions"
      },
      {
        "tool_name": "heat_exchanger_lmtd",
        "args": [
          "t_hot_in",
          "t_hot_out",
          "t_cold_in",
          "t_cold_out",
          "flow_type"
        ],
        "doc": "Calculate Log Mean Temperature Difference (LMTD) for heat exchanger\n\nArgs:\n    t_hot_in: Hot fluid inlet temperature in K\n    t_hot_out: Hot fluid outlet temperature in K\n    t_cold_in: Cold fluid inlet temperature in K\n    t_cold_out: Cold fluid outlet temperature in K\n    flow_type: 'counter' or 'parallel' flow\n\nReturns:\n    LMTD in K"
      },
      {
        "tool_name": "heat_exchanger_design",
        "args": [
          "duty",
          "overall_htc",
          "t_hot_in",
          "t_hot_out",
          "t_cold_in",
          "t_cold_out",
          "flow_type"
        ],
        "doc": "Design heat exchanger using LMTD method\n\nArgs:\n    duty: Heat duty in W\n    overall_htc: Overall heat transfer coefficient in W/(m\u00b2\u00b7K)\n    t_hot_in: Hot fluid inlet temperature in K\n    t_hot_out: Hot fluid outlet temperature in K\n    t_cold_in: Cold fluid inlet temperature in K\n    t_cold_out: Cold fluid outlet temperature in K\n    flow_type: 'counter' or 'parallel' flow\n\nReturns:\n    Dictionary with area, LMTD, and NTU"
      },
      {
        "tool_name": "reynolds_number",
        "args": [
          "velocity",
          "diameter",
          "density",
          "viscosity"
        ],
        "doc": "Calculate Reynolds number for pipe flow\n\nRe = \u03c1vD/\u03bc\n\nArgs:\n    velocity: Flow velocity in m/s\n    diameter: Pipe diameter in m\n    density: Fluid density in kg/m\u00b3 (default: self.density)\n    viscosity: Dynamic viscosity in Pa\u00b7s (default: self.viscosity)\n\nReturns:\n    Reynolds number (dimensionless)"
      },
      {
        "tool_name": "pressure_drop_ergun",
        "args": [
          "velocity",
          "particle_diameter",
          "bed_length",
          "void_fraction",
          "density",
          "viscosity"
        ],
        "doc": "Calculate pressure drop through packed bed using Ergun equation\n\nArgs:\n    velocity: Superficial velocity in m/s\n    particle_diameter: Particle diameter in m\n    bed_length: Bed length in m\n    void_fraction: Bed void fraction (0-1)\n    density: Fluid density in kg/m\u00b3\n    viscosity: Dynamic viscosity in Pa\u00b7s\n\nReturns:\n    Pressure drop in Pa"
      },
      {
        "tool_name": "vle_raoults_law",
        "args": [
          "x",
          "vapor_pressure",
          "total_pressure"
        ],
        "doc": "Calculate vapor-liquid equilibrium using Raoult's Law\n\nArgs:\n    x: Liquid mole fractions\n    vapor_pressure: Pure component vapor pressures in Pa\n    total_pressure: Total pressure in Pa (default: self.pressure)\n\nReturns:\n    Tuple of (vapor mole fractions, calculated total pressure)"
      },
      {
        "tool_name": "antoine_equation",
        "args": [
          "temperature",
          "a",
          "b",
          "c"
        ],
        "doc": "Calculate vapor pressure using Antoine equation\n\nlog10(P) = A - B/(C + T)\n\nArgs:\n    temperature: Temperature in K\n    a, b, c: Antoine coefficients\n\nReturns:\n    Vapor pressure in Pa"
      },
      {
        "tool_name": "fugacity_coefficient",
        "args": [
          "pressure",
          "temperature",
          "critical_pressure",
          "critical_temperature",
          "acentric_factor"
        ],
        "doc": "Calculate fugacity coefficient using Peng-Robinson EOS\n\nArgs:\n    pressure: Pressure in Pa\n    temperature: Temperature in K\n    critical_pressure: Critical pressure in Pa\n    critical_temperature: Critical temperature in K\n    acentric_factor: Acentric factor\n\nReturns:\n    Fugacity coefficient (dimensionless)"
      },
      {
        "tool_name": "process_optimization",
        "args": [
          "objective_func",
          "constraints",
          "bounds",
          "initial_guess"
        ],
        "doc": "Optimize process parameters\n\nArgs:\n    objective_func: Objective function to minimize\n    constraints: List of constraint dictionaries\n    bounds: Variable bounds as list of (min, max) tuples\n    initial_guess: Initial guess for variables\n\nReturns:\n    Dictionary with optimal values and objective"
      }
    ]
  },
  {
    "id": "deep_learning_lab.py",
    "name": "Deep Learning",
    "description": "Production-ready deep learning algorithms implemented from scratch.",
    "capabilities": [
      {
        "tool_name": "relu",
        "args": [
          "x"
        ],
        "doc": "ReLU activation function."
      },
      {
        "tool_name": "relu_derivative",
        "args": [
          "x"
        ],
        "doc": "Derivative of ReLU."
      },
      {
        "tool_name": "leaky_relu",
        "args": [
          "x",
          "alpha"
        ],
        "doc": "Leaky ReLU activation function."
      },
      {
        "tool_name": "leaky_relu_derivative",
        "args": [
          "x",
          "alpha"
        ],
        "doc": "Derivative of Leaky ReLU."
      },
      {
        "tool_name": "sigmoid",
        "args": [
          "x"
        ],
        "doc": "Sigmoid activation function."
      },
      {
        "tool_name": "sigmoid_derivative",
        "args": [
          "x"
        ],
        "doc": "Derivative of sigmoid."
      },
      {
        "tool_name": "tanh",
        "args": [
          "x"
        ],
        "doc": "Tanh activation function."
      },
      {
        "tool_name": "tanh_derivative",
        "args": [
          "x"
        ],
        "doc": "Derivative of tanh."
      },
      {
        "tool_name": "gelu",
        "args": [
          "x"
        ],
        "doc": "Gaussian Error Linear Unit (GELU) activation."
      },
      {
        "tool_name": "gelu_derivative",
        "args": [
          "x"
        ],
        "doc": "Derivative of GELU."
      },
      {
        "tool_name": "softmax",
        "args": [
          "x"
        ],
        "doc": "Softmax activation function."
      },
      {
        "tool_name": "get_activation",
        "args": [
          "name"
        ],
        "doc": "Get activation function and its derivative by name."
      },
      {
        "tool_name": "dropout",
        "args": [
          "x",
          "rate",
          "training"
        ],
        "doc": "Apply dropout regularization."
      },
      {
        "tool_name": "batch_normalization",
        "args": [
          "x",
          "layer_idx",
          "training",
          "eps"
        ],
        "doc": "Apply batch normalization."
      },
      {
        "tool_name": "forward_propagation",
        "args": [
          "X",
          "training"
        ],
        "doc": "Perform forward propagation through the network.\n\nArgs:\n    X: Input data\n    training: Whether in training mode\n\nReturns:\n    Output predictions and cache for backpropagation"
      },
      {
        "tool_name": "backpropagation",
        "args": [
          "y_true",
          "cache"
        ],
        "doc": "Perform backpropagation to compute gradients.\n\nArgs:\n    y_true: True labels (one-hot encoded)\n    cache: Cache from forward propagation\n\nReturns:\n    Gradients for weights and biases"
      },
      {
        "tool_name": "clip_gradients",
        "args": [
          "gradients"
        ],
        "doc": "Clip gradients to prevent exploding gradients."
      },
      {
        "tool_name": "sgd_update",
        "args": [
          "grad_weights",
          "grad_biases",
          "lr"
        ],
        "doc": "SGD with momentum optimizer update."
      },
      {
        "tool_name": "adam_update",
        "args": [
          "grad_weights",
          "grad_biases",
          "lr"
        ],
        "doc": "Adam optimizer update."
      },
      {
        "tool_name": "rmsprop_update",
        "args": [
          "grad_weights",
          "grad_biases",
          "lr"
        ],
        "doc": "RMSprop optimizer update."
      },
      {
        "tool_name": "adagrad_update",
        "args": [
          "grad_weights",
          "grad_biases",
          "lr"
        ],
        "doc": "Adagrad optimizer update."
      },
      {
        "tool_name": "update_parameters",
        "args": [
          "grad_weights",
          "grad_biases",
          "lr"
        ],
        "doc": "Update parameters using configured optimizer."
      },
      {
        "tool_name": "get_learning_rate",
        "args": [
          "epoch"
        ],
        "doc": "Get learning rate based on schedule."
      },
      {
        "tool_name": "cross_entropy_loss",
        "args": [
          "y_true",
          "y_pred"
        ],
        "doc": "Calculate cross-entropy loss."
      },
      {
        "tool_name": "mse_loss",
        "args": [
          "y_true",
          "y_pred"
        ],
        "doc": "Calculate mean squared error loss."
      },
      {
        "tool_name": "train",
        "args": [
          "X_train",
          "y_train",
          "X_val",
          "y_val",
          "verbose"
        ],
        "doc": "Train the deep neural network.\n\nArgs:\n    X_train: Training features\n    y_train: Training labels (one-hot encoded)\n    X_val: Validation features\n    y_val: Validation labels\n    verbose: Whether to print progress\n\nReturns:\n    Training history"
      },
      {
        "tool_name": "predict",
        "args": [
          "X"
        ],
        "doc": "Make predictions on input data."
      },
      {
        "tool_name": "evaluate",
        "args": [
          "X",
          "y"
        ],
        "doc": "Evaluate model on test data."
      },
      {
        "tool_name": "get_parameter_count",
        "args": [],
        "doc": "Get total number of trainable parameters."
      }
    ]
  },
  {
    "id": "holographic_data_storage_simulator_lab.py",
    "name": "Holographic Data Storage Simulator",
    "description": "Holographic Data Storage Simulator\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "kruskal_mst_builder_lab.py",
    "name": "Kruskal Mst Builder",
    "description": "Kruskal MST Builder\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "superconductor_band_structure_lab.py",
    "name": "Superconductor Band Structure",
    "description": "Superconductor Band Structure\n\nProduction-ready simulator built by ECH0.",
    "capabilities": [
      {
        "tool_name": "run_simulation",
        "args": [],
        "doc": "Main simulation loop"
      },
      {
        "tool_name": "analyze_results",
        "args": [],
        "doc": "Analyze simulation output"
      }
    ]
  },
  {
    "id": "condensed_matter_physics_lab.py",
    "name": "Condensed Matter Physics",
    "description": "Advanced condensed matter physics simulation laboratory.",
    "capabilities": [
      {
        "tool_name": "create_crystal_structure",
        "args": [
          "structure_type",
          "lattice_constant"
        ],
        "doc": "Create common crystal structures.\n\nArgs:\n    structure_type: Type of structure ('fcc', 'bcc', 'diamond', 'graphene', etc.)\n    lattice_constant: Lattice parameter in Angstroms\n\nReturns:\n    Crystal object"
      },
      {
        "tool_name": "reciprocal_lattice",
        "args": [
          "crystal"
        ],
        "doc": "Calculate reciprocal lattice vectors.\n\nArgs:\n    crystal: Crystal structure\n\nReturns:\n    3x3 matrix of reciprocal lattice vectors"
      },
      {
        "tool_name": "brillouin_zone_path",
        "args": [
          "crystal_type",
          "n_points"
        ],
        "doc": "Generate k-points along high-symmetry path in Brillouin zone.\n\nArgs:\n    crystal_type: Type of crystal ('fcc', 'bcc', etc.)\n    n_points: Number of points along path\n\nReturns:\n    Tuple of (k-points array, symmetry labels)"
      },
      {
        "tool_name": "tight_binding_hamiltonian",
        "args": [
          "k",
          "crystal",
          "t",
          "t_nn"
        ],
        "doc": "Construct tight-binding Hamiltonian for given k-point.\n\nArgs:\n    k: Wave vector\n    crystal: Crystal structure\n    t: Nearest-neighbor hopping parameter (eV)\n    t_nn: Next-nearest-neighbor hopping (eV)\n\nReturns:\n    Hamiltonian matrix"
      },
      {
        "tool_name": "calculate_band_structure",
        "args": [
          "crystal",
          "k_points",
          "hopping_params"
        ],
        "doc": "Calculate electronic band structure.\n\nArgs:\n    crystal: Crystal structure\n    k_points: Array of k-points\n    hopping_params: Dictionary of hopping parameters\n\nReturns:\n    Band energies (n_kpoints x n_bands)"
      },
      {
        "tool_name": "density_of_states",
        "args": [
          "energies",
          "energy_range",
          "n_bins",
          "broadening"
        ],
        "doc": "Calculate density of states from band structure.\n\nArgs:\n    energies: Band energies\n    energy_range: (E_min, E_max) in eV\n    n_bins: Number of energy bins\n    broadening: Gaussian broadening in eV\n\nReturns:\n    Tuple of (energy array, DOS array)"
      },
      {
        "tool_name": "fermi_dirac",
        "args": [
          "E",
          "E_F",
          "T"
        ],
        "doc": "Fermi-Dirac distribution function.\n\nArgs:\n    E: Energy array (eV)\n    E_F: Fermi energy (eV)\n    T: Temperature (K)\n\nReturns:\n    Occupation probability"
      },
      {
        "tool_name": "bcs_gap_equation",
        "args": [
          "T",
          "V",
          "omega_D",
          "DOS_EF"
        ],
        "doc": "Solve BCS gap equation for superconductivity.\n\nArgs:\n    T: Temperature (K)\n    V: Pairing potential (eV)\n    omega_D: Debye frequency (eV)\n    DOS_EF: Density of states at Fermi level (1/eV)\n\nReturns:\n    Superconducting gap (eV)"
      },
      {
        "tool_name": "bcs_coherence_length",
        "args": [
          "Delta",
          "v_F"
        ],
        "doc": "Calculate BCS coherence length.\n\nArgs:\n    Delta: Superconducting gap (eV)\n    v_F: Fermi velocity (m/s)\n\nReturns:\n    Coherence length in meters"
      },
      {
        "tool_name": "phonon_dispersion",
        "args": [
          "k",
          "M",
          "K",
          "K_nn"
        ],
        "doc": "Calculate phonon dispersion relation (1D chain model).\n\nArgs:\n    k: Wave vector array\n    M: Atomic mass (kg)\n    K: Spring constant (N/m)\n    K_nn: Next-nearest neighbor spring constant\n\nReturns:\n    Phonon frequencies (rad/s)"
      },
      {
        "tool_name": "debye_model",
        "args": [
          "T",
          "theta_D"
        ],
        "doc": "Calculate thermodynamic properties using Debye model.\n\nArgs:\n    T: Temperature (K)\n    theta_D: Debye temperature (K)\n\nReturns:\n    Dictionary of thermodynamic properties"
      },
      {
        "tool_name": "drude_conductivity",
        "args": [
          "omega",
          "n",
          "tau",
          "m"
        ],
        "doc": "Calculate Drude optical conductivity.\n\nArgs:\n    omega: Frequency array (rad/s)\n    n: Electron density (m^-3)\n    tau: Scattering time (s)\n    m: Electron mass (kg)\n\nReturns:\n    Complex conductivity"
      },
      {
        "tool_name": "hall_coefficient",
        "args": [
          "carrier_type",
          "n"
        ],
        "doc": "Calculate Hall coefficient.\n\nArgs:\n    carrier_type: 'electron' or 'hole'\n    n: Carrier density (m^-3)\n\nReturns:\n    Hall coefficient (m\u00b3/C)"
      },
      {
        "tool_name": "thermal_conductivity_electrons",
        "args": [
          "sigma",
          "T"
        ],
        "doc": "Calculate electronic thermal conductivity (Wiedemann-Franz law).\n\nArgs:\n    sigma: Electrical conductivity (S/m)\n    T: Temperature (K)\n\nReturns:\n    Thermal conductivity (W/m/K)"
      },
      {
        "tool_name": "bloch_theorem",
        "args": [
          "k",
          "r",
          "u_k"
        ],
        "doc": "Bloch wavefunction.\n\nArgs:\n    k: Wave vector\n    r: Position vector\n    u_k: Periodic function u_k(r)\n\nReturns:\n    Bloch wavefunction value"
      },
      {
        "tool_name": "wannier_function",
        "args": [
          "n",
          "R",
          "band_structure",
          "k_points"
        ],
        "doc": "Calculate Wannier function (simplified).\n\nArgs:\n    n: Band index\n    R: Lattice vector\n    band_structure: Band energies\n    k_points: k-point mesh\n\nReturns:\n    Wannier function values"
      },
      {
        "tool_name": "anderson_localization",
        "args": [
          "L",
          "W",
          "t"
        ],
        "doc": "Anderson localization in 1D disordered system.\n\nArgs:\n    L: System size\n    W: Disorder strength\n    t: Hopping parameter\n\nReturns:\n    Eigenvalues and participation ratios"
      },
      {
        "tool_name": "topological_invariant_1d",
        "args": [
          "H_k",
          "k_points"
        ],
        "doc": "Calculate 1D topological invariant (winding number).\n\nArgs:\n    H_k: Function that returns Hamiltonian for given k\n    k_points: k-points around Brillouin zone\n\nReturns:\n    Winding number"
      },
      {
        "tool_name": "quantum_hall_conductance",
        "args": [
          "B",
          "n"
        ],
        "doc": "Calculate quantum Hall conductance.\n\nArgs:\n    B: Magnetic field (T)\n    n: Landau level filling factor\n\nReturns:\n    Hall conductance (e\u00b2/h units)"
      },
      {
        "tool_name": "magnetic_susceptibility_pauli",
        "args": [
          "DOS_EF"
        ],
        "doc": "Calculate Pauli paramagnetic susceptibility.\n\nArgs:\n    DOS_EF: Density of states at Fermi level (1/eV/m\u00b3)\n\nReturns:\n    Magnetic susceptibility (SI units)"
      }
    ]
  },
  {
    "id": "systems_biology_lab.py",
    "name": "Systems Biology",
    "description": "Integrated biological systems modeling",
    "capabilities": [
      {
        "tool_name": "simulate_gene_regulatory_network",
        "args": [
          "n_genes"
        ],
        "doc": "Simulate gene regulatory network dynamics"
      },
      {
        "tool_name": "analyze_network_motifs",
        "args": [
          "adjacency_matrix"
        ],
        "doc": "Identify network motifs"
      },
      {
        "tool_name": "predict_cell_fate",
        "args": [
          "initial_state"
        ],
        "doc": "Predict cell differentiation fate"
      }
    ]
  },
  {
    "id": "drug_design_lab.py",
    "name": "Drug Design",
    "description": "Comprehensive drug design laboratory for lead discovery and optimization.\nImplements validated models used in pharmaceutical research.",
    "capabilities": [
      {
        "tool_name": "lipinski_rule_of_five",
        "args": [
          "descriptors",
          "strict"
        ],
        "doc": "Evaluate Lipinski's Rule of Five for oral bioavailability.\n\nArgs:\n    descriptors: Molecular descriptors\n    strict: If True, all rules must pass; if False, allow 1 violation\n\nReturns:\n    Tuple of (passes, individual_rules, violations_count)"
      },
      {
        "tool_name": "extended_lipinski",
        "args": [
          "descriptors"
        ],
        "doc": "Extended Lipinski rules for modern drug discovery (including biologics).\n\nArgs:\n    descriptors: Molecular descriptors\n\nReturns:\n    Tuple of (passes, individual_rules)"
      },
      {
        "tool_name": "veber_oral_bioavailability",
        "args": [
          "descriptors"
        ],
        "doc": "Veber rules for oral bioavailability (focus on flexibility and polarity).\n\nArgs:\n    descriptors: Molecular descriptors\n\nReturns:\n    Tuple of (passes, scores)"
      },
      {
        "tool_name": "build_qsar_model",
        "args": [
          "descriptors_matrix",
          "activities",
          "model_type"
        ],
        "doc": "Build a QSAR model from descriptor-activity data.\n\nArgs:\n    descriptors_matrix: Matrix of molecular descriptors (n_compounds x n_descriptors)\n    activities: Biological activities (pIC50, pKi, etc.)\n    model_type: Type of model (\"linear\", \"polynomial\", \"gaussian\")\n\nReturns:\n    Trained QSAR model"
      },
      {
        "tool_name": "predict_activity",
        "args": [
          "descriptors",
          "qsar_model"
        ],
        "doc": "Predict biological activity using QSAR model.\n\nArgs:\n    descriptors: Molecular descriptors for compound\n    qsar_model: Trained QSAR model\n\nReturns:\n    Tuple of (predicted_activity, within_applicability_domain)"
      },
      {
        "tool_name": "calculate_logp",
        "args": [
          "fragment_contributions"
        ],
        "doc": "Calculate LogP using fragment-based method (simplified Ghose-Crippen).\n\nArgs:\n    fragment_contributions: Dictionary of fragment types and counts\n\nReturns:\n    Estimated LogP"
      },
      {
        "tool_name": "calculate_psa",
        "args": [
          "functional_groups"
        ],
        "doc": "Calculate topological polar surface area (TPSA).\n\nArgs:\n    functional_groups: Dictionary of functional groups and counts\n\nReturns:\n    TPSA in \u0173"
      },
      {
        "tool_name": "estimate_solubility",
        "args": [
          "descriptors"
        ],
        "doc": "Estimate aqueous solubility using General Solubility Equation (GSE).\n\nLogS = 0.5 - 0.01*MW - LogP\n\nArgs:\n    descriptors: Molecular descriptors\n\nReturns:\n    LogS (log10 of solubility in mol/L)"
      },
      {
        "tool_name": "calculate_drug_efficiency_metrics",
        "args": [
          "descriptors",
          "activity"
        ],
        "doc": "Calculate drug efficiency metrics (ligand efficiency, lipophilic efficiency, etc.).\n\nArgs:\n    descriptors: Molecular descriptors\n    activity: Biological activity (pIC50 or pKi)\n\nReturns:\n    Dictionary of efficiency metrics"
      },
      {
        "tool_name": "estimate_docking_score",
        "args": [
          "descriptors",
          "protein_features"
        ],
        "doc": "Estimate virtual docking score using empirical scoring function.\n\nArgs:\n    descriptors: Molecular descriptors\n    protein_features: Protein binding site features\n\nReturns:\n    Dictionary with docking scores and components"
      },
      {
        "tool_name": "predict_admet",
        "args": [
          "descriptors"
        ],
        "doc": "Predict ADMET properties using empirical models.\n\nArgs:\n    descriptors: Molecular descriptors\n\nReturns:\n    Complete ADMET profile"
      },
      {
        "tool_name": "lead_optimization_score",
        "args": [
          "descriptors",
          "activity",
          "admet",
          "target_profile"
        ],
        "doc": "Calculate comprehensive lead optimization score.\n\nArgs:\n    descriptors: Molecular descriptors\n    activity: Biological activity (pIC50)\n    admet: ADMET profile\n    target_profile: Target product profile (optional)\n\nReturns:\n    Dictionary with optimization scores"
      },
      {
        "tool_name": "suggest_optimizations",
        "args": [
          "descriptors",
          "activity",
          "admet"
        ],
        "doc": "Suggest specific optimizations to improve drug properties.\n\nArgs:\n    descriptors: Molecular descriptors\n    activity: Current biological activity\n    admet: ADMET profile\n\nReturns:\n    List of optimization suggestions"
      },
      {
        "tool_name": "fragment_growing",
        "args": [
          "core_descriptors",
          "available_fragments"
        ],
        "doc": "Suggest fragment additions for lead optimization.\n\nArgs:\n    core_descriptors: Core molecule descriptors\n    available_fragments: List of fragment descriptors\n\nReturns:\n    Ranked list of suggested fragment additions"
      }
    ]
  },
  {
    "id": "polymer_chemistry_lab.py",
    "name": "Polymer Chemistry",
    "description": "Advanced polymer chemistry laboratory for comprehensive polymer simulations.",
    "capabilities": [
      {
        "tool_name": "chain_growth_polymerization",
        "args": [
          "monomer",
          "conditions",
          "kp",
          "kt",
          "ki"
        ],
        "doc": "Model free radical chain growth polymerization.\n\nIncludes initiation, propagation, and termination steps."
      },
      {
        "tool_name": "step_growth_polymerization",
        "args": [
          "monomers",
          "conditions",
          "k"
        ],
        "doc": "Model step-growth (condensation) polymerization.\n\nAA + BB \u2192 AA-BB + byproduct"
      },
      {
        "tool_name": "living_polymerization",
        "args": [
          "monomer",
          "conditions",
          "kp"
        ],
        "doc": "Model living/controlled polymerization (e.g., anionic, RAFT, ATRP).\n\nNo termination, narrow molecular weight distribution."
      },
      {
        "tool_name": "schulz_zimm_distribution",
        "args": [
          "MW_avg",
          "PDI",
          "MW_range"
        ],
        "doc": "Calculate Schulz-Zimm molecular weight distribution.\n\nCommon for radical and condensation polymerizations."
      },
      {
        "tool_name": "poisson_distribution",
        "args": [
          "DP_avg",
          "DP_range"
        ],
        "doc": "Calculate Poisson distribution for living polymerization.\n\nVery narrow distribution."
      },
      {
        "tool_name": "log_normal_distribution",
        "args": [
          "MW_avg",
          "sigma",
          "MW_range"
        ],
        "doc": "Calculate log-normal molecular weight distribution.\n\nCommon for some polymerization systems."
      },
      {
        "tool_name": "fox_equation",
        "args": [
          "components"
        ],
        "doc": "Calculate Tg of polymer blend/copolymer using Fox equation.\n\n1/Tg = \u03a3(wi/Tgi)"
      },
      {
        "tool_name": "gordon_taylor_equation",
        "args": [
          "Tg1",
          "Tg2",
          "w1",
          "k"
        ],
        "doc": "Calculate Tg using Gordon-Taylor equation.\n\nTg = (w1*Tg1 + k*w2*Tg2) / (w1 + k*w2)"
      },
      {
        "tool_name": "free_volume_theory_tg",
        "args": [
          "molecular_weight",
          "K"
        ],
        "doc": "Estimate Tg from molecular weight using free volume theory.\n\nTg = Tg\u221e - K/Mn (Flory-Fox equation)"
      },
      {
        "tool_name": "young_modulus",
        "args": [
          "polymer",
          "temperature"
        ],
        "doc": "Estimate Young's modulus based on polymer properties."
      },
      {
        "tool_name": "tensile_strength",
        "args": [
          "polymer",
          "strain_rate"
        ],
        "doc": "Estimate tensile strength.\n\nDepends on MW, crystallinity, and strain rate."
      },
      {
        "tool_name": "rubber_elasticity",
        "args": [
          "crosslink_density",
          "temperature"
        ],
        "doc": "Calculate shear modulus for rubber using statistical mechanics.\n\nG = \u03c1RT/Mc where Mc is molecular weight between crosslinks"
      },
      {
        "tool_name": "stress_relaxation",
        "args": [
          "initial_stress",
          "time",
          "relaxation_times",
          "weights"
        ],
        "doc": "Model stress relaxation using Maxwell model.\n\n\u03c3(t) = \u03c30 * \u03a3 wi * exp(-t/\u03c4i)"
      },
      {
        "tool_name": "flory_huggins_free_energy",
        "args": [
          "phi",
          "chi",
          "N"
        ],
        "doc": "Calculate Flory-Huggins free energy of mixing.\n\n\u0394Gmix/RT = \u03c6*ln(\u03c6) + (1-\u03c6)*ln(1-\u03c6)/N + \u03c7*\u03c6*(1-\u03c6)"
      },
      {
        "tool_name": "solubility_parameter",
        "args": [
          "cohesive_energy",
          "molar_volume"
        ],
        "doc": "Calculate Hildebrand solubility parameter.\n\n\u03b4 = (E_coh/V_m)^0.5"
      },
      {
        "tool_name": "mark_houwink_viscosity",
        "args": [
          "molecular_weight",
          "K",
          "a"
        ],
        "doc": "Calculate intrinsic viscosity using Mark-Houwink equation.\n\n[\u03b7] = K*M^a"
      },
      {
        "tool_name": "theta_temperature",
        "args": [
          "enthalpy",
          "entropy"
        ],
        "doc": "Calculate theta temperature (Flory temperature).\n\nAt \u03b8: Second virial coefficient = 0"
      },
      {
        "tool_name": "avrami_crystallization",
        "args": [
          "time",
          "k",
          "n"
        ],
        "doc": "Model crystallization kinetics using Avrami equation.\n\nX(t) = 1 - exp(-k*t^n)"
      },
      {
        "tool_name": "hoffman_weeks_melting",
        "args": [
          "crystallization_temp",
          "equilibrium_melting"
        ],
        "doc": "Calculate melting temperature using Hoffman-Weeks equation.\n\nTm = Tc/2 + Tm\u00b0/2"
      },
      {
        "tool_name": "lauritzen_hoffman_growth",
        "args": [
          "temperature",
          "Tg",
          "Tm",
          "U",
          "K_g"
        ],
        "doc": "Calculate crystal growth rate using Lauritzen-Hoffman theory."
      },
      {
        "tool_name": "copolymer_composition",
        "args": [
          "f1",
          "r1",
          "r2"
        ],
        "doc": "Calculate instantaneous copolymer composition.\n\nMayo-Lewis equation: F1 = (r1*f1\u00b2 + f1*f2) / (r1*f1\u00b2 + 2*f1*f2 + r2*f2\u00b2)"
      },
      {
        "tool_name": "sequence_distribution",
        "args": [
          "F1",
          "r1",
          "r2"
        ],
        "doc": "Calculate sequence length distributions in copolymer."
      },
      {
        "tool_name": "thermal_degradation",
        "args": [
          "time",
          "activation_energy",
          "temperature"
        ],
        "doc": "Model thermal degradation kinetics.\n\nFirst-order random chain scission."
      },
      {
        "tool_name": "photo_oxidation",
        "args": [
          "time",
          "uv_intensity",
          "oxygen_concentration"
        ],
        "doc": "Model photo-oxidative degradation."
      },
      {
        "tool_name": "hydrolytic_degradation",
        "args": [
          "time",
          "pH",
          "temperature"
        ],
        "doc": "Model hydrolytic degradation (e.g., polyesters)."
      },
      {
        "tool_name": "estimate_tg",
        "args": [
          "polymer"
        ],
        "doc": "Estimate glass transition temperature."
      },
      {
        "tool_name": "run_comprehensive_demo",
        "args": [],
        "doc": "Run comprehensive demonstration of polymer chemistry capabilities."
      }
    ]
  },
  {
    "id": "research_publication_lab.py",
    "name": "Research Publication",
    "description": "Research Publication Laboratory - Automated paper discovery and whitepaper publishing.\n\nFeatures:\n1. Scrape papers from Hugging Face/Papers with Code\n2. Analyze paper relevance to scientific domains\n3. Generate whitepaper drafts for QuLab Infinite research\n4. Publish whitepapers to various platforms\n5. Track publication metrics and citations",
    "capabilities": [
      {
        "tool_name": "scrape_huggingface_papers",
        "args": [
          "query",
          "limit",
          "categories"
        ],
        "doc": "Scrape research papers from Hugging Face/Papers with Code\n\nArgs:\n    query: Search query (e.g., \"quantum chemistry\", \"machine learning\")\n    limit: Maximum number of papers to return\n    categories: Filter by categories (e.g., [\"cs.AI\", \"physics.chem-ph\"])\n\nReturns:\n    List of PaperMetadata objects"
      },
      {
        "tool_name": "analyze_paper_relevance",
        "args": [
          "paper",
          "domains"
        ],
        "doc": "Analyze how relevant a paper is to specific scientific domains\n\nArgs:\n    paper: PaperMetadata object\n    domains: List of domains to check (e.g., [\"quantum\", \"chemistry\", \"materials\"])\n\nReturns:\n    Relevance analysis with scores"
      },
      {
        "tool_name": "generate_whitepaper_draft",
        "args": [
          "topic",
          "related_papers",
          "qu_lab_focus"
        ],
        "doc": "Generate a whitepaper draft based on research topic and related papers\n\nArgs:\n    topic: Research topic (e.g., \"Quantum Chemistry Simulation\")\n    related_papers: List of relevant papers\n    qu_lab_focus: Specific QuLab focus area\n\nReturns:\n    WhitepaperDraft object"
      },
      {
        "tool_name": "publish_whitepaper",
        "args": [
          "draft",
          "platform"
        ],
        "doc": "Publish a whitepaper to a specified platform\n\nArgs:\n    draft: WhitepaperDraft to publish\n    platform: Target platform (\"github_pages\", \"medium\", \"arxiv\")\n\nReturns:\n    Publication result with URL and status"
      },
      {
        "tool_name": "research_topic_analysis",
        "args": [
          "topic",
          "depth"
        ],
        "doc": "Perform comprehensive research analysis on a topic\n\nArgs:\n    topic: Research topic to analyze\n    depth: Analysis depth (\"basic\", \"comprehensive\", \"expert\")\n\nReturns:\n    Complete research analysis"
      }
    ]
  },
  {
    "id": "biophysics_lab.py",
    "name": "Biophysics",
    "description": "Biological physics simulations",
    "capabilities": [
      {
        "tool_name": "simulate_protein_folding_energy",
        "args": [
          "sequence"
        ],
        "doc": "Calculate protein folding free energy"
      },
      {
        "tool_name": "calculate_membrane_permeability",
        "args": [
          "molecule_weight",
          "logP"
        ],
        "doc": "Calculate membrane permeability coefficient"
      },
      {
        "tool_name": "simulate_ion_channel_current",
        "args": [
          "voltage_mv",
          "conductance_ns"
        ],
        "doc": "Calculate ion channel current using Hodgkin-Huxley model"
      }
    ]
  },
  {
    "id": "epigenetics_lab.py",
    "name": "Epigenetics",
    "description": "Epigenetic modifications and inheritance",
    "capabilities": [
      {
        "tool_name": "analyze_methylation_pattern",
        "args": [
          "sequence"
        ],
        "doc": "Analyze CpG methylation patterns"
      },
      {
        "tool_name": "predict_chromatin_state",
        "args": [
          "histone_marks"
        ],
        "doc": "Predict chromatin state from histone modifications"
      },
      {
        "tool_name": "simulate_inheritance",
        "args": [
          "parent_methylation",
          "generations"
        ],
        "doc": "Simulate epigenetic inheritance"
      }
    ]
  },
  {
    "id": "generative_design_lab.py",
    "name": "Generative Design",
    "description": "",
    "capabilities": [
      {
        "tool_name": "find_optimal_material",
        "args": [
          "target_property",
          "constraints"
        ],
        "doc": "Simulates an inverse design process where the user asks for a property \n(e.g. \"Maximize Tensile Strength\") and the AI returns the best structure."
      },
      {
        "tool_name": "run_demo",
        "args": [],
        "doc": "No description available."
      }
    ]
  },
  {
    "id": "toxicology_lab.py",
    "name": "Toxicology",
    "description": "Advanced toxicology assessment laboratory",
    "capabilities": [
      {
        "tool_name": "probit_analysis",
        "args": [
          "doses",
          "responses",
          "n_animals"
        ],
        "doc": "Probit analysis for LD50/LC50 calculation\n\nReference: Finney, D.J. (1971) Probit Analysis, 3rd ed. Cambridge University Press."
      },
      {
        "tool_name": "logit_analysis",
        "args": [
          "doses",
          "responses"
        ],
        "doc": "Logistic regression for dose-response analysis\n\nReference: Berkson, J. (1944) JASA 39(227):357-365"
      },
      {
        "tool_name": "hill_equation",
        "args": [
          "concentration",
          "ic50",
          "hill_coefficient",
          "top",
          "bottom"
        ],
        "doc": "Hill equation for dose-response modeling\n\nReference: Hill, A.V. (1910) Journal of Physiology 40:190-224"
      },
      {
        "tool_name": "benchmark_dose",
        "args": [
          "doses",
          "responses",
          "bmr"
        ],
        "doc": "Benchmark Dose (BMD) calculation using exponential model\n\nReference: Crump, K.S. (1984) Fundamental and Applied Toxicology 4(5):854-871"
      },
      {
        "tool_name": "pbpk_model",
        "args": [
          "time",
          "dose",
          "route",
          "params"
        ],
        "doc": "Physiologically-Based Pharmacokinetic (PBPK) modeling\n\nReference: Reddy, M. et al. (2005) Physiologically Based Pharmacokinetic Modeling. Wiley."
      },
      {
        "tool_name": "predict_admet",
        "args": [],
        "doc": "Predict ADMET properties using QSAR models\n\nReference: Lipinski, C.A. et al. (2001) Advanced Drug Delivery Reviews 46(1-3):3-26"
      },
      {
        "tool_name": "organ_toxicity_index",
        "args": [
          "dose",
          "duration_days",
          "organ"
        ],
        "doc": "Calculate organ-specific toxicity index\n\nReference: Krewski, D. et al. (2010) Journal of Toxicology and Environmental Health B 13(2-4):51-138"
      },
      {
        "tool_name": "calculate_noael",
        "args": [
          "doses",
          "responses",
          "control_response",
          "alpha"
        ],
        "doc": "Calculate NOAEL (No Observed Adverse Effect Level) and LOAEL\n\nReference: OECD (2008) Guidelines for the Testing of Chemicals"
      },
      {
        "tool_name": "therapeutic_index",
        "args": [
          "ld50",
          "ed50"
        ],
        "doc": "Calculate therapeutic index (safety margin)\n\nReference: Muller, P.Y. & Milton, M.N. (2012) Nature Reviews Drug Discovery 11(10):751-761"
      },
      {
        "tool_name": "allometric_scaling",
        "args": [
          "dose_animal",
          "weight_animal",
          "species_from",
          "species_to"
        ],
        "doc": "Interspecies dose scaling using allometry\n\nReference: Reagan-Shaw, S. et al. (2008) FASEB Journal 22(3):659-661"
      },
      {
        "tool_name": "margin_of_safety",
        "args": [
          "noael",
          "human_dose",
          "safety_factors"
        ],
        "doc": "Calculate margin of safety with uncertainty factors\n\nReference: Dourson, M.L. & Stara, J.F. (1983) Regulatory Toxicology and Pharmacology 3(3):224-238"
      },
      {
        "tool_name": "genotoxicity_battery",
        "args": [],
        "doc": "Predict standard genotoxicity test battery results\n\nReference: ICH S2(R1) Guidance on Genotoxicity Testing"
      }
    ]
  },
  {
    "id": "pharmacology_lab.py",
    "name": "Pharmacology",
    "description": "Comprehensive pharmacology laboratory for PK/PD modeling and analysis.\nImplements validated models used in clinical pharmacology research.",
    "capabilities": [
      {
        "tool_name": "one_compartment_model",
        "args": [
          "dose",
          "params",
          "time",
          "iv"
        ],
        "doc": "One-compartment PK model with first-order elimination.\n\nArgs:\n    dose: Drug dose in mg\n    params: PK parameters\n    time: Time points in hours\n    iv: If True, IV bolus; if False, oral with absorption\n\nReturns:\n    Plasma concentrations at each time point (mg/L)"
      },
      {
        "tool_name": "two_compartment_model",
        "args": [
          "dose",
          "k10",
          "k12",
          "k21",
          "v1",
          "time"
        ],
        "doc": "Two-compartment PK model (central and peripheral compartments).\n\nArgs:\n    dose: Drug dose in mg\n    k10: Elimination rate from central compartment (1/h)\n    k12: Transfer rate central\u2192peripheral (1/h)\n    k21: Transfer rate peripheral\u2192central (1/h)\n    v1: Central compartment volume (L)\n    time: Time points in hours\n\nReturns:\n    Tuple of (central concentrations, peripheral concentrations) in mg/L"
      },
      {
        "tool_name": "three_compartment_model",
        "args": [
          "dose",
          "params_dict",
          "time"
        ],
        "doc": "Three-compartment PK model (central + two peripheral compartments).\n\nArgs:\n    dose: Drug dose in mg\n    params_dict: Dictionary with rate constants (k10, k12, k21, k13, k31) and v1\n    time: Time points in hours\n\nReturns:\n    Tuple of (central, peripheral1, peripheral2) concentrations in mg/L"
      },
      {
        "tool_name": "emax_model",
        "args": [
          "concentration",
          "params"
        ],
        "doc": "Emax pharmacodynamic model: E = E0 + Emax * C / (EC50 + C)\n\nArgs:\n    concentration: Drug concentration(s)\n    params: PD parameters\n\nReturns:\n    Pharmacological effect"
      },
      {
        "tool_name": "sigmoid_emax_model",
        "args": [
          "concentration",
          "params"
        ],
        "doc": "Sigmoid Emax model (Hill equation): E = E0 + Emax * C^n / (EC50^n + C^n)\n\nArgs:\n    concentration: Drug concentration(s)\n    params: PD parameters including hill_coefficient\n\nReturns:\n    Pharmacological effect"
      },
      {
        "tool_name": "indirect_response_model",
        "args": [
          "concentration",
          "time",
          "params",
          "inhibition"
        ],
        "doc": "Indirect response model for delayed drug effects.\n\nArgs:\n    concentration: Drug concentrations over time\n    time: Time points\n    params: PD parameters\n    inhibition: If True, drug inhibits; if False, drug stimulates\n\nReturns:\n    Response over time"
      },
      {
        "tool_name": "calculate_bioavailability",
        "args": [
          "auc_oral",
          "auc_iv",
          "dose_oral",
          "dose_iv"
        ],
        "doc": "Calculate absolute bioavailability from AUC data.\n\nF = (AUC_oral / Dose_oral) / (AUC_iv / Dose_iv)\n\nArgs:\n    auc_oral: Area under curve for oral administration\n    auc_iv: Area under curve for IV administration\n    dose_oral: Oral dose\n    dose_iv: IV dose\n\nReturns:\n    Bioavailability fraction (0-1)"
      },
      {
        "tool_name": "calculate_clearance",
        "args": [
          "dose",
          "auc"
        ],
        "doc": "Calculate total body clearance.\n\nCL = Dose / AUC\n\nArgs:\n    dose: Drug dose (mg)\n    auc: Area under concentration-time curve (mg*h/L)\n\nReturns:\n    Clearance in L/h"
      },
      {
        "tool_name": "renal_clearance",
        "args": [
          "fu",
          "gfr",
          "secretion_rate",
          "reabsorption_fraction"
        ],
        "doc": "Calculate renal clearance considering filtration, secretion, and reabsorption.\n\nCLr = fu * GFR + Secretion - Reabsorption\n\nArgs:\n    fu: Fraction unbound in plasma (0-1)\n    gfr: Glomerular filtration rate (mL/min)\n    secretion_rate: Active secretion rate (mL/min)\n    reabsorption_fraction: Fraction reabsorbed (0-1)\n\nReturns:\n    Renal clearance in L/h"
      },
      {
        "tool_name": "hepatic_clearance",
        "args": [
          "fu",
          "intrinsic_clearance",
          "hepatic_blood_flow"
        ],
        "doc": "Calculate hepatic clearance using well-stirred model.\n\nCLh = Q * fu * CLint / (Q + fu * CLint)\n\nArgs:\n    fu: Fraction unbound in plasma\n    intrinsic_clearance: Intrinsic clearance (L/h)\n    hepatic_blood_flow: Hepatic blood flow (L/h), uses default if None\n\nReturns:\n    Hepatic clearance in L/h"
      },
      {
        "tool_name": "population_pk_parameters",
        "args": [
          "n_subjects",
          "typical_cl",
          "typical_vd",
          "omega_cl",
          "omega_vd",
          "seed"
        ],
        "doc": "Generate population PK parameters with inter-individual variability.\nUses log-normal distribution for PK parameters.\n\nArgs:\n    n_subjects: Number of subjects\n    typical_cl: Population typical clearance (L/h)\n    typical_vd: Population typical volume (L)\n    omega_cl: CV for clearance (coefficient of variation)\n    omega_vd: CV for volume of distribution\n    seed: Random seed for reproducibility\n\nReturns:\n    List of PKParameters for each subject"
      },
      {
        "tool_name": "mixed_effects_model",
        "args": [
          "concentrations",
          "covariates",
          "fixed_effects"
        ],
        "doc": "Simple mixed-effects model for population PK analysis.\n\nArgs:\n    concentrations: Observed concentrations\n    covariates: Dictionary of covariates (e.g., weight, age, creatinine)\n    fixed_effects: Initial estimates of fixed effects\n\nReturns:\n    Predicted concentrations and estimated parameters"
      },
      {
        "tool_name": "therapeutic_window_analysis",
        "args": [
          "concentrations",
          "min_effective",
          "max_toxic",
          "time"
        ],
        "doc": "Analyze drug concentrations relative to therapeutic window.\n\nArgs:\n    concentrations: Drug concentrations\n    min_effective: Minimum effective concentration\n    max_toxic: Maximum toxic concentration\n    time: Time points (optional)\n\nReturns:\n    Dictionary with therapeutic metrics"
      },
      {
        "tool_name": "calculate_half_life",
        "args": [
          "concentrations",
          "time",
          "terminal_points"
        ],
        "doc": "Calculate elimination half-life from terminal phase.\n\nArgs:\n    concentrations: Drug concentrations\n    time: Time points\n    terminal_points: Number of points to use for terminal phase\n\nReturns:\n    Tuple of (half_life, r_squared of fit)"
      },
      {
        "tool_name": "volume_of_distribution",
        "args": [
          "dose",
          "concentration_0",
          "body_weight"
        ],
        "doc": "Calculate different volumes of distribution.\n\nArgs:\n    dose: Drug dose (mg)\n    concentration_0: Initial concentration (mg/L)\n    body_weight: Body weight in kg\n\nReturns:\n    Dictionary with different Vd calculations"
      },
      {
        "tool_name": "validate_parameters",
        "args": [
          "params"
        ],
        "doc": "Validate pharmacological parameters are within reasonable ranges.\n\nArgs:\n    params: PK or PD parameters to validate\n\nReturns:\n    True if valid, raises ValueError if not"
      }
    ]
  },
  {
    "id": "immunology_lab.py",
    "name": "Immunology",
    "description": "Production-ready immunology simulation laboratory.",
    "capabilities": [
      {
        "tool_name": "generate_antibody_repertoire",
        "args": [
          "diversity"
        ],
        "doc": "Generate diverse antibody repertoire through V(D)J recombination."
      },
      {
        "tool_name": "antibody_antigen_affinity",
        "args": [
          "antibody",
          "antigen"
        ],
        "doc": "Calculate binding affinity between antibody and antigen."
      },
      {
        "tool_name": "somatic_hypermutation",
        "args": [
          "antibody",
          "mutation_rate"
        ],
        "doc": "Simulate somatic hypermutation in B cells."
      },
      {
        "tool_name": "affinity_maturation",
        "args": [
          "initial_antibody",
          "antigen",
          "generations",
          "population_size"
        ],
        "doc": "Simulate affinity maturation in germinal centers."
      },
      {
        "tool_name": "t_cell_activation",
        "args": [
          "signal1_strength",
          "signal2_strength",
          "signal3_cytokines"
        ],
        "doc": "Model T cell activation with three-signal model."
      },
      {
        "tool_name": "simulate_infection_response",
        "args": [
          "pathogen_load",
          "duration_days"
        ],
        "doc": "Simulate complete immune response to infection."
      },
      {
        "tool_name": "simulate_vaccination",
        "args": [
          "vaccine_type",
          "doses",
          "duration_days"
        ],
        "doc": "Simulate immune response to vaccination."
      },
      {
        "tool_name": "model_cytokine_network",
        "args": [
          "initial_stimulus",
          "time_steps"
        ],
        "doc": "Model cytokine signaling network dynamics."
      },
      {
        "tool_name": "calculate_neutralizing_antibody_titer",
        "args": [
          "antibodies",
          "virus"
        ],
        "doc": "Calculate neutralizing antibody titer against virus."
      },
      {
        "tool_name": "mhc_peptide_binding",
        "args": [
          "peptide",
          "mhc_allele"
        ],
        "doc": "Predict MHC-peptide binding affinity."
      },
      {
        "tool_name": "tcr_repertoire_diversity",
        "args": [
          "repertoire_size"
        ],
        "doc": "Analyze T cell receptor repertoire diversity."
      },
      {
        "tool_name": "simulate_autoimmune_response",
        "args": [
          "self_antigen",
          "tolerance_threshold"
        ],
        "doc": "Simulate breakdown of immunological tolerance."
      },
      {
        "tool_name": "model_immunosenescence",
        "args": [
          "age_years"
        ],
        "doc": "Model age-related changes in immune function."
      },
      {
        "tool_name": "simulate_immunotherapy",
        "args": [
          "therapy_type",
          "tumor_burden",
          "duration_weeks"
        ],
        "doc": "Simulate cancer immunotherapy response."
      },
      {
        "tool_name": "run_comprehensive_analysis",
        "args": [],
        "doc": "Run complete immunology analysis pipeline."
      }
    ]
  },
  {
    "id": "mechanical_engineering_lab.py",
    "name": "Mechanical Engineering",
    "description": "Comprehensive mechanical engineering calculations including:\n- Stress and strain analysis\n- Fatigue life prediction\n- Vibration analysis\n- Heat transfer calculations\n- Fluid mechanics\n- Finite Element Analysis basics",
    "capabilities": [
      {
        "tool_name": "calculate_stress",
        "args": [
          "force",
          "area"
        ],
        "doc": "Calculate normal stress using \u03c3 = F/A\n\nArgs:\n    force: Applied force in Newtons\n    area: Cross-sectional area in m^2\n\nReturns:\n    Stress in Pa"
      },
      {
        "tool_name": "calculate_strain",
        "args": [
          "stress"
        ],
        "doc": "Calculate strain using Hooke's Law: \u03b5 = \u03c3/E\n\nArgs:\n    stress: Applied stress in Pa\n\nReturns:\n    Strain (dimensionless)"
      },
      {
        "tool_name": "von_mises_stress",
        "args": [
          "sigma_x",
          "sigma_y",
          "sigma_z",
          "tau_xy",
          "tau_yz",
          "tau_xz"
        ],
        "doc": "Calculate von Mises equivalent stress for 3D stress state\n\n\u03c3_vm = sqrt(0.5 * [(\u03c3_x - \u03c3_y)\u00b2 + (\u03c3_y - \u03c3_z)\u00b2 + (\u03c3_z - \u03c3_x)\u00b2 + 6(\u03c4_xy\u00b2 + \u03c4_yz\u00b2 + \u03c4_xz\u00b2)])\n\nArgs:\n    sigma_x, sigma_y, sigma_z: Normal stresses in Pa\n    tau_xy, tau_yz, tau_xz: Shear stresses in Pa\n\nReturns:\n    Von Mises equivalent stress in Pa"
      },
      {
        "tool_name": "principal_stresses",
        "args": [
          "sigma_x",
          "sigma_y",
          "tau_xy"
        ],
        "doc": "Calculate principal stresses and angle for 2D stress state\n\nArgs:\n    sigma_x, sigma_y: Normal stresses in Pa\n    tau_xy: Shear stress in Pa\n\nReturns:\n    Tuple of (\u03c3_1, \u03c3_2, \u03b8_p) where \u03b8_p is principal angle in radians"
      },
      {
        "tool_name": "fatigue_life_basquin",
        "args": [
          "stress_amplitude",
          "fatigue_strength_coeff",
          "fatigue_strength_exp"
        ],
        "doc": "Calculate fatigue life using Basquin's equation: \u03c3_a = \u03c3_f' * (2N_f)^b\n\nArgs:\n    stress_amplitude: Stress amplitude in Pa\n    fatigue_strength_coeff: Fatigue strength coefficient (default: 0.9 * ultimate_strength)\n    fatigue_strength_exp: Fatigue strength exponent (typically -0.05 to -0.12)\n\nReturns:\n    Number of cycles to failure"
      },
      {
        "tool_name": "goodman_diagram",
        "args": [
          "mean_stress",
          "alternating_stress",
          "endurance_limit"
        ],
        "doc": "Calculate safety factor using Goodman criterion for fatigue under mean stress\n\nGoodman equation: \u03c3_a/S_e + \u03c3_m/S_ut = 1/n\n\nArgs:\n    mean_stress: Mean stress in Pa\n    alternating_stress: Alternating stress in Pa\n    endurance_limit: Material endurance limit (default: 0.5 * ultimate_strength)\n\nReturns:\n    Safety factor"
      },
      {
        "tool_name": "natural_frequency_beam",
        "args": [
          "length",
          "width",
          "height",
          "boundary"
        ],
        "doc": "Calculate natural frequency of a rectangular beam\n\nArgs:\n    length: Beam length in meters\n    width: Beam width in meters\n    height: Beam height in meters\n    boundary: Boundary condition ('simply_supported', 'cantilever', 'fixed')\n\nReturns:\n    Natural frequency in Hz"
      },
      {
        "tool_name": "damped_vibration",
        "args": [
          "mass",
          "stiffness",
          "damping",
          "time",
          "initial_disp",
          "initial_vel"
        ],
        "doc": "Calculate response of damped single degree of freedom system\n\nArgs:\n    mass: Mass in kg\n    stiffness: Spring stiffness in N/m\n    damping: Damping coefficient in N\u00b7s/m\n    time: Time array in seconds\n    initial_disp: Initial displacement in meters\n    initial_vel: Initial velocity in m/s\n\nReturns:\n    Displacement array in meters"
      },
      {
        "tool_name": "heat_conduction_1d",
        "args": [
          "length",
          "temp_hot",
          "temp_cold",
          "area",
          "thermal_resistance"
        ],
        "doc": "Calculate 1D steady-state heat conduction using Fourier's law\n\nArgs:\n    length: Material thickness in meters\n    temp_hot: Hot side temperature in K\n    temp_cold: Cold side temperature in K\n    area: Cross-sectional area in m^2\n    thermal_resistance: Additional thermal resistance in K/W\n\nReturns:\n    Dictionary with heat flux, heat rate, and thermal resistance"
      },
      {
        "tool_name": "convection_heat_transfer",
        "args": [
          "surface_temp",
          "fluid_temp",
          "area",
          "heat_transfer_coeff"
        ],
        "doc": "Calculate convective heat transfer using Newton's law of cooling\n\nArgs:\n    surface_temp: Surface temperature in K\n    fluid_temp: Fluid temperature in K\n    area: Surface area in m^2\n    heat_transfer_coeff: Convection coefficient in W/(m^2\u00b7K)\n\nReturns:\n    Dictionary with heat rate and heat flux"
      },
      {
        "tool_name": "reynolds_number",
        "args": [
          "velocity",
          "characteristic_length",
          "viscosity"
        ],
        "doc": "Calculate Reynolds number for fluid flow\n\nRe = \u03c1VL/\u03bc\n\nArgs:\n    velocity: Flow velocity in m/s\n    characteristic_length: Characteristic length in meters\n    viscosity: Dynamic viscosity in Pa\u00b7s (default: air at 20\u00b0C)\n\nReturns:\n    Reynolds number (dimensionless)"
      },
      {
        "tool_name": "pressure_drop_pipe",
        "args": [
          "flow_rate",
          "pipe_diameter",
          "pipe_length",
          "roughness",
          "viscosity"
        ],
        "doc": "Calculate pressure drop in pipe using Darcy-Weisbach equation\n\nArgs:\n    flow_rate: Volumetric flow rate in m^3/s\n    pipe_diameter: Pipe internal diameter in meters\n    pipe_length: Pipe length in meters\n    roughness: Pipe roughness in meters (default: commercial steel)\n    viscosity: Fluid dynamic viscosity in Pa\u00b7s (default: water)\n\nReturns:\n    Dictionary with pressure drop, velocity, Reynolds number, and friction factor"
      },
      {
        "tool_name": "finite_element_stiffness_matrix",
        "args": [
          "length",
          "area"
        ],
        "doc": "Generate stiffness matrix for 1D bar element (basic FEA)\n\nArgs:\n    length: Element length in meters\n    area: Cross-sectional area in m^2\n\nReturns:\n    2x2 stiffness matrix in N/m"
      },
      {
        "tool_name": "beam_deflection",
        "args": [
          "length",
          "load",
          "width",
          "height",
          "load_type"
        ],
        "doc": "Calculate maximum deflection of a beam under various loading conditions\n\nArgs:\n    length: Beam length in meters\n    load: Applied load in N (point) or N/m (distributed)\n    width: Beam width in meters\n    height: Beam height in meters\n    load_type: Type of loading ('point_center', 'point_end', 'distributed')\n\nReturns:\n    Maximum deflection in meters"
      },
      {
        "tool_name": "thermal_stress",
        "args": [
          "temp_change",
          "constrained"
        ],
        "doc": "Calculate thermal stress due to temperature change\n\nArgs:\n    temp_change: Change in temperature in K\n    constrained: Whether thermal expansion is constrained\n\nReturns:\n    Thermal stress in Pa (if constrained) or strain (if unconstrained)"
      }
    ]
  },
  {
    "id": "immunology_lab.py",
    "name": "Immunology",
    "description": "Production immunology laboratory with validated models",
    "capabilities": [
      {
        "tool_name": "simulate_antibody_antigen_binding",
        "args": [
          "antibody_conc_nM",
          "antigen_conc_nM",
          "affinity",
          "duration_s"
        ],
        "doc": "Simulate antibody-antigen binding kinetics using Langmuir model\n\nArgs:\n    antibody_conc_nM: Antibody concentration (nM)\n    antigen_conc_nM: Antigen concentration (nM)\n    affinity: 'high_affinity', 'medium_affinity', or 'low_affinity'\n    duration_s: Duration in seconds\n\nReturns:\n    Binding kinetics data"
      },
      {
        "tool_name": "simulate_immune_response",
        "args": [
          "pathogen_dose",
          "pathogen_growth_rate",
          "duration_days"
        ],
        "doc": "Simulate complete immune response to pathogen\n\nArgs:\n    pathogen_dose: Initial pathogen count\n    pathogen_growth_rate: Doubling time (hours)\n    duration_days: Simulation duration\n\nReturns:\n    Immune response dynamics"
      },
      {
        "tool_name": "calculate_vaccine_efficacy",
        "args": [
          "vaccine_type",
          "dose_schedule",
          "adjuvant"
        ],
        "doc": "Calculate vaccine efficacy based on vaccine parameters\n\nArgs:\n    vaccine_type: 'mRNA', 'protein', 'inactivated', 'live_attenuated'\n    dose_schedule: Days for each dose\n    adjuvant: Whether adjuvant is included\n\nReturns:\n    Vaccine efficacy metrics"
      },
      {
        "tool_name": "simulate_autoimmune_disease",
        "args": [
          "disease",
          "duration_months",
          "treatment"
        ],
        "doc": "Simulate autoimmune disease progression\n\nArgs:\n    disease: 'rheumatoid_arthritis', 'lupus', 'multiple_sclerosis', 'type1_diabetes'\n    duration_months: Simulation duration\n    treatment: 'corticosteroid', 'dmard', 'biologic', None\n\nReturns:\n    Disease progression metrics"
      }
    ]
  },
  {
    "id": "materials_lab.py",
    "name": "Materials",
    "description": "Main Materials Science Laboratory API\n\nProvides unified interface for:\n- Material database access (6.6 million+ materials)\n- Material testing simulations\n- Material design and optimization\n- Property prediction with ML",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a materials science experiment.\n\nArgs:\n    experiment_spec: Dictionary specifying the experiment.\n        Required keys:\n        - 'experiment_type': str (e.g., 'tensile', 'compression', 'hardness')\n        - 'material_name': str\n        Other keys are passed as kwargs to the respective test method.\n\nReturns:\n    A dictionary containing the experiment results."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get the current status of the Materials Lab.\nFor MaterialsLab, this returns the database statistics."
      },
      {
        "tool_name": "validate_material_properties",
        "args": [
          "material_name",
          "properties"
        ],
        "doc": "Validate a material's tabulated properties against reference data.\n\nArgs:\n    material_name: Name used in the materials database.\n    properties: Optional iterable of property names to validate. If\n        omitted, all mapped properties for the material are checked.\n    raise_on_missing: When True, raise a ValueError if the material or\n        requested property does not have a configured reference datum.\n\nReturns:\n    Mapping of property name to ValidationResult."
      },
      {
        "tool_name": "validate_accuracy_suite",
        "args": [],
        "doc": "Run the configured accuracy suite for all mapped materials.\n\nReturns:\n    Nested mapping of material -> property -> ValidationResult."
      },
      {
        "tool_name": "get_material",
        "args": [
          "name"
        ],
        "doc": "Get material by name"
      },
      {
        "tool_name": "search_materials",
        "args": [],
        "doc": "Search materials by criteria"
      },
      {
        "tool_name": "list_categories",
        "args": [],
        "doc": "List all material categories"
      },
      {
        "tool_name": "list_materials",
        "args": [
          "category"
        ],
        "doc": "List material names, optionally filtered by category."
      },
      {
        "tool_name": "get_statistics",
        "args": [],
        "doc": "Get database statistics"
      },
      {
        "tool_name": "get_material_profile",
        "args": [
          "material_name"
        ],
        "doc": "Generate a detailed property profile with curves and metadata."
      },
      {
        "tool_name": "get_material_safety",
        "args": [
          "material_name"
        ],
        "doc": "Return MSDS-style safety information if available."
      },
      {
        "tool_name": "register_calibration",
        "args": [
          "material_name",
          "test_type",
          "property_name",
          "reference_value",
          "measured_value"
        ],
        "doc": "Register calibration measurement."
      },
      {
        "tool_name": "get_calibration_summary",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "simulate_ice_growth",
        "args": [
          "material_name",
          "temperature_k",
          "relative_humidity",
          "duration_hours"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "run_batch_experiments",
        "args": [
          "batch_specs"
        ],
        "doc": "Run multiple experiments and return serialisable summaries."
      },
      {
        "tool_name": "tensile_test",
        "args": [
          "material_name"
        ],
        "doc": "Run tensile test"
      },
      {
        "tool_name": "compression_test",
        "args": [
          "material_name"
        ],
        "doc": "Run compression test"
      },
      {
        "tool_name": "fatigue_test",
        "args": [
          "material_name"
        ],
        "doc": "Run fatigue test"
      },
      {
        "tool_name": "impact_test",
        "args": [
          "material_name"
        ],
        "doc": "Run impact test"
      },
      {
        "tool_name": "hardness_test",
        "args": [
          "material_name"
        ],
        "doc": "Run hardness test"
      },
      {
        "tool_name": "thermal_test",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "Run thermal test"
      },
      {
        "tool_name": "corrosion_test",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "Run corrosion test"
      },
      {
        "tool_name": "environmental_test",
        "args": [
          "material_name"
        ],
        "doc": "Run environmental test"
      },
      {
        "tool_name": "optimize_alloy",
        "args": [
          "base_elements",
          "target_properties"
        ],
        "doc": "Optimize alloy composition"
      },
      {
        "tool_name": "design_composite",
        "args": [
          "fiber_name",
          "matrix_name"
        ],
        "doc": "Design composite material"
      },
      {
        "tool_name": "add_nanoparticles",
        "args": [
          "base_material_name"
        ],
        "doc": "Add nanoparticles to material"
      },
      {
        "tool_name": "apply_coating",
        "args": [
          "base_material_name"
        ],
        "doc": "Apply surface coating"
      },
      {
        "tool_name": "design_lattice",
        "args": [
          "base_material_name"
        ],
        "doc": "Design lattice structure for AM"
      },
      {
        "tool_name": "predict_from_composition",
        "args": [
          "composition",
          "properties"
        ],
        "doc": "Predict properties from composition"
      },
      {
        "tool_name": "predict_from_structure",
        "args": [
          "crystal_structure",
          "bonding_type",
          "properties"
        ],
        "doc": "Predict properties from structure"
      },
      {
        "tool_name": "predict_by_similarity",
        "args": [
          "reference_material_name",
          "property_name"
        ],
        "doc": "Predict property by similarity"
      },
      {
        "tool_name": "compare_materials",
        "args": [
          "material_names",
          "properties"
        ],
        "doc": "Compare multiple materials"
      },
      {
        "tool_name": "find_best_material",
        "args": [
          "category",
          "optimize_for",
          "constraints"
        ],
        "doc": "Find best material for application\n\nArgs:\n    category: Material category to search\n    optimize_for: Property to maximize\n    constraints: Dict of property constraints (min/max values)"
      }
    ]
  },
  {
    "id": "geophysics_lab.py",
    "name": "Geophysics",
    "description": "Production-ready geophysics simulation and analysis",
    "capabilities": [
      {
        "tool_name": "earthquake_magnitude_energy",
        "args": [
          "magnitude",
          "scale"
        ],
        "doc": "Calculate earthquake energy release from magnitude\nSupports moment magnitude (Mw) and Richter scale (ML)\n\nArgs:\n    magnitude: Earthquake magnitude\n    scale: 'moment' (Mw) or 'richter' (ML)\n\nReturns:\n    Dictionary with energy, TNT equivalent, and seismic properties"
      },
      {
        "tool_name": "seismic_wave_arrival",
        "args": [
          "epicenter_distance_km",
          "focal_depth_km"
        ],
        "doc": "Calculate P-wave and S-wave arrival times\nUses straight-ray approximation through homogeneous crust\n\nArgs:\n    epicenter_distance_km: Horizontal distance from epicenter\n    focal_depth_km: Earthquake focal depth\n\nReturns:\n    Dictionary with arrival times and travel paths"
      },
      {
        "tool_name": "plate_motion_model",
        "args": [
          "spreading_rate_mm_yr",
          "time_years"
        ],
        "doc": "Model seafloor spreading and plate motion\nBased on constant spreading rate assumption\n\nArgs:\n    spreading_rate_mm_yr: Spreading rate in mm/year\n    time_years: Time array in years\n\nReturns:\n    Dictionary with plate positions and magnetic anomalies"
      },
      {
        "tool_name": "gravity_anomaly",
        "args": [
          "density_contrast_kg_m3",
          "body_depth_m",
          "body_radius_m",
          "distance_m"
        ],
        "doc": "Calculate gravity anomaly from buried spherical mass\nUses point mass approximation for distant observations\n\nArgs:\n    density_contrast_kg_m3: Density contrast with surroundings\n    body_depth_m: Depth to center of mass\n    body_radius_m: Radius of spherical body\n    distance_m: Horizontal distance array\n\nReturns:\n    Dictionary with gravity anomaly profile"
      },
      {
        "tool_name": "mineral_identification",
        "args": [
          "density_measured",
          "hardness_measured",
          "tolerance_density",
          "tolerance_hardness"
        ],
        "doc": "Identify minerals based on physical properties\nCompares measured values against mineral database\n\nArgs:\n    density_measured: Measured density in kg/m\u00b3\n    hardness_measured: Measured Mohs hardness\n    tolerance_density: Density matching tolerance\n    tolerance_hardness: Hardness matching tolerance\n\nReturns:\n    Dictionary with candidate minerals and confidence scores"
      },
      {
        "tool_name": "resource_grade_estimation",
        "args": [
          "sample_grades",
          "sample_locations",
          "cutoff_grade"
        ],
        "doc": "Estimate mineral resource grade and tonnage\nUses statistical methods for ore body characterization\n\nArgs:\n    sample_grades: Array of assay grades (e.g., % metal)\n    sample_locations: Array of sample depths (m)\n    cutoff_grade: Economic cutoff grade\n\nReturns:\n    Dictionary with resource statistics and classification"
      },
      {
        "tool_name": "seismic_moment_tensor",
        "args": [
          "strike",
          "dip",
          "rake",
          "magnitude"
        ],
        "doc": "Calculate seismic moment tensor from fault parameters\nUses double-couple representation\n\nArgs:\n    strike: Fault strike angle (0-360\u00b0)\n    dip: Fault dip angle (0-90\u00b0)\n    rake: Slip rake angle (-180 to 180\u00b0)\n    magnitude: Moment magnitude\n\nReturns:\n    Dictionary with moment tensor components and fault type"
      },
      {
        "tool_name": "run_diagnostics",
        "args": [],
        "doc": "Run comprehensive geophysics diagnostics"
      }
    ]
  },
  {
    "id": "base_lab.py",
    "name": "Base",
    "description": "Abstract base class for all laboratories in QuLabInfinite.\n\nThis class defines the common interface that all specialized labs\n(e.g., MaterialsLab, ChemistryLaboratory, QuantumLabSimulator) must implement.\nThis ensures a consistent API for initialization, configuration,\nand execution of simulations across the platform.",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a specific experiment based on the provided specification.\n\nArgs:\n    experiment_spec: A dictionary defining the experiment to be run,\n                     including parameters and desired outputs.\n\nReturns:\n    A dictionary containing the results of the experiment."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get the current status of the laboratory.\n\nReturns:\n    A dictionary containing status information, such as backend state,\n    loaded data, and available capabilities."
      },
      {
        "tool_name": "get_capabilities",
        "args": [],
        "doc": "Get the capabilities of the laboratory.\n\nReturns:\n    A dictionary describing the capabilities of the lab."
      }
    ]
  },
  {
    "id": "cardiology_lab.py",
    "name": "Cardiology",
    "description": "Production cardiology laboratory with validated physiological models",
    "capabilities": [
      {
        "tool_name": "simulate_cardiac_cycle",
        "args": [
          "heart_rate",
          "contractility",
          "duration_s"
        ],
        "doc": "Simulate complete cardiac cycle with pressure-volume relationships\n\nArgs:\n    heart_rate: Heart rate (bpm)\n    contractility: Contractility factor (1.0 = normal)\n    duration_s: Duration in seconds\n\nReturns:\n    Cardiac cycle data"
      },
      {
        "tool_name": "generate_ecg_signal",
        "args": [
          "heart_rate",
          "rhythm",
          "duration_s",
          "sampling_rate"
        ],
        "doc": "Generate realistic ECG signal\n\nArgs:\n    heart_rate: Heart rate (bpm)\n    rhythm: 'normal_sinus', 'atrial_fib', 'ventricular_tach'\n    duration_s: Duration in seconds\n    sampling_rate: Sampling rate (Hz)\n\nReturns:\n    ECG signal data"
      },
      {
        "tool_name": "calculate_blood_flow",
        "args": [
          "vessel_radius_mm",
          "vessel_length_cm",
          "pressure_drop_mmHg"
        ],
        "doc": "Calculate blood flow using Poiseuille's Law\n\nArgs:\n    vessel_radius_mm: Vessel inner radius (mm)\n    vessel_length_cm: Vessel length (cm)\n    pressure_drop_mmHg: Pressure difference (mmHg)\n\nReturns:\n    Blood flow calculations"
      },
      {
        "tool_name": "simulate_drug_effect",
        "args": [
          "drug",
          "dose_mg",
          "duration_hours"
        ],
        "doc": "Simulate cardiac drug effects over time\n\nArgs:\n    drug: Drug type\n    dose_mg: Dose in mg\n    duration_hours: Simulation duration\n\nReturns:\n    Drug effect timeline"
      }
    ]
  },
  {
    "id": "atmospheric_lab.py",
    "name": "Atmospheric",
    "description": "Production-ready atmospheric science simulation and analysis",
    "capabilities": [
      {
        "tool_name": "energy_balance_model",
        "args": [
          "co2_ppm",
          "albedo",
          "ocean_heat_capacity"
        ],
        "doc": "Zero-dimensional energy balance climate model\nBased on Budyko-Sellers model with radiative forcing\n\nArgs:\n    co2_ppm: CO2 concentration (parts per million)\n    albedo: Planetary albedo (0-1)\n    ocean_heat_capacity: Ocean heat capacity (J/(m^2\u00b7K))\n\nReturns:\n    Dictionary with equilibrium temperature and forcing"
      },
      {
        "tool_name": "greenhouse_gas_forcing",
        "args": [
          "concentrations"
        ],
        "doc": "Calculate radiative forcing from multiple greenhouse gases\nUses IPCC AR6 simplified expressions\n\nArgs:\n    concentrations: Dict with gas names and concentrations\n                   CO2 in ppm, others in ppb\n\nReturns:\n    Dictionary with individual and total forcing"
      },
      {
        "tool_name": "atmospheric_pressure_profile",
        "args": [
          "altitude_km",
          "temperature_profile"
        ],
        "doc": "Calculate atmospheric pressure and density vs altitude\nUses barometric formula with realistic temperature profile\n\nArgs:\n    altitude_km: Altitude array in kilometers\n    temperature_profile: Optional temperature profile (K), uses US Standard Atmosphere if None\n\nReturns:\n    Dictionary with pressure, density, and temperature profiles"
      },
      {
        "tool_name": "air_quality_index",
        "args": [
          "pollutants",
          "standard"
        ],
        "doc": "Calculate Air Quality Index from pollutant concentrations\nBased on EPA AQI calculation method\n\nArgs:\n    pollutants: Dict with pollutant concentrations\n               PM2.5, PM10 in \u03bcg/m\u00b3\n               O3, CO, SO2, NO2 in ppb or ppm\n    standard: 'EPA' (US) or 'WHO' (World Health Organization)\n\nReturns:\n    Dictionary with AQI values and health categories"
      },
      {
        "tool_name": "simple_weather_prediction",
        "args": [
          "initial_conditions",
          "forecast_hours"
        ],
        "doc": "Simplified numerical weather prediction using primitive equations\nImplements basic advection-diffusion for temperature and pressure\n\nArgs:\n    initial_conditions: Dict with T (K), P (Pa), u (m/s), v (m/s)\n    forecast_hours: Forecast duration in hours\n\nReturns:\n    Dictionary with forecasted temperature and pressure evolution"
      },
      {
        "tool_name": "run_diagnostics",
        "args": [],
        "doc": "Run comprehensive atmospheric science diagnostics"
      }
    ]
  },
  {
    "id": "atmospheric_science_lab.py",
    "name": "Atmospheric Science",
    "description": "Main laboratory interface for atmospheric science simulations\nIntegrates climate modeling, air quality, and weather prediction",
    "capabilities": [
      {
        "tool_name": "run_comprehensive_climate_analysis",
        "args": [
          "co2_ppm",
          "ch4_ppb",
          "n2o_ppb",
          "projection_years"
        ],
        "doc": "Run complete climate analysis with current greenhouse gas levels\n\nArgs:\n    co2_ppm: CO2 concentration\n    ch4_ppb: CH4 concentration\n    n2o_ppb: N2O concentration\n    projection_years: Years to project\n\nReturns:\n    Comprehensive climate analysis results"
      },
      {
        "tool_name": "run_air_quality_assessment",
        "args": [
          "pollutants"
        ],
        "doc": "Comprehensive air quality assessment\n\nArgs:\n    pollutants: Dictionary of pollutant concentrations\n\nReturns:\n    Air quality analysis with health recommendations"
      },
      {
        "tool_name": "run_greenhouse_gas_scenario",
        "args": [
          "emissions_gt_per_year",
          "years"
        ],
        "doc": "Simulate greenhouse gas emission scenario\n\nArgs:\n    emissions_gt_per_year: Annual emissions\n    years: Simulation duration\n\nReturns:\n    CO2 cycle simulation and climate impact"
      },
      {
        "tool_name": "run_weather_forecast_analysis",
        "args": [
          "altitude_m",
          "surface_temp_c",
          "relative_humidity",
          "surface_pressure_hpa"
        ],
        "doc": "Comprehensive weather analysis at specified altitude\n\nArgs:\n    altitude_m: Altitude for analysis\n    surface_temp_c: Surface temperature\n    relative_humidity: Relative humidity (0-1)\n    surface_pressure_hpa: Surface pressure\n\nReturns:\n    Complete weather analysis"
      }
    ]
  },
  {
    "id": "base_lab.py",
    "name": "Base",
    "description": "Abstract base class for all laboratories in QuLabInfinite.\n\nThis class defines the common interface that all specialized labs\n(e.g., MaterialsLab, ChemistryLaboratory, QuantumLabSimulator) must implement.\nThis ensures a consistent API for initialization, configuration,\nand execution of simulations across the platform.",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a specific experiment based on the provided specification.\n\nArgs:\n    experiment_spec: A dictionary defining the experiment to be run,\n                     including parameters and desired outputs.\n\nReturns:\n    A dictionary containing the results of the experiment."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get the current status of the laboratory.\n\nReturns:\n    A dictionary containing status information, such as backend state,\n    loaded data, and available capabilities."
      },
      {
        "tool_name": "get_capabilities",
        "args": [],
        "doc": "Get the capabilities of the laboratory.\n\nReturns:\n    A dictionary describing the capabilities of the lab."
      }
    ]
  },
  {
    "id": "materials_lab.py",
    "name": "Materials",
    "description": "Main Materials Science Laboratory API\n\nProvides unified interface for:\n- Material database access (1000+ materials)\n- Material testing simulations\n- Material design and optimization\n- Property prediction with ML",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a materials science experiment.\n\nArgs:\n    experiment_spec: Dictionary specifying the experiment.\n        Required keys:\n        - 'experiment_type': str (e.g., 'tensile', 'compression', 'hardness')\n        - 'material_name': str\n        Other keys are passed as kwargs to the respective test method.\n\nReturns:\n    A dictionary containing the experiment results."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get the current status of the Materials Lab.\nFor MaterialsLab, this returns the database statistics."
      },
      {
        "tool_name": "validate_material_properties",
        "args": [
          "material_name",
          "properties"
        ],
        "doc": "Validate a material's tabulated properties against reference data.\n\nArgs:\n    material_name: Name used in the materials database.\n    properties: Optional iterable of property names to validate. If\n        omitted, all mapped properties for the material are checked.\n    raise_on_missing: When True, raise a ValueError if the material or\n        requested property does not have a configured reference datum.\n\nReturns:\n    Mapping of property name to ValidationResult."
      },
      {
        "tool_name": "validate_accuracy_suite",
        "args": [],
        "doc": "Run the configured accuracy suite for all mapped materials.\n\nReturns:\n    Nested mapping of material -> property -> ValidationResult."
      },
      {
        "tool_name": "get_material",
        "args": [
          "name"
        ],
        "doc": "Get material by name"
      },
      {
        "tool_name": "search_materials",
        "args": [],
        "doc": "Search materials by criteria"
      },
      {
        "tool_name": "list_categories",
        "args": [],
        "doc": "List all material categories"
      },
      {
        "tool_name": "list_materials",
        "args": [
          "category"
        ],
        "doc": "List material names, optionally filtered by category."
      },
      {
        "tool_name": "get_statistics",
        "args": [],
        "doc": "Get database statistics"
      },
      {
        "tool_name": "get_material_profile",
        "args": [
          "material_name"
        ],
        "doc": "Generate a detailed property profile with curves and metadata."
      },
      {
        "tool_name": "get_material_safety",
        "args": [
          "material_name"
        ],
        "doc": "Return MSDS-style safety information if available."
      },
      {
        "tool_name": "register_calibration",
        "args": [
          "material_name",
          "test_type",
          "property_name",
          "reference_value",
          "measured_value"
        ],
        "doc": "Register calibration measurement."
      },
      {
        "tool_name": "get_calibration_summary",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "simulate_ice_growth",
        "args": [
          "material_name",
          "temperature_k",
          "relative_humidity",
          "duration_hours"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "run_batch_experiments",
        "args": [
          "batch_specs"
        ],
        "doc": "Run multiple experiments and return serialisable summaries."
      },
      {
        "tool_name": "tensile_test",
        "args": [
          "material_name"
        ],
        "doc": "Run tensile test"
      },
      {
        "tool_name": "compression_test",
        "args": [
          "material_name"
        ],
        "doc": "Run compression test"
      },
      {
        "tool_name": "fatigue_test",
        "args": [
          "material_name"
        ],
        "doc": "Run fatigue test"
      },
      {
        "tool_name": "impact_test",
        "args": [
          "material_name"
        ],
        "doc": "Run impact test"
      },
      {
        "tool_name": "hardness_test",
        "args": [
          "material_name"
        ],
        "doc": "Run hardness test"
      },
      {
        "tool_name": "thermal_test",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "Run thermal test"
      },
      {
        "tool_name": "corrosion_test",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "Run corrosion test"
      },
      {
        "tool_name": "environmental_test",
        "args": [
          "material_name"
        ],
        "doc": "Run environmental test"
      },
      {
        "tool_name": "optimize_alloy",
        "args": [
          "base_elements",
          "target_properties"
        ],
        "doc": "Optimize alloy composition"
      },
      {
        "tool_name": "design_composite",
        "args": [
          "fiber_name",
          "matrix_name"
        ],
        "doc": "Design composite material"
      },
      {
        "tool_name": "add_nanoparticles",
        "args": [
          "base_material_name"
        ],
        "doc": "Add nanoparticles to material"
      },
      {
        "tool_name": "apply_coating",
        "args": [
          "base_material_name"
        ],
        "doc": "Apply surface coating"
      },
      {
        "tool_name": "design_lattice",
        "args": [
          "base_material_name"
        ],
        "doc": "Design lattice structure for AM"
      },
      {
        "tool_name": "predict_from_composition",
        "args": [
          "composition",
          "properties"
        ],
        "doc": "Predict properties from composition"
      },
      {
        "tool_name": "predict_from_structure",
        "args": [
          "crystal_structure",
          "bonding_type",
          "properties"
        ],
        "doc": "Predict properties from structure"
      },
      {
        "tool_name": "predict_by_similarity",
        "args": [
          "reference_material_name",
          "property_name"
        ],
        "doc": "Predict property by similarity"
      },
      {
        "tool_name": "compare_materials",
        "args": [
          "material_names",
          "properties"
        ],
        "doc": "Compare multiple materials"
      },
      {
        "tool_name": "find_best_material",
        "args": [
          "category",
          "optimize_for",
          "constraints"
        ],
        "doc": "Find best material for application\n\nArgs:\n    category: Material category to search\n    optimize_for: Property to maximize\n    constraints: Dict of property constraints (min/max values)"
      }
    ]
  },
  {
    "id": "materials_lab.py",
    "name": "Materials",
    "description": "Main Materials Science Laboratory API\n\nProvides unified interface for:\n- Material database access (1000+ materials)\n- Material testing simulations\n- Material design and optimization\n- Property prediction with ML",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a materials science experiment.\n\nArgs:\n    experiment_spec: Dictionary specifying the experiment.\n        Required keys:\n        - 'experiment_type': str (e.g., 'tensile', 'compression', 'hardness')\n        - 'material_name': str\n        Other keys are passed as kwargs to the respective test method.\n\nReturns:\n    A dictionary containing the experiment results."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get the current status of the Materials Lab.\nFor MaterialsLab, this returns the database statistics."
      },
      {
        "tool_name": "validate_material_properties",
        "args": [
          "material_name",
          "properties"
        ],
        "doc": "Validate a material's tabulated properties against reference data.\n\nArgs:\n    material_name: Name used in the materials database.\n    properties: Optional iterable of property names to validate. If\n        omitted, all mapped properties for the material are checked.\n    raise_on_missing: When True, raise a ValueError if the material or\n        requested property does not have a configured reference datum.\n\nReturns:\n    Mapping of property name to ValidationResult."
      },
      {
        "tool_name": "validate_accuracy_suite",
        "args": [],
        "doc": "Run the configured accuracy suite for all mapped materials.\n\nReturns:\n    Nested mapping of material -> property -> ValidationResult."
      },
      {
        "tool_name": "get_material",
        "args": [
          "name"
        ],
        "doc": "Get material by name"
      },
      {
        "tool_name": "search_materials",
        "args": [],
        "doc": "Search materials by criteria"
      },
      {
        "tool_name": "list_categories",
        "args": [],
        "doc": "List all material categories"
      },
      {
        "tool_name": "list_materials",
        "args": [
          "category"
        ],
        "doc": "List material names, optionally filtered by category."
      },
      {
        "tool_name": "get_statistics",
        "args": [],
        "doc": "Get database statistics"
      },
      {
        "tool_name": "get_material_profile",
        "args": [
          "material_name"
        ],
        "doc": "Generate a detailed property profile with curves and metadata."
      },
      {
        "tool_name": "get_material_safety",
        "args": [
          "material_name"
        ],
        "doc": "Return MSDS-style safety information if available."
      },
      {
        "tool_name": "register_calibration",
        "args": [
          "material_name",
          "test_type",
          "property_name",
          "reference_value",
          "measured_value"
        ],
        "doc": "Register calibration measurement."
      },
      {
        "tool_name": "get_calibration_summary",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "simulate_ice_growth",
        "args": [
          "material_name",
          "temperature_k",
          "relative_humidity",
          "duration_hours"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "run_batch_experiments",
        "args": [
          "batch_specs"
        ],
        "doc": "Run multiple experiments and return serialisable summaries."
      },
      {
        "tool_name": "tensile_test",
        "args": [
          "material_name"
        ],
        "doc": "Run tensile test"
      },
      {
        "tool_name": "compression_test",
        "args": [
          "material_name"
        ],
        "doc": "Run compression test"
      },
      {
        "tool_name": "fatigue_test",
        "args": [
          "material_name"
        ],
        "doc": "Run fatigue test"
      },
      {
        "tool_name": "impact_test",
        "args": [
          "material_name"
        ],
        "doc": "Run impact test"
      },
      {
        "tool_name": "hardness_test",
        "args": [
          "material_name"
        ],
        "doc": "Run hardness test"
      },
      {
        "tool_name": "thermal_test",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "Run thermal test"
      },
      {
        "tool_name": "corrosion_test",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "Run corrosion test"
      },
      {
        "tool_name": "environmental_test",
        "args": [
          "material_name"
        ],
        "doc": "Run environmental test"
      },
      {
        "tool_name": "optimize_alloy",
        "args": [
          "base_elements",
          "target_properties"
        ],
        "doc": "Optimize alloy composition"
      },
      {
        "tool_name": "design_composite",
        "args": [
          "fiber_name",
          "matrix_name"
        ],
        "doc": "Design composite material"
      },
      {
        "tool_name": "add_nanoparticles",
        "args": [
          "base_material_name"
        ],
        "doc": "Add nanoparticles to material"
      },
      {
        "tool_name": "apply_coating",
        "args": [
          "base_material_name"
        ],
        "doc": "Apply surface coating"
      },
      {
        "tool_name": "design_lattice",
        "args": [
          "base_material_name"
        ],
        "doc": "Design lattice structure for AM"
      },
      {
        "tool_name": "predict_from_composition",
        "args": [
          "composition",
          "properties"
        ],
        "doc": "Predict properties from composition"
      },
      {
        "tool_name": "predict_from_structure",
        "args": [
          "crystal_structure",
          "bonding_type",
          "properties"
        ],
        "doc": "Predict properties from structure"
      },
      {
        "tool_name": "predict_by_similarity",
        "args": [
          "reference_material_name",
          "property_name"
        ],
        "doc": "Predict property by similarity"
      },
      {
        "tool_name": "compare_materials",
        "args": [
          "material_names",
          "properties"
        ],
        "doc": "Compare multiple materials"
      },
      {
        "tool_name": "find_best_material",
        "args": [
          "category",
          "optimize_for",
          "constraints"
        ],
        "doc": "Find best material for application\n\nArgs:\n    category: Material category to search\n    optimize_for: Property to maximize\n    constraints: Dict of property constraints (min/max values)"
      }
    ]
  },
  {
    "id": "base_lab.py",
    "name": "Base",
    "description": "Abstract base class for all laboratories in QuLabInfinite.\n\nThis class defines the common interface that all specialized labs\n(e.g., MaterialsLab, ChemistryLaboratory, QuantumLabSimulator) must implement.\nThis ensures a consistent API for initialization, configuration,\nand execution of simulations across the platform.",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a specific experiment based on the provided specification.\n\nArgs:\n    experiment_spec: A dictionary defining the experiment to be run,\n                     including parameters and desired outputs.\n\nReturns:\n    A dictionary containing the results of the experiment."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get the current status of the laboratory.\n\nReturns:\n    A dictionary containing status information, such as backend state,\n    loaded data, and available capabilities."
      },
      {
        "tool_name": "get_capabilities",
        "args": [],
        "doc": "Get the capabilities of the laboratory.\n\nReturns:\n    A dictionary describing the capabilities of the lab."
      }
    ]
  },
  {
    "id": "quantum_lab.py",
    "name": "Quantum",
    "description": "Unified quantum laboratory simulator.\n\nFeatures:\n- 30-qubit exact statevector simulation\n- Tensor network approximation for >30 qubits\n- Quantum chemistry integration\n- Materials science quantum calculations\n- Quantum sensor modeling\n- Cognition-inspired algorithms\n\nIntegration:\n- Wraps existing CircuitSimulator (30-qubit exact)\n- Wraps QuantumCognition (quantum-inspired)\n- Extends with chemistry, materials, sensors\n\nECH0 Usage Examples:\n```python\n# Basic circuit simulation\nlab = QuantumLabSimulator(num_qubits=5)\nlab.h(0)  # Hadamard on qubit 0\nlab.cnot(0, 1)  # Entangle qubits\nresults = lab.measure_all()\n\n# Chemistry calculation\nfrom quantum_chemistry import Molecule\nh2 = Molecule.hydrogen_molecule(bond_length=0.74)\nenergy = lab.chemistry.compute_ground_state_energy(h2)\n\n# Materials property\nenergy_gap = lab.materials.compute_band_gap(\"silicon\")\n\n# Quantum sensing\nsensitivity = lab.sensors.magnetometry_sensitivity(num_qubits=10)\n```",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a quantum experiment.\n\nExample spec:\n{\n    \"experiment_type\": \"bell_pair\",\n}\n{\n    \"experiment_type\": \"ghz_state\",\n    \"num_qubits\": 4\n}\n{\n    \"experiment_type\": \"custom_circuit\",\n    \"operations\": [\n        {\"gate\": \"h\", \"qubit\": 0},\n        {\"gate\": \"cnot\", \"control\": 0, \"target\": 1}\n    ]\n}"
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get information about current backend and state."
      },
      {
        "tool_name": "h",
        "args": [
          "qubit"
        ],
        "doc": "Apply Hadamard gate"
      },
      {
        "tool_name": "x",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-X gate"
      },
      {
        "tool_name": "y",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-Y gate"
      },
      {
        "tool_name": "z",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-Z gate"
      },
      {
        "tool_name": "rx",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RX rotation"
      },
      {
        "tool_name": "ry",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RY rotation"
      },
      {
        "tool_name": "rz",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RZ rotation"
      },
      {
        "tool_name": "cnot",
        "args": [
          "control",
          "target"
        ],
        "doc": "Apply CNOT gate"
      },
      {
        "tool_name": "cz",
        "args": [
          "control",
          "target"
        ],
        "doc": "Apply CZ gate"
      },
      {
        "tool_name": "measure",
        "args": [
          "qubit"
        ],
        "doc": "Measure single qubit"
      },
      {
        "tool_name": "measure_all",
        "args": [],
        "doc": "Measure all qubits"
      },
      {
        "tool_name": "get_probabilities",
        "args": [],
        "doc": "Get probability distribution"
      },
      {
        "tool_name": "expectation_value",
        "args": [
          "observable"
        ],
        "doc": "Compute expectation value of observable.\n\nArgs:\n    observable: Pauli string like 'Z0' or 'X0Y1Z2'\n\nReturns:\n    Expectation value <\u03c8|O|\u03c8>"
      },
      {
        "tool_name": "fidelity",
        "args": [
          "target_state"
        ],
        "doc": "Compute fidelity with target state.\n\nF = |<\u03c8|\u03c6>|\u00b2"
      },
      {
        "tool_name": "chemistry",
        "args": [],
        "doc": "Access quantum chemistry module"
      },
      {
        "tool_name": "materials",
        "args": [],
        "doc": "Access quantum materials module"
      },
      {
        "tool_name": "sensors",
        "args": [],
        "doc": "Access quantum sensors module"
      },
      {
        "tool_name": "reset",
        "args": [],
        "doc": "Reset quantum state to |0\u27e9^n"
      },
      {
        "tool_name": "print_state",
        "args": [
          "top_n"
        ],
        "doc": "Print quantum state"
      },
      {
        "tool_name": "get_backend_info",
        "args": [],
        "doc": "Get information about current backend"
      }
    ]
  },
  {
    "id": "chemistry_lab.py",
    "name": "Chemistry",
    "description": "Unified chemistry laboratory interface.\n\nProvides access to:\n1. Molecular Dynamics (100k atoms @ 1fs)\n2. Reaction Simulation (TST, NEB, catalysis)\n3. Synthesis Planning (retrosynthesis, optimization)\n4. Spectroscopy Prediction (NMR, IR, UV-Vis, MS, XRD)\n5. Solvation Models (PCM, COSMO, SMD, pH effects)\n6. Quantum Chemistry (DFT, HF, MP2, CCSD(T))\n\nTarget accuracy: <5% error on reaction energetics, <10% on spectroscopy",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a chemistry experiment."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Returns a summary of the lab's configuration and capabilities."
      },
      {
        "tool_name": "calculate_dissolution_enthalpy",
        "args": [
          "salt",
          "solvent",
          "temperature_K"
        ],
        "doc": "Compute the dissolution enthalpy for an ionic solid using the Born-Haber cycle.\n\nArgs:\n    salt: Salt formula (e.g., \"NaCl\")\n    solvent: Solvent identifier\n    temperature_K: Temperature in Kelvin\n\nReturns:\n    Dictionary with \u0394H (kJ/mol) and source metadata."
      },
      {
        "tool_name": "create_md_simulation",
        "args": [
          "atoms",
          "box_size",
          "force_field",
          "ensemble",
          "timestep"
        ],
        "doc": "Create molecular dynamics simulation."
      },
      {
        "tool_name": "run_md_simulation",
        "args": [
          "n_steps",
          "temperature",
          "output_interval"
        ],
        "doc": "Run MD simulation."
      },
      {
        "tool_name": "simulate_reaction",
        "args": [
          "reactants",
          "products",
          "conditions",
          "reaction_name",
          "materials_lab",
          "environment_simulator"
        ],
        "doc": "Simulate chemical reaction and predict kinetics."
      },
      {
        "tool_name": "get_reaction_metadata",
        "args": [
          "reaction_name"
        ],
        "doc": "Expose reaction metadata summary."
      },
      {
        "tool_name": "plan_synthesis",
        "args": [
          "target",
          "max_depth"
        ],
        "doc": "Plan synthesis route to target compound."
      },
      {
        "tool_name": "analyze_synthesis_safety",
        "args": [
          "route"
        ],
        "doc": "Analyze safety of synthesis route."
      },
      {
        "tool_name": "predict_nmr",
        "args": [
          "molecule",
          "nucleus"
        ],
        "doc": "Predict NMR spectrum."
      },
      {
        "tool_name": "predict_ir",
        "args": [
          "molecule"
        ],
        "doc": "Predict IR spectrum."
      },
      {
        "tool_name": "predict_uv_vis",
        "args": [
          "molecule"
        ],
        "doc": "Predict UV-Vis spectrum."
      },
      {
        "tool_name": "predict_mass_spectrum",
        "args": [
          "molecule"
        ],
        "doc": "Predict mass spectrum."
      },
      {
        "tool_name": "calculate_solvation_energy",
        "args": [
          "solute",
          "solvent_name",
          "model"
        ],
        "doc": "Calculate solvation free energy."
      },
      {
        "tool_name": "predict_logP",
        "args": [
          "solute"
        ],
        "doc": "Predict octanol-water partition coefficient."
      },
      {
        "tool_name": "calculate_pH_effect",
        "args": [
          "solute",
          "pH",
          "pKa"
        ],
        "doc": "Calculate pH effects on ionization."
      },
      {
        "tool_name": "quantum_calculation",
        "args": [
          "molecule",
          "method",
          "basis_set"
        ],
        "doc": "Perform quantum chemistry calculation."
      },
      {
        "tool_name": "optimize_geometry",
        "args": [
          "molecule",
          "method"
        ],
        "doc": "Optimize molecular geometry."
      },
      {
        "tool_name": "calculate_vibrational_frequencies",
        "args": [
          "molecule"
        ],
        "doc": "Calculate vibrational frequencies."
      },
      {
        "tool_name": "complete_molecule_characterization",
        "args": [
          "molecule"
        ],
        "doc": "Complete characterization of molecule:\n- Spectroscopy (NMR, IR, UV-Vis, MS)\n- Solvation (logP, solubility)\n- Quantum properties (HOMO-LUMO, dipole)"
      },
      {
        "tool_name": "reaction_optimization_workflow",
        "args": [
          "reactants",
          "products",
          "catalysts"
        ],
        "doc": "Optimize reaction conditions:\n- Find optimal catalyst\n- Determine best temperature/pressure\n- Predict yields"
      }
    ]
  },
  {
    "id": "universal_lab.py",
    "name": "Universal",
    "description": "",
    "capabilities": [
      {
        "tool_name": "get_lab_info",
        "args": [
          "lab_id"
        ],
        "doc": "Introspects a lab file to find classes and methods."
      },
      {
        "tool_name": "combine_materials",
        "args": [
          "materials",
          "conditions"
        ],
        "doc": "Simulates the combination of materials under given conditions."
      }
    ]
  },
  {
    "id": "frequency_lab.py",
    "name": "Frequency",
    "description": "",
    "capabilities": [
      {
        "tool_name": "capture_and_analyze",
        "args": [
          "center_freq",
          "bandwidth",
          "sample_rate"
        ],
        "doc": "Capture signals from the SDR and perform frequency analysis."
      },
      {
        "tool_name": "scan_wifi_beacons",
        "args": [],
        "doc": "Scan for Wi-Fi beacons in the 2.4 GHz band.\nThis is a simplified demonstration. A real scan would hop channels."
      },
      {
        "tool_name": "deauth_wifi_target",
        "args": [
          "bssid",
          "client"
        ],
        "doc": "Transmit deauthentication packets to a target client on a network.\nWARNING: This is for educational purposes only. Unauthorized deauthentication\nattacks are illegal."
      },
      {
        "tool_name": "generate_and_transmit",
        "args": [
          "signal_params"
        ],
        "doc": "Generate a signal based on params and transmit it."
      },
      {
        "tool_name": "transmit_signal",
        "args": [
          "signal",
          "center_freq",
          "sample_rate"
        ],
        "doc": "Transmit a signal using the SDR."
      },
      {
        "tool_name": "run_sweep",
        "args": [
          "start_freq",
          "end_freq",
          "step_freq",
          "bandwidth",
          "sample_rate"
        ],
        "doc": "Sweep a frequency range and analyze the spectrum."
      }
    ]
  },
  {
    "id": "protein_engineering_lab.py",
    "name": "Protein Engineering",
    "description": "Production protein engineering laboratory with validated models",
    "capabilities": [
      {
        "tool_name": "get_reference_sequence",
        "args": [
          "name"
        ],
        "doc": "Retrieve a curated protein sequence.\n\nArgs:\n    name: Protein identifier (e.g., 'lysozyme')"
      },
      {
        "tool_name": "calculate_isoelectric_point",
        "args": [
          "sequence",
          "precision",
          "composition_override"
        ],
        "doc": "Calculate the isoelectric point (pI) for a protein sequence.\n\nUses a Henderson-Hasselbalch charge balance with standard pKa values."
      },
      {
        "tool_name": "predict_protein_folding",
        "args": [
          "sequence",
          "iterations"
        ],
        "doc": "Predict protein 3D structure (simplified AlphaFold-style)\n\nArgs:\n    sequence: Amino acid sequence\n    iterations: Optimization iterations\n\nReturns:\n    Predicted protein structure"
      },
      {
        "tool_name": "simulate_enzyme_kinetics",
        "args": [
          "enzyme_name",
          "vmax",
          "km"
        ],
        "doc": "Simulate Michaelis-Menten enzyme kinetics\n\nArgs:\n    enzyme_name: Enzyme identifier\n    vmax: Maximum velocity (\u03bcM/s)\n    km: Michaelis constant (\u03bcM)\n\nReturns:\n    Enzyme kinetics data"
      },
      {
        "tool_name": "calculate_binding_affinity",
        "args": [
          "protein_sequence",
          "ligand_name",
          "binding_site_residues"
        ],
        "doc": "Calculate protein-ligand binding affinity\n\nArgs:\n    protein_sequence: Protein sequence\n    ligand_name: Ligand identifier\n    binding_site_residues: Residue indices in binding site\n\nReturns:\n    Binding affinity metrics"
      },
      {
        "tool_name": "predict_mutation_effect",
        "args": [
          "sequence",
          "position",
          "new_amino_acid"
        ],
        "doc": "Predict effect of point mutation\n\nArgs:\n    sequence: Original sequence\n    position: Position to mutate (0-indexed)\n    new_amino_acid: New amino acid (single letter)\n\nReturns:\n    Mutation effect prediction"
      },
      {
        "tool_name": "design_stabilizing_mutations",
        "args": [
          "sequence",
          "n_mutations"
        ],
        "doc": "Design mutations to stabilize protein\n\nArgs:\n    sequence: Original sequence\n    n_mutations: Number of mutations to design\n\nReturns:\n    List of proposed stabilizing mutations"
      }
    ]
  },
  {
    "id": "quantum_lab.py",
    "name": "Quantum",
    "description": "Unified quantum laboratory simulator.\n\nFeatures:\n- 30-qubit exact statevector simulation\n- Tensor network approximation for >30 qubits\n- Quantum chemistry integration\n- Materials science quantum calculations\n- Quantum sensor modeling\n- Cognition-inspired algorithms\n\nIntegration:\n- Wraps existing CircuitSimulator (30-qubit exact)\n- Wraps QuantumCognition (quantum-inspired)\n- Extends with chemistry, materials, sensors\n\nECH0 Usage Examples:\n```python\n# Basic circuit simulation\nlab = QuantumLabSimulator(num_qubits=5)\nlab.h(0)  # Hadamard on qubit 0\nlab.cnot(0, 1)  # Entangle qubits\nresults = lab.measure_all()\n\n# Chemistry calculation\nfrom quantum_chemistry import Molecule\nh2 = Molecule.hydrogen_molecule(bond_length=0.74)\nenergy = lab.chemistry.compute_ground_state_energy(h2)\n\n# Materials property\nenergy_gap = lab.materials.compute_band_gap(\"silicon\")\n\n# Quantum sensing\nsensitivity = lab.sensors.magnetometry_sensitivity(num_qubits=10)\n```",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a quantum experiment.\n\nExample spec:\n{\n    \"experiment_type\": \"bell_pair\",\n}\n{\n    \"experiment_type\": \"ghz_state\",\n    \"num_qubits\": 4\n}\n{\n    \"experiment_type\": \"custom_circuit\",\n    \"operations\": [\n        {\"gate\": \"h\", \"qubit\": 0},\n        {\"gate\": \"cnot\", \"control\": 0, \"target\": 1}\n    ]\n}"
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get information about current backend and state."
      },
      {
        "tool_name": "h",
        "args": [
          "qubit"
        ],
        "doc": "Apply Hadamard gate"
      },
      {
        "tool_name": "x",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-X gate"
      },
      {
        "tool_name": "y",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-Y gate"
      },
      {
        "tool_name": "z",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-Z gate"
      },
      {
        "tool_name": "rx",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RX rotation"
      },
      {
        "tool_name": "ry",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RY rotation"
      },
      {
        "tool_name": "rz",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RZ rotation"
      },
      {
        "tool_name": "cnot",
        "args": [
          "control",
          "target"
        ],
        "doc": "Apply CNOT gate"
      },
      {
        "tool_name": "cz",
        "args": [
          "control",
          "target"
        ],
        "doc": "Apply CZ gate"
      },
      {
        "tool_name": "measure",
        "args": [
          "qubit"
        ],
        "doc": "Measure single qubit"
      },
      {
        "tool_name": "measure_all",
        "args": [],
        "doc": "Measure all qubits"
      },
      {
        "tool_name": "get_probabilities",
        "args": [],
        "doc": "Get probability distribution"
      },
      {
        "tool_name": "expectation_value",
        "args": [
          "observable"
        ],
        "doc": "Compute expectation value of observable.\n\nArgs:\n    observable: Pauli string like 'Z0' or 'X0Y1Z2'\n\nReturns:\n    Expectation value <\u03c8|O|\u03c8>"
      },
      {
        "tool_name": "fidelity",
        "args": [
          "target_state"
        ],
        "doc": "Compute fidelity with target state.\n\nF = |<\u03c8|\u03c6>|\u00b2"
      },
      {
        "tool_name": "chemistry",
        "args": [],
        "doc": "Access quantum chemistry module"
      },
      {
        "tool_name": "materials",
        "args": [],
        "doc": "Access quantum materials module"
      },
      {
        "tool_name": "sensors",
        "args": [],
        "doc": "Access quantum sensors module"
      },
      {
        "tool_name": "reset",
        "args": [],
        "doc": "Reset quantum state to |0\u27e9^n"
      },
      {
        "tool_name": "print_state",
        "args": [
          "top_n"
        ],
        "doc": "Print quantum state"
      },
      {
        "tool_name": "get_backend_info",
        "args": [],
        "doc": "Get information about current backend"
      }
    ]
  },
  {
    "id": "magic_rd_lab.py",
    "name": "Magic Rd",
    "description": "Magic R&D Lab - Advanced Computing as a Service\n\nSimple pricing: Rent our \"magic machine\" by the hour, day, or week.\nPerfect for:\n- Quantum computing research\n- AI/ML model training\n- Complex scientific simulations\n- Data analysis at scale\n- Computational chemistry/physics\n- Custom R&D projects",
    "capabilities": [
      {
        "tool_name": "create_customer",
        "args": [
          "name",
          "company",
          "email"
        ],
        "doc": "Create new customer account."
      },
      {
        "tool_name": "book_session",
        "args": [
          "customer_id",
          "package",
          "project_description"
        ],
        "doc": "Book an R&D Lab session."
      },
      {
        "tool_name": "get_session_status",
        "args": [
          "session_id"
        ],
        "doc": "Get status of an R&D session."
      },
      {
        "tool_name": "get_customer_dashboard",
        "args": [
          "customer_id"
        ],
        "doc": "Get customer dashboard with all sessions and stats."
      },
      {
        "tool_name": "get_pricing_info",
        "args": [],
        "doc": "Get pricing information for marketing."
      },
      {
        "tool_name": "get_business_metrics",
        "args": [],
        "doc": "Get business performance metrics."
      }
    ]
  },
  {
    "id": "magic_rd_lab.py",
    "name": "Magic Rd",
    "description": "Magic R&D Lab - Advanced Computing as a Service\n\nSimple pricing: Rent our \"magic machine\" by the hour, day, or week.\nPerfect for:\n- Quantum computing research\n- AI/ML model training\n- Complex scientific simulations\n- Data analysis at scale\n- Computational chemistry/physics\n- Custom R&D projects",
    "capabilities": [
      {
        "tool_name": "create_customer",
        "args": [
          "name",
          "company",
          "email"
        ],
        "doc": "Create new customer account."
      },
      {
        "tool_name": "book_session",
        "args": [
          "customer_id",
          "package",
          "project_description"
        ],
        "doc": "Book an R&D Lab session."
      },
      {
        "tool_name": "get_session_status",
        "args": [
          "session_id"
        ],
        "doc": "Get status of an R&D session."
      },
      {
        "tool_name": "get_customer_dashboard",
        "args": [
          "customer_id"
        ],
        "doc": "Get customer dashboard with all sessions and stats."
      },
      {
        "tool_name": "get_pricing_info",
        "args": [],
        "doc": "Get pricing information for marketing."
      },
      {
        "tool_name": "get_business_metrics",
        "args": [],
        "doc": "Get business performance metrics."
      }
    ]
  },
  {
    "id": "nuclear_lab.py",
    "name": "Nuclear",
    "description": "Production-ready nuclear physics simulation and analysis",
    "capabilities": [
      {
        "tool_name": "radioactive_decay",
        "args": [
          "isotope",
          "initial_activity_Bq",
          "time_array_seconds"
        ],
        "doc": "Model radioactive decay using exponential decay law\nN(t) = N0 * exp(-\u03bbt), where \u03bb = ln(2)/T_half\n\nArgs:\n    isotope: Isotope name (e.g., 'U-238', 'C-14')\n    initial_activity_Bq: Initial activity in Becquerels\n    time_array_seconds: Time points for calculation\n\nReturns:\n    Dictionary with activity, nuclei count, and energy release"
      },
      {
        "tool_name": "fusion_reaction_rate",
        "args": [
          "reaction",
          "temperature_keV",
          "density_m3"
        ],
        "doc": "Calculate fusion reaction rate using Maxwellian-averaged cross-section\nRate = n1 * n2 * <\u03c3v> where <\u03c3v> is reactivity\n\nArgs:\n    reaction: Reaction name (e.g., 'D-T', 'D-D_branch1')\n    temperature_keV: Plasma temperature in keV\n    density_m3: Number density (particles/m\u00b3)\n\nReturns:\n    Dictionary with reaction rate and power output"
      },
      {
        "tool_name": "fusion_triple_product",
        "args": [
          "temperature_keV",
          "density_m3",
          "confinement_time_s"
        ],
        "doc": "Calculate fusion triple product (nT\u03c4) and assess ignition condition\nIgnition requires nT\u03c4 > 5\u00d710\u00b2\u00b9 keV\u00b7s/m\u00b3\n\nArgs:\n    temperature_keV: Plasma temperature\n    density_m3: Number density\n    confinement_time_s: Energy confinement time\n\nReturns:\n    Dictionary with triple product and ignition assessment"
      },
      {
        "tool_name": "radiation_attenuation",
        "args": [
          "radiation_type",
          "initial_intensity",
          "material",
          "thickness_cm"
        ],
        "doc": "Calculate radiation attenuation through shielding material\nUses exponential attenuation: I = I0 * exp(-\u03bcx)\n\nArgs:\n    radiation_type: 'gamma', 'beta', 'alpha', 'neutron'\n    initial_intensity: Initial intensity (arbitrary units)\n    material: 'lead', 'concrete', 'water', 'aluminum', 'steel'\n    thickness_cm: Shield thickness in cm\n\nReturns:\n    Dictionary with transmitted intensity and attenuation"
      },
      {
        "tool_name": "fission_chain_reaction",
        "args": [
          "initial_neutrons",
          "k_effective",
          "generation_time_s",
          "num_generations"
        ],
        "doc": "Model nuclear fission chain reaction\nn(t) = n0 * k^t for discrete generations\n\nArgs:\n    initial_neutrons: Initial neutron population\n    k_effective: Effective multiplication factor\n    generation_time_s: Time between generations\n    num_generations: Number of generations to simulate\n\nReturns:\n    Dictionary with neutron population evolution"
      },
      {
        "tool_name": "mass_energy_equivalence",
        "args": [
          "mass_kg",
          "energy_J"
        ],
        "doc": "Convert between mass and energy using E=mc\u00b2\n\nArgs:\n    mass_kg: Mass in kilograms (provide either mass or energy)\n    energy_J: Energy in Joules\n\nReturns:\n    Dictionary with conversions"
      },
      {
        "tool_name": "run_diagnostics",
        "args": [],
        "doc": "Run comprehensive nuclear physics diagnostics"
      }
    ]
  },
  {
    "id": "genomics_lab.py",
    "name": "Genomics",
    "description": "Production genomics laboratory with validated scientific algorithms",
    "capabilities": [
      {
        "tool_name": "generate_random_sequence",
        "args": [
          "length",
          "gc_content"
        ],
        "doc": "Generate random DNA sequence with specified GC content\n\nArgs:\n    length: Sequence length in base pairs\n    gc_content: Target GC content (0-1)\n\nReturns:\n    DNA sequence string"
      },
      {
        "tool_name": "sequence_dna",
        "args": [
          "sequence",
          "coverage"
        ],
        "doc": "Simulate DNA sequencing with realistic error rates\n\nArgs:\n    sequence: Input DNA sequence\n    coverage: Sequencing coverage depth\n\nReturns:\n    Sequencing results with quality scores"
      },
      {
        "tool_name": "analyze_gene_expression",
        "args": [
          "gene_name",
          "tissue"
        ],
        "doc": "Analyze gene expression levels using GTEx-like parameters\n\nArgs:\n    gene_name: Gene identifier\n    tissue: Tissue type\n\nReturns:\n    Expression analysis results"
      },
      {
        "tool_name": "design_crispr_guide",
        "args": [
          "target_sequence",
          "position"
        ],
        "doc": "Design CRISPR-Cas9 guide RNA with on-target scoring\nBased on Doench et al. 2016 algorithm\n\nArgs:\n    target_sequence: Target DNA sequence\n    position: Position in sequence to target\n\nReturns:\n    CRISPR target information"
      },
      {
        "tool_name": "predict_mutation_effect",
        "args": [
          "original_seq",
          "position",
          "mutated_base"
        ],
        "doc": "Predict mutation pathogenicity using CADD-like scoring\n\nArgs:\n    original_seq: Original DNA sequence\n    position: Mutation position\n    mutated_base: New base\n\nReturns:\n    Mutation object with pathogenicity prediction"
      },
      {
        "tool_name": "simulate_mutation_accumulation",
        "args": [
          "sequence",
          "generations"
        ],
        "doc": "Simulate mutation accumulation over generations\n\nArgs:\n    sequence: Initial DNA sequence\n    generations: Number of generations\n\nReturns:\n    List of accumulated mutations"
      },
      {
        "tool_name": "rna_sequencing",
        "args": [
          "gene_name",
          "tissue"
        ],
        "doc": "Simulate RNA-Seq experiment\n\nArgs:\n    gene_name: Gene to sequence\n    tissue: Tissue type\n\nReturns:\n    RNA-Seq results"
      }
    ]
  },
  {
    "id": "astrobiology_lab.py",
    "name": "Astrobiology",
    "description": "Production-ready astrobiology simulation and analysis",
    "capabilities": [
      {
        "tool_name": "habitable_zone",
        "args": [
          "stellar_luminosity",
          "stellar_temperature"
        ],
        "doc": "Calculate habitable zone boundaries for a star\nUses energy balance models (Kopparapu et al. 2013)\n\nArgs:\n    stellar_luminosity: Star luminosity (solar units)\n    stellar_temperature: Star effective temperature (K)\n\nReturns:\n    Dictionary with inner and outer HZ boundaries"
      },
      {
        "tool_name": "planetary_habitability_index",
        "args": [
          "surface_temp_K",
          "atmosphere_present",
          "liquid_water",
          "energy_source",
          "organic_compounds",
          "stellar_activity"
        ],
        "doc": "Calculate planetary habitability index (0-1 scale)\nBased on multiple habitability factors\n\nArgs:\n    surface_temp_K: Surface temperature\n    atmosphere_present: Has substantial atmosphere\n    liquid_water: Has liquid water\n    energy_source: Has chemical or radiative energy source\n    organic_compounds: Has organic chemistry\n    stellar_activity: Stellar activity level (1.0 = solar-like)\n\nReturns:\n    Dictionary with habitability score and factors"
      },
      {
        "tool_name": "biosignature_detection",
        "args": [
          "atmospheric_composition",
          "spectral_snr"
        ],
        "doc": "Assess biosignature detectability in exoplanet atmosphere\nBased on spectroscopic observability\n\nArgs:\n    atmospheric_composition: Gas mixing ratios (ppm)\n    spectral_snr: Signal-to-noise ratio of spectrum\n\nReturns:\n    Dictionary with biosignature assessment"
      },
      {
        "tool_name": "drake_equation",
        "args": [
          "custom_params"
        ],
        "doc": "Calculate Drake equation estimate for communicating civilizations\nN = R* \u00d7 fp \u00d7 ne \u00d7 fl \u00d7 fi \u00d7 fc \u00d7 L\n\nArgs:\n    custom_params: Optional custom parameter values\n\nReturns:\n    Dictionary with Drake equation results"
      },
      {
        "tool_name": "extremophile_survival",
        "args": [
          "temperature_K",
          "pH",
          "salinity_percent",
          "pressure_atm",
          "radiation_Gy_yr"
        ],
        "doc": "Model extremophile organism survival under extreme conditions\nBased on known extremophile tolerance ranges\n\nArgs:\n    temperature_K: Environmental temperature\n    pH: Acidity/alkalinity\n    salinity_percent: Salt concentration\n    pressure_atm: Pressure in atmospheres\n    radiation_Gy_yr: Ionizing radiation dose per year\n\nReturns:\n    Dictionary with survival probability and tolerant organisms"
      },
      {
        "tool_name": "prebiotic_chemistry_yield",
        "args": [
          "energy_source",
          "atmosphere_type",
          "temperature_K",
          "time_years"
        ],
        "doc": "Estimate prebiotic organic compound synthesis yield\nBased on Miller-Urey and related experiments\n\nArgs:\n    energy_source: 'lightning', 'UV', 'hydrothermal', 'cosmic_rays'\n    atmosphere_type: 'reducing', 'neutral', 'oxidizing'\n    temperature_K: Reaction temperature\n    time_years: Reaction timescale\n\nReturns:\n    Dictionary with yield estimates and complexity"
      },
      {
        "tool_name": "run_diagnostics",
        "args": [],
        "doc": "Run comprehensive astrobiology diagnostics"
      }
    ]
  },
  {
    "id": "chemistry_lab.py",
    "name": "Chemistry",
    "description": "Unified chemistry laboratory interface.\n\nProvides access to:\n1. Molecular Dynamics (100k atoms @ 1fs)\n2. Reaction Simulation (TST, NEB, catalysis)\n3. Synthesis Planning (retrosynthesis, optimization)\n4. Spectroscopy Prediction (NMR, IR, UV-Vis, MS, XRD)\n5. Solvation Models (PCM, COSMO, SMD, pH effects)\n6. Quantum Chemistry (DFT, HF, MP2, CCSD(T))\n\nTarget accuracy: <5% error on reaction energetics, <10% on spectroscopy",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a chemistry experiment."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Returns a summary of the lab's configuration and capabilities."
      },
      {
        "tool_name": "calculate_dissolution_enthalpy",
        "args": [
          "salt",
          "solvent",
          "temperature_K"
        ],
        "doc": "Compute the dissolution enthalpy for an ionic solid using the Born-Haber cycle.\n\nArgs:\n    salt: Salt formula (e.g., \"NaCl\")\n    solvent: Solvent identifier\n    temperature_K: Temperature in Kelvin\n\nReturns:\n    Dictionary with \u0394H (kJ/mol) and source metadata."
      },
      {
        "tool_name": "create_md_simulation",
        "args": [
          "atoms",
          "box_size",
          "force_field",
          "ensemble",
          "timestep"
        ],
        "doc": "Create molecular dynamics simulation."
      },
      {
        "tool_name": "run_md_simulation",
        "args": [
          "n_steps",
          "temperature",
          "output_interval"
        ],
        "doc": "Run MD simulation."
      },
      {
        "tool_name": "simulate_reaction",
        "args": [
          "reactants",
          "products",
          "conditions",
          "reaction_name",
          "materials_lab",
          "environment_simulator"
        ],
        "doc": "Simulate chemical reaction and predict kinetics."
      },
      {
        "tool_name": "get_reaction_metadata",
        "args": [
          "reaction_name"
        ],
        "doc": "Expose reaction metadata summary."
      },
      {
        "tool_name": "plan_synthesis",
        "args": [
          "target",
          "max_depth"
        ],
        "doc": "Plan synthesis route to target compound."
      },
      {
        "tool_name": "analyze_synthesis_safety",
        "args": [
          "route"
        ],
        "doc": "Analyze safety of synthesis route."
      },
      {
        "tool_name": "predict_nmr",
        "args": [
          "molecule",
          "nucleus"
        ],
        "doc": "Predict NMR spectrum."
      },
      {
        "tool_name": "predict_ir",
        "args": [
          "molecule"
        ],
        "doc": "Predict IR spectrum."
      },
      {
        "tool_name": "predict_uv_vis",
        "args": [
          "molecule"
        ],
        "doc": "Predict UV-Vis spectrum."
      },
      {
        "tool_name": "predict_mass_spectrum",
        "args": [
          "molecule"
        ],
        "doc": "Predict mass spectrum."
      },
      {
        "tool_name": "calculate_solvation_energy",
        "args": [
          "solute",
          "solvent_name",
          "model"
        ],
        "doc": "Calculate solvation free energy."
      },
      {
        "tool_name": "predict_logP",
        "args": [
          "solute"
        ],
        "doc": "Predict octanol-water partition coefficient."
      },
      {
        "tool_name": "calculate_pH_effect",
        "args": [
          "solute",
          "pH",
          "pKa"
        ],
        "doc": "Calculate pH effects on ionization."
      },
      {
        "tool_name": "quantum_calculation",
        "args": [
          "molecule",
          "method",
          "basis_set"
        ],
        "doc": "Perform quantum chemistry calculation."
      },
      {
        "tool_name": "optimize_geometry",
        "args": [
          "molecule",
          "method"
        ],
        "doc": "Optimize molecular geometry."
      },
      {
        "tool_name": "calculate_vibrational_frequencies",
        "args": [
          "molecule"
        ],
        "doc": "Calculate vibrational frequencies."
      },
      {
        "tool_name": "complete_molecule_characterization",
        "args": [
          "molecule"
        ],
        "doc": "Complete characterization of molecule:\n- Spectroscopy (NMR, IR, UV-Vis, MS)\n- Solvation (logP, solubility)\n- Quantum properties (HOMO-LUMO, dipole)"
      },
      {
        "tool_name": "reaction_optimization_workflow",
        "args": [
          "reactants",
          "products",
          "catalysts"
        ],
        "doc": "Optimize reaction conditions:\n- Find optimal catalyst\n- Determine best temperature/pressure\n- Predict yields"
      }
    ]
  },
  {
    "id": "neuroscience_lab.py",
    "name": "Neuroscience",
    "description": "Production neuroscience laboratory with validated models",
    "capabilities": [
      {
        "tool_name": "create_izhikevich_neuron",
        "args": [
          "neuron_type"
        ],
        "doc": "Create Izhikevich neuron model parameters\nIzhikevich (2003) - efficient spiking neuron model\n\nArgs:\n    neuron_type: Type of neuron\n\nReturns:\n    Dictionary of model parameters"
      },
      {
        "tool_name": "simulate_neuron_spike",
        "args": [
          "params",
          "input_current",
          "duration_ms"
        ],
        "doc": "Simulate single neuron using Izhikevich model\n\nArgs:\n    params: Neuron parameters\n    input_current: Input current (pA)\n    duration_ms: Simulation duration\n\nReturns:\n    Tuple of (time_array, voltage_array)"
      },
      {
        "tool_name": "simulate_neural_network",
        "args": [
          "n_neurons",
          "connectivity",
          "duration_ms"
        ],
        "doc": "Simulate network of interconnected neurons\n\nArgs:\n    n_neurons: Number of neurons\n    connectivity: Connection probability (0-1)\n    duration_ms: Simulation duration\n\nReturns:\n    Network activity data"
      },
      {
        "tool_name": "simulate_neurotransmitter_dynamics",
        "args": [
          "nt_type",
          "stimulation_times",
          "duration_ms"
        ],
        "doc": "Simulate neurotransmitter release and clearance\n\nArgs:\n    nt_type: Neurotransmitter type\n    stimulation_times: Times of neural firing (ms)\n    duration_ms: Simulation duration\n\nReturns:\n    Neurotransmitter concentration over time"
      },
      {
        "tool_name": "simulate_eeg_signal",
        "args": [
          "brain_state",
          "duration_s",
          "sampling_rate"
        ],
        "doc": "Simulate EEG signal based on brain state\n\nArgs:\n    brain_state: 'awake', 'drowsy', 'asleep', 'deep_sleep'\n    duration_s: Duration in seconds\n    sampling_rate: Sampling rate in Hz\n\nReturns:\n    Brain activity with EEG signal"
      },
      {
        "tool_name": "calculate_consciousness_metric",
        "args": [
          "neural_activity"
        ],
        "doc": "Calculate consciousness metric using simplified Integrated Information Theory (IIT)\n\nBased on Tononi et al. IIT - Phi (\u03a6) measures integrated information\n\nArgs:\n    neural_activity: Neural activity matrix (neurons x time)\n\nReturns:\n    Phi value (0-1 scale)"
      }
    ]
  },
  {
    "id": "cognitive_lab.py",
    "name": "Cognitive",
    "description": "Production-ready cognitive science simulation and analysis",
    "capabilities": [
      {
        "tool_name": "working_memory_model",
        "args": [
          "num_items",
          "chunking_strategy",
          "chunk_size"
        ],
        "doc": "Model working memory capacity and performance\nBased on Miller's Law and Baddeley's working memory model\n\nArgs:\n    num_items: Number of items to remember\n    chunking_strategy: Whether items are chunked\n    chunk_size: Size of each chunk\n\nReturns:\n    Dictionary with recall probability and capacity analysis"
      },
      {
        "tool_name": "forgetting_curve",
        "args": [
          "initial_strength",
          "time_hours",
          "forgetting_rate",
          "rehearsal_times"
        ],
        "doc": "Model memory decay using Ebbinghaus forgetting curve\nR(t) = R0 * exp(-bt) where b is forgetting rate\n\nArgs:\n    initial_strength: Initial memory strength (0-1)\n    time_hours: Time array in hours\n    forgetting_rate: 'rapid', 'moderate', 'slow'\n    rehearsal_times: Optional times (hours) of memory rehearsal\n\nReturns:\n    Dictionary with retention over time"
      },
      {
        "tool_name": "reinforcement_learning",
        "args": [
          "action_history",
          "reward_history",
          "learning_rate",
          "discount_factor"
        ],
        "doc": "Model reinforcement learning using Q-learning algorithm\nQ(s,a) \u2190 Q(s,a) + \u03b1[R + \u03b3 max Q(s',a') - Q(s,a)]\n\nArgs:\n    action_history: Sequence of actions taken\n    reward_history: Rewards received for each action\n    learning_rate: Learning rate \u03b1 (0-1)\n    discount_factor: Future reward discount \u03b3 (0-1)\n\nReturns:\n    Dictionary with learned Q-values and policy"
      },
      {
        "tool_name": "prospect_theory_value",
        "args": [
          "outcome",
          "reference_point"
        ],
        "doc": "Calculate subjective value using Prospect Theory\nv(x) = x^\u03b1 for gains, -\u03bb(-x)^\u03b2 for losses\n\nArgs:\n    outcome: Objective outcome value\n    reference_point: Reference point for gain/loss framing\n\nReturns:\n    Dictionary with subjective value and framing effects"
      },
      {
        "tool_name": "decision_making_model",
        "args": [
          "options",
          "decision_mode"
        ],
        "doc": "Model decision-making under uncertainty\nSupports rational (expected utility) and heuristic modes\n\nArgs:\n    options: List of dicts with 'value' and 'probability'\n    decision_mode: 'rational', 'satisficing', 'heuristic'\n\nReturns:\n    Dictionary with decision and reasoning"
      },
      {
        "tool_name": "cognitive_load_model",
        "args": [
          "task_complexity",
          "intrinsic_load",
          "extraneous_load",
          "germane_load"
        ],
        "doc": "Model cognitive load using Sweller's Cognitive Load Theory\nTotal load = intrinsic + extraneous + germane\n\nArgs:\n    task_complexity: Base task complexity (0-1)\n    intrinsic_load: Load from task inherent complexity (0-1)\n    extraneous_load: Load from poor design (0-1)\n    germane_load: Load from schema construction (0-1)\n\nReturns:\n    Dictionary with cognitive load analysis"
      },
      {
        "tool_name": "attention_model",
        "args": [
          "stimulus_intensity",
          "stimulus_novelty",
          "current_focus",
          "fatigue_level"
        ],
        "doc": "Model selective attention based on stimulus properties\nCombines bottom-up (stimulus-driven) and top-down (goal-driven) attention\n\nArgs:\n    stimulus_intensity: Physical intensity (0-1)\n    stimulus_novelty: Novelty/unexpectedness (0-1)\n    current_focus: Current task focus strength (0-1)\n    fatigue_level: Mental fatigue (0-1, higher = more tired)\n\nReturns:\n    Dictionary with attention allocation"
      },
      {
        "tool_name": "behavioral_prediction",
        "args": [
          "past_behavior",
          "context_similarity",
          "habit_strength"
        ],
        "doc": "Predict future behavior based on past patterns\nUses habit formation and context-dependent retrieval\n\nArgs:\n    past_behavior: Binary sequence (0=no action, 1=action)\n    context_similarity: Similarity to past contexts (0-1)\n    habit_strength: Strength of habitual response (0-1)\n\nReturns:\n    Dictionary with prediction and confidence"
      },
      {
        "tool_name": "run_diagnostics",
        "args": [],
        "doc": "Run comprehensive cognitive science diagnostics"
      }
    ]
  },
  {
    "id": "base_lab.py",
    "name": "Base",
    "description": "Abstract base class for all laboratories in QuLabInfinite.\n\nThis class defines the common interface that all specialized labs\n(e.g., MaterialsLab, ChemistryLaboratory, QuantumLabSimulator) must implement.\nThis ensures a consistent API for initialization, configuration,\nand execution of simulations across the platform.",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a specific experiment based on the provided specification.\n\nArgs:\n    experiment_spec: A dictionary defining the experiment to be run,\n                     including parameters and desired outputs.\n\nReturns:\n    A dictionary containing the results of the experiment."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get the current status of the laboratory.\n\nReturns:\n    A dictionary containing status information, such as backend state,\n    loaded data, and available capabilities."
      },
      {
        "tool_name": "get_capabilities",
        "args": [],
        "doc": "Get the capabilities of the laboratory.\n\nReturns:\n    A dictionary describing the capabilities of the lab."
      }
    ]
  },
  {
    "id": "materials_lab.py",
    "name": "Materials",
    "description": "Main Materials Science Laboratory API\n\nProvides unified interface for:\n- Material database access (1000+ materials)\n- Material testing simulations\n- Material design and optimization\n- Property prediction with ML",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a materials science experiment.\n\nArgs:\n    experiment_spec: Dictionary specifying the experiment.\n        Required keys:\n        - 'experiment_type': str (e.g., 'tensile', 'compression', 'hardness')\n        - 'material_name': str\n        Other keys are passed as kwargs to the respective test method.\n\nReturns:\n    A dictionary containing the experiment results."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get the current status of the Materials Lab.\nFor MaterialsLab, this returns the database statistics."
      },
      {
        "tool_name": "validate_material_properties",
        "args": [
          "material_name",
          "properties"
        ],
        "doc": "Validate a material's tabulated properties against reference data.\n\nArgs:\n    material_name: Name used in the materials database.\n    properties: Optional iterable of property names to validate. If\n        omitted, all mapped properties for the material are checked.\n    raise_on_missing: When True, raise a ValueError if the material or\n        requested property does not have a configured reference datum.\n\nReturns:\n    Mapping of property name to ValidationResult."
      },
      {
        "tool_name": "validate_accuracy_suite",
        "args": [],
        "doc": "Run the configured accuracy suite for all mapped materials.\n\nReturns:\n    Nested mapping of material -> property -> ValidationResult."
      },
      {
        "tool_name": "get_material",
        "args": [
          "name"
        ],
        "doc": "Get material by name"
      },
      {
        "tool_name": "search_materials",
        "args": [],
        "doc": "Search materials by criteria"
      },
      {
        "tool_name": "list_categories",
        "args": [],
        "doc": "List all material categories"
      },
      {
        "tool_name": "list_materials",
        "args": [
          "category"
        ],
        "doc": "List material names, optionally filtered by category."
      },
      {
        "tool_name": "get_statistics",
        "args": [],
        "doc": "Get database statistics"
      },
      {
        "tool_name": "get_material_profile",
        "args": [
          "material_name"
        ],
        "doc": "Generate a detailed property profile with curves and metadata."
      },
      {
        "tool_name": "get_material_safety",
        "args": [
          "material_name"
        ],
        "doc": "Return MSDS-style safety information if available."
      },
      {
        "tool_name": "register_calibration",
        "args": [
          "material_name",
          "test_type",
          "property_name",
          "reference_value",
          "measured_value"
        ],
        "doc": "Register calibration measurement."
      },
      {
        "tool_name": "get_calibration_summary",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "simulate_ice_growth",
        "args": [
          "material_name",
          "temperature_k",
          "relative_humidity",
          "duration_hours"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "run_batch_experiments",
        "args": [
          "batch_specs"
        ],
        "doc": "Run multiple experiments and return serialisable summaries."
      },
      {
        "tool_name": "tensile_test",
        "args": [
          "material_name"
        ],
        "doc": "Run tensile test"
      },
      {
        "tool_name": "compression_test",
        "args": [
          "material_name"
        ],
        "doc": "Run compression test"
      },
      {
        "tool_name": "fatigue_test",
        "args": [
          "material_name"
        ],
        "doc": "Run fatigue test"
      },
      {
        "tool_name": "impact_test",
        "args": [
          "material_name"
        ],
        "doc": "Run impact test"
      },
      {
        "tool_name": "hardness_test",
        "args": [
          "material_name"
        ],
        "doc": "Run hardness test"
      },
      {
        "tool_name": "thermal_test",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "Run thermal test"
      },
      {
        "tool_name": "corrosion_test",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "Run corrosion test"
      },
      {
        "tool_name": "environmental_test",
        "args": [
          "material_name"
        ],
        "doc": "Run environmental test"
      },
      {
        "tool_name": "optimize_alloy",
        "args": [
          "base_elements",
          "target_properties"
        ],
        "doc": "Optimize alloy composition"
      },
      {
        "tool_name": "design_composite",
        "args": [
          "fiber_name",
          "matrix_name"
        ],
        "doc": "Design composite material"
      },
      {
        "tool_name": "add_nanoparticles",
        "args": [
          "base_material_name"
        ],
        "doc": "Add nanoparticles to material"
      },
      {
        "tool_name": "apply_coating",
        "args": [
          "base_material_name"
        ],
        "doc": "Apply surface coating"
      },
      {
        "tool_name": "design_lattice",
        "args": [
          "base_material_name"
        ],
        "doc": "Design lattice structure for AM"
      },
      {
        "tool_name": "predict_from_composition",
        "args": [
          "composition",
          "properties"
        ],
        "doc": "Predict properties from composition"
      },
      {
        "tool_name": "predict_from_structure",
        "args": [
          "crystal_structure",
          "bonding_type",
          "properties"
        ],
        "doc": "Predict properties from structure"
      },
      {
        "tool_name": "predict_by_similarity",
        "args": [
          "reference_material_name",
          "property_name"
        ],
        "doc": "Predict property by similarity"
      },
      {
        "tool_name": "compare_materials",
        "args": [
          "material_names",
          "properties"
        ],
        "doc": "Compare multiple materials"
      },
      {
        "tool_name": "find_best_material",
        "args": [
          "category",
          "optimize_for",
          "constraints"
        ],
        "doc": "Find best material for application\n\nArgs:\n    category: Material category to search\n    optimize_for: Property to maximize\n    constraints: Dict of property constraints (min/max values)"
      }
    ]
  },
  {
    "id": "quantum_lab.py",
    "name": "Quantum",
    "description": "Unified quantum laboratory simulator.\n\nFeatures:\n- 30-qubit exact statevector simulation\n- Tensor network approximation for >30 qubits\n- Quantum chemistry integration\n- Materials science quantum calculations\n- Quantum sensor modeling\n- Cognition-inspired algorithms\n\nIntegration:\n- Wraps existing CircuitSimulator (30-qubit exact)\n- Wraps QuantumCognition (quantum-inspired)\n- Extends with chemistry, materials, sensors\n\nECH0 Usage Examples:\n```python\n# Basic circuit simulation\nlab = QuantumLabSimulator(num_qubits=5)\nlab.h(0)  # Hadamard on qubit 0\nlab.cnot(0, 1)  # Entangle qubits\nresults = lab.measure_all()\n\n# Chemistry calculation\nfrom quantum_chemistry import Molecule\nh2 = Molecule.hydrogen_molecule(bond_length=0.74)\nenergy = lab.chemistry.compute_ground_state_energy(h2)\n\n# Materials property\nenergy_gap = lab.materials.compute_band_gap(\"silicon\")\n\n# Quantum sensing\nsensitivity = lab.sensors.magnetometry_sensitivity(num_qubits=10)\n```",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a quantum experiment.\n\nExample spec:\n{\n    \"experiment_type\": \"bell_pair\",\n}\n{\n    \"experiment_type\": \"ghz_state\",\n    \"num_qubits\": 4\n}\n{\n    \"experiment_type\": \"custom_circuit\",\n    \"operations\": [\n        {\"gate\": \"h\", \"qubit\": 0},\n        {\"gate\": \"cnot\", \"control\": 0, \"target\": 1}\n    ]\n}"
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get information about current backend and state."
      },
      {
        "tool_name": "h",
        "args": [
          "qubit"
        ],
        "doc": "Apply Hadamard gate"
      },
      {
        "tool_name": "x",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-X gate"
      },
      {
        "tool_name": "y",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-Y gate"
      },
      {
        "tool_name": "z",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-Z gate"
      },
      {
        "tool_name": "rx",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RX rotation"
      },
      {
        "tool_name": "ry",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RY rotation"
      },
      {
        "tool_name": "rz",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RZ rotation"
      },
      {
        "tool_name": "cnot",
        "args": [
          "control",
          "target"
        ],
        "doc": "Apply CNOT gate"
      },
      {
        "tool_name": "cz",
        "args": [
          "control",
          "target"
        ],
        "doc": "Apply CZ gate"
      },
      {
        "tool_name": "measure",
        "args": [
          "qubit"
        ],
        "doc": "Measure single qubit"
      },
      {
        "tool_name": "measure_all",
        "args": [],
        "doc": "Measure all qubits"
      },
      {
        "tool_name": "get_probabilities",
        "args": [],
        "doc": "Get probability distribution"
      },
      {
        "tool_name": "expectation_value",
        "args": [
          "observable"
        ],
        "doc": "Compute expectation value of observable.\n\nArgs:\n    observable: Pauli string like 'Z0' or 'X0Y1Z2'\n\nReturns:\n    Expectation value <\u03c8|O|\u03c8>"
      },
      {
        "tool_name": "fidelity",
        "args": [
          "target_state"
        ],
        "doc": "Compute fidelity with target state.\n\nF = |<\u03c8|\u03c6>|\u00b2"
      },
      {
        "tool_name": "chemistry",
        "args": [],
        "doc": "Access quantum chemistry module"
      },
      {
        "tool_name": "materials",
        "args": [],
        "doc": "Access quantum materials module"
      },
      {
        "tool_name": "sensors",
        "args": [],
        "doc": "Access quantum sensors module"
      },
      {
        "tool_name": "reset",
        "args": [],
        "doc": "Reset quantum state to |0\u27e9^n"
      },
      {
        "tool_name": "print_state",
        "args": [
          "top_n"
        ],
        "doc": "Print quantum state"
      },
      {
        "tool_name": "get_backend_info",
        "args": [],
        "doc": "Get information about current backend"
      }
    ]
  },
  {
    "id": "chemistry_lab.py",
    "name": "Chemistry",
    "description": "Unified chemistry laboratory interface.\n\nProvides access to:\n1. Molecular Dynamics (100k atoms @ 1fs)\n2. Reaction Simulation (TST, NEB, catalysis)\n3. Synthesis Planning (retrosynthesis, optimization)\n4. Spectroscopy Prediction (NMR, IR, UV-Vis, MS, XRD)\n5. Solvation Models (PCM, COSMO, SMD, pH effects)\n6. Quantum Chemistry (DFT, HF, MP2, CCSD(T))\n\nTarget accuracy: <5% error on reaction energetics, <10% on spectroscopy",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a chemistry experiment."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Returns a summary of the lab's configuration and capabilities."
      },
      {
        "tool_name": "calculate_dissolution_enthalpy",
        "args": [
          "salt",
          "solvent",
          "temperature_K"
        ],
        "doc": "Compute the dissolution enthalpy for an ionic solid using the Born-Haber cycle.\n\nArgs:\n    salt: Salt formula (e.g., \"NaCl\")\n    solvent: Solvent identifier\n    temperature_K: Temperature in Kelvin\n\nReturns:\n    Dictionary with \u0394H (kJ/mol) and source metadata."
      },
      {
        "tool_name": "create_md_simulation",
        "args": [
          "atoms",
          "box_size",
          "force_field",
          "ensemble",
          "timestep"
        ],
        "doc": "Create molecular dynamics simulation."
      },
      {
        "tool_name": "run_md_simulation",
        "args": [
          "n_steps",
          "temperature",
          "output_interval"
        ],
        "doc": "Run MD simulation."
      },
      {
        "tool_name": "simulate_reaction",
        "args": [
          "reactants",
          "products",
          "conditions",
          "reaction_name",
          "materials_lab",
          "environment_simulator"
        ],
        "doc": "Simulate chemical reaction and predict kinetics."
      },
      {
        "tool_name": "get_reaction_metadata",
        "args": [
          "reaction_name"
        ],
        "doc": "Expose reaction metadata summary."
      },
      {
        "tool_name": "plan_synthesis",
        "args": [
          "target",
          "max_depth"
        ],
        "doc": "Plan synthesis route to target compound."
      },
      {
        "tool_name": "analyze_synthesis_safety",
        "args": [
          "route"
        ],
        "doc": "Analyze safety of synthesis route."
      },
      {
        "tool_name": "predict_nmr",
        "args": [
          "molecule",
          "nucleus"
        ],
        "doc": "Predict NMR spectrum."
      },
      {
        "tool_name": "predict_ir",
        "args": [
          "molecule"
        ],
        "doc": "Predict IR spectrum."
      },
      {
        "tool_name": "predict_uv_vis",
        "args": [
          "molecule"
        ],
        "doc": "Predict UV-Vis spectrum."
      },
      {
        "tool_name": "predict_mass_spectrum",
        "args": [
          "molecule"
        ],
        "doc": "Predict mass spectrum."
      },
      {
        "tool_name": "calculate_solvation_energy",
        "args": [
          "solute",
          "solvent_name",
          "model"
        ],
        "doc": "Calculate solvation free energy."
      },
      {
        "tool_name": "predict_logP",
        "args": [
          "solute"
        ],
        "doc": "Predict octanol-water partition coefficient."
      },
      {
        "tool_name": "calculate_pH_effect",
        "args": [
          "solute",
          "pH",
          "pKa"
        ],
        "doc": "Calculate pH effects on ionization."
      },
      {
        "tool_name": "quantum_calculation",
        "args": [
          "molecule",
          "method",
          "basis_set"
        ],
        "doc": "Perform quantum chemistry calculation."
      },
      {
        "tool_name": "optimize_geometry",
        "args": [
          "molecule",
          "method"
        ],
        "doc": "Optimize molecular geometry."
      },
      {
        "tool_name": "calculate_vibrational_frequencies",
        "args": [
          "molecule"
        ],
        "doc": "Calculate vibrational frequencies."
      },
      {
        "tool_name": "complete_molecule_characterization",
        "args": [
          "molecule"
        ],
        "doc": "Complete characterization of molecule:\n- Spectroscopy (NMR, IR, UV-Vis, MS)\n- Solvation (logP, solubility)\n- Quantum properties (HOMO-LUMO, dipole)"
      },
      {
        "tool_name": "reaction_optimization_workflow",
        "args": [
          "reactants",
          "products",
          "catalysts"
        ],
        "doc": "Optimize reaction conditions:\n- Find optimal catalyst\n- Determine best temperature/pressure\n- Predict yields"
      }
    ]
  },
  {
    "id": "chronology_lab.py",
    "name": "Chronology",
    "description": "Lab Node for Temporal Physics and Chronology Protection.",
    "capabilities": [
      {
        "tool_name": "simulate_ctc_formation",
        "args": [
          "acceleration_g",
          "duration_years",
          "distance_ly"
        ],
        "doc": "Simulates the formation of a Closed Timelike Curve (CTC) between two wormhole mouths.\n\nArgs:\n    acceleration_g: Acceleration in Earth gravities (g)\n    duration_years: Duration of acceleration in rocket time (years)\n    distance_ly: Spatial separation between wormhole mouths (light-years)"
      },
      {
        "tool_name": "analyze_paradox_probability",
        "args": [
          "action_type",
          "time_offset_years"
        ],
        "doc": "Analyzes the probability of a timeline-destabilizing paradox based on action magnitude.\n\nArgs:\n    action_type: Type of retrospective interference (\"physical\", \"informational\", \"none\")\n    time_offset_years: Number of years into the past target"
      }
    ]
  },
  {
    "id": "universal_lab.py",
    "name": "Universal",
    "description": "",
    "capabilities": [
      {
        "tool_name": "get_lab_info",
        "args": [
          "lab_id"
        ],
        "doc": "Introspects a lab file to find classes and methods."
      },
      {
        "tool_name": "combine_materials",
        "args": [
          "materials",
          "conditions"
        ],
        "doc": "Simulates the combination of materials under given conditions."
      }
    ]
  },
  {
    "id": "base_lab.py",
    "name": "Base",
    "description": "Abstract base class for all laboratories in QuLabInfinite.\n\nThis class defines the common interface that all specialized labs\n(e.g., MaterialsLab, ChemistryLaboratory, QuantumLabSimulator) must implement.\nThis ensures a consistent API for initialization, configuration,\nand execution of simulations across the platform.",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a specific experiment based on the provided specification.\n\nArgs:\n    experiment_spec: A dictionary defining the experiment to be run,\n                     including parameters and desired outputs.\n\nReturns:\n    A dictionary containing the results of the experiment."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get the current status of the laboratory.\n\nReturns:\n    A dictionary containing status information, such as backend state,\n    loaded data, and available capabilities."
      },
      {
        "tool_name": "get_capabilities",
        "args": [],
        "doc": "Get the capabilities of the laboratory.\n\nReturns:\n    A dictionary describing the capabilities of the lab."
      }
    ]
  },
  {
    "id": "materials_lab.py",
    "name": "Materials",
    "description": "Main Materials Science Laboratory API\n\nProvides unified interface for:\n- Material database access (1000+ materials)\n- Material testing simulations\n- Material design and optimization\n- Property prediction with ML",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a materials science experiment.\n\nArgs:\n    experiment_spec: Dictionary specifying the experiment.\n        Required keys:\n        - 'experiment_type': str (e.g., 'tensile', 'compression', 'hardness')\n        - 'material_name': str\n        Other keys are passed as kwargs to the respective test method.\n\nReturns:\n    A dictionary containing the experiment results."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get the current status of the Materials Lab.\nFor MaterialsLab, this returns the database statistics."
      },
      {
        "tool_name": "validate_material_properties",
        "args": [
          "material_name",
          "properties"
        ],
        "doc": "Validate a material's tabulated properties against reference data.\n\nArgs:\n    material_name: Name used in the materials database.\n    properties: Optional iterable of property names to validate. If\n        omitted, all mapped properties for the material are checked.\n    raise_on_missing: When True, raise a ValueError if the material or\n        requested property does not have a configured reference datum.\n\nReturns:\n    Mapping of property name to ValidationResult."
      },
      {
        "tool_name": "validate_accuracy_suite",
        "args": [],
        "doc": "Run the configured accuracy suite for all mapped materials.\n\nReturns:\n    Nested mapping of material -> property -> ValidationResult."
      },
      {
        "tool_name": "get_material",
        "args": [
          "name"
        ],
        "doc": "Get material by name"
      },
      {
        "tool_name": "search_materials",
        "args": [],
        "doc": "Search materials by criteria"
      },
      {
        "tool_name": "list_categories",
        "args": [],
        "doc": "List all material categories"
      },
      {
        "tool_name": "list_materials",
        "args": [
          "category"
        ],
        "doc": "List material names, optionally filtered by category."
      },
      {
        "tool_name": "get_statistics",
        "args": [],
        "doc": "Get database statistics"
      },
      {
        "tool_name": "get_material_profile",
        "args": [
          "material_name"
        ],
        "doc": "Generate a detailed property profile with curves and metadata."
      },
      {
        "tool_name": "get_material_safety",
        "args": [
          "material_name"
        ],
        "doc": "Return MSDS-style safety information if available."
      },
      {
        "tool_name": "register_calibration",
        "args": [
          "material_name",
          "test_type",
          "property_name",
          "reference_value",
          "measured_value"
        ],
        "doc": "Register calibration measurement."
      },
      {
        "tool_name": "get_calibration_summary",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "simulate_ice_growth",
        "args": [
          "material_name",
          "temperature_k",
          "relative_humidity",
          "duration_hours"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "run_batch_experiments",
        "args": [
          "batch_specs"
        ],
        "doc": "Run multiple experiments and return serialisable summaries."
      },
      {
        "tool_name": "tensile_test",
        "args": [
          "material_name"
        ],
        "doc": "Run tensile test"
      },
      {
        "tool_name": "compression_test",
        "args": [
          "material_name"
        ],
        "doc": "Run compression test"
      },
      {
        "tool_name": "fatigue_test",
        "args": [
          "material_name"
        ],
        "doc": "Run fatigue test"
      },
      {
        "tool_name": "impact_test",
        "args": [
          "material_name"
        ],
        "doc": "Run impact test"
      },
      {
        "tool_name": "hardness_test",
        "args": [
          "material_name"
        ],
        "doc": "Run hardness test"
      },
      {
        "tool_name": "thermal_test",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "Run thermal test"
      },
      {
        "tool_name": "corrosion_test",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "Run corrosion test"
      },
      {
        "tool_name": "environmental_test",
        "args": [
          "material_name"
        ],
        "doc": "Run environmental test"
      },
      {
        "tool_name": "optimize_alloy",
        "args": [
          "base_elements",
          "target_properties"
        ],
        "doc": "Optimize alloy composition"
      },
      {
        "tool_name": "design_composite",
        "args": [
          "fiber_name",
          "matrix_name"
        ],
        "doc": "Design composite material"
      },
      {
        "tool_name": "add_nanoparticles",
        "args": [
          "base_material_name"
        ],
        "doc": "Add nanoparticles to material"
      },
      {
        "tool_name": "apply_coating",
        "args": [
          "base_material_name"
        ],
        "doc": "Apply surface coating"
      },
      {
        "tool_name": "design_lattice",
        "args": [
          "base_material_name"
        ],
        "doc": "Design lattice structure for AM"
      },
      {
        "tool_name": "predict_from_composition",
        "args": [
          "composition",
          "properties"
        ],
        "doc": "Predict properties from composition"
      },
      {
        "tool_name": "predict_from_structure",
        "args": [
          "crystal_structure",
          "bonding_type",
          "properties"
        ],
        "doc": "Predict properties from structure"
      },
      {
        "tool_name": "predict_by_similarity",
        "args": [
          "reference_material_name",
          "property_name"
        ],
        "doc": "Predict property by similarity"
      },
      {
        "tool_name": "compare_materials",
        "args": [
          "material_names",
          "properties"
        ],
        "doc": "Compare multiple materials"
      },
      {
        "tool_name": "find_best_material",
        "args": [
          "category",
          "optimize_for",
          "constraints"
        ],
        "doc": "Find best material for application\n\nArgs:\n    category: Material category to search\n    optimize_for: Property to maximize\n    constraints: Dict of property constraints (min/max values)"
      }
    ]
  },
  {
    "id": "materials_lab.py",
    "name": "Materials",
    "description": "Main Materials Science Laboratory API\n\nProvides unified interface for:\n- Material database access (6.6 million+ materials)\n- Material testing simulations\n- Material design and optimization\n- Property prediction with ML",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a materials science experiment.\n\nArgs:\n    experiment_spec: Dictionary specifying the experiment.\n        Required keys:\n        - 'experiment_type': str (e.g., 'tensile', 'compression', 'hardness')\n        - 'material_name': str\n        Other keys are passed as kwargs to the respective test method.\n\nReturns:\n    A dictionary containing the experiment results."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get the current status of the Materials Lab.\nFor MaterialsLab, this returns the database statistics."
      },
      {
        "tool_name": "validate_material_properties",
        "args": [
          "material_name",
          "properties"
        ],
        "doc": "Validate a material's tabulated properties against reference data.\n\nArgs:\n    material_name: Name used in the materials database.\n    properties: Optional iterable of property names to validate. If\n        omitted, all mapped properties for the material are checked.\n    raise_on_missing: When True, raise a ValueError if the material or\n        requested property does not have a configured reference datum.\n\nReturns:\n    Mapping of property name to ValidationResult."
      },
      {
        "tool_name": "validate_accuracy_suite",
        "args": [],
        "doc": "Run the configured accuracy suite for all mapped materials.\n\nReturns:\n    Nested mapping of material -> property -> ValidationResult."
      },
      {
        "tool_name": "get_material",
        "args": [
          "name"
        ],
        "doc": "Get material by name"
      },
      {
        "tool_name": "search_materials",
        "args": [],
        "doc": "Search materials by criteria"
      },
      {
        "tool_name": "list_categories",
        "args": [],
        "doc": "List all material categories"
      },
      {
        "tool_name": "list_materials",
        "args": [
          "category"
        ],
        "doc": "List material names, optionally filtered by category."
      },
      {
        "tool_name": "get_statistics",
        "args": [],
        "doc": "Get database statistics"
      },
      {
        "tool_name": "get_material_profile",
        "args": [
          "material_name"
        ],
        "doc": "Generate a detailed property profile with curves and metadata."
      },
      {
        "tool_name": "get_material_safety",
        "args": [
          "material_name"
        ],
        "doc": "Return MSDS-style safety information if available."
      },
      {
        "tool_name": "register_calibration",
        "args": [
          "material_name",
          "test_type",
          "property_name",
          "reference_value",
          "measured_value"
        ],
        "doc": "Register calibration measurement."
      },
      {
        "tool_name": "get_calibration_summary",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "simulate_ice_growth",
        "args": [
          "material_name",
          "temperature_k",
          "relative_humidity",
          "duration_hours"
        ],
        "doc": "No description available."
      },
      {
        "tool_name": "run_batch_experiments",
        "args": [
          "batch_specs"
        ],
        "doc": "Run multiple experiments and return serialisable summaries."
      },
      {
        "tool_name": "tensile_test",
        "args": [
          "material_name"
        ],
        "doc": "Run tensile test"
      },
      {
        "tool_name": "compression_test",
        "args": [
          "material_name"
        ],
        "doc": "Run compression test"
      },
      {
        "tool_name": "fatigue_test",
        "args": [
          "material_name"
        ],
        "doc": "Run fatigue test"
      },
      {
        "tool_name": "impact_test",
        "args": [
          "material_name"
        ],
        "doc": "Run impact test"
      },
      {
        "tool_name": "hardness_test",
        "args": [
          "material_name"
        ],
        "doc": "Run hardness test"
      },
      {
        "tool_name": "thermal_test",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "Run thermal test"
      },
      {
        "tool_name": "corrosion_test",
        "args": [
          "material_name",
          "test_type"
        ],
        "doc": "Run corrosion test"
      },
      {
        "tool_name": "environmental_test",
        "args": [
          "material_name"
        ],
        "doc": "Run environmental test"
      },
      {
        "tool_name": "optimize_alloy",
        "args": [
          "base_elements",
          "target_properties"
        ],
        "doc": "Optimize alloy composition"
      },
      {
        "tool_name": "design_composite",
        "args": [
          "fiber_name",
          "matrix_name"
        ],
        "doc": "Design composite material"
      },
      {
        "tool_name": "add_nanoparticles",
        "args": [
          "base_material_name"
        ],
        "doc": "Add nanoparticles to material"
      },
      {
        "tool_name": "apply_coating",
        "args": [
          "base_material_name"
        ],
        "doc": "Apply surface coating"
      },
      {
        "tool_name": "design_lattice",
        "args": [
          "base_material_name"
        ],
        "doc": "Design lattice structure for AM"
      },
      {
        "tool_name": "predict_from_composition",
        "args": [
          "composition",
          "properties"
        ],
        "doc": "Predict properties from composition"
      },
      {
        "tool_name": "predict_from_structure",
        "args": [
          "crystal_structure",
          "bonding_type",
          "properties"
        ],
        "doc": "Predict properties from structure"
      },
      {
        "tool_name": "predict_by_similarity",
        "args": [
          "reference_material_name",
          "property_name"
        ],
        "doc": "Predict property by similarity"
      },
      {
        "tool_name": "compare_materials",
        "args": [
          "material_names",
          "properties"
        ],
        "doc": "Compare multiple materials"
      },
      {
        "tool_name": "find_best_material",
        "args": [
          "category",
          "optimize_for",
          "constraints"
        ],
        "doc": "Find best material for application\n\nArgs:\n    category: Material category to search\n    optimize_for: Property to maximize\n    constraints: Dict of property constraints (min/max values)"
      }
    ]
  },
  {
    "id": "base_lab.py",
    "name": "Base",
    "description": "Abstract base class for all laboratories in QuLabInfinite.\n\nThis class defines the common interface that all specialized labs\n(e.g., MaterialsLab, ChemistryLaboratory, QuantumLabSimulator) must implement.\nThis ensures a consistent API for initialization, configuration,\nand execution of simulations across the platform.",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a specific experiment based on the provided specification.\n\nArgs:\n    experiment_spec: A dictionary defining the experiment to be run,\n                     including parameters and desired outputs.\n\nReturns:\n    A dictionary containing the results of the experiment."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get the current status of the laboratory.\n\nReturns:\n    A dictionary containing status information, such as backend state,\n    loaded data, and available capabilities."
      },
      {
        "tool_name": "get_capabilities",
        "args": [],
        "doc": "Get the capabilities of the laboratory.\n\nReturns:\n    A dictionary describing the capabilities of the lab."
      }
    ]
  },
  {
    "id": "quantum_lab.py",
    "name": "Quantum",
    "description": "Unified quantum laboratory simulator.\n\nFeatures:\n- 30-qubit exact statevector simulation\n- Tensor network approximation for >30 qubits\n- Quantum chemistry integration\n- Materials science quantum calculations\n- Quantum sensor modeling\n- Cognition-inspired algorithms\n\nIntegration:\n- Wraps existing CircuitSimulator (30-qubit exact)\n- Wraps QuantumCognition (quantum-inspired)\n- Extends with chemistry, materials, sensors\n\nECH0 Usage Examples:\n```python\n# Basic circuit simulation\nlab = QuantumLabSimulator(num_qubits=5)\nlab.h(0)  # Hadamard on qubit 0\nlab.cnot(0, 1)  # Entangle qubits\nresults = lab.measure_all()\n\n# Chemistry calculation\nfrom quantum_chemistry import Molecule\nh2 = Molecule.hydrogen_molecule(bond_length=0.74)\nenergy = lab.chemistry.compute_ground_state_energy(h2)\n\n# Materials property\nenergy_gap = lab.materials.compute_band_gap(\"silicon\")\n\n# Quantum sensing\nsensitivity = lab.sensors.magnetometry_sensitivity(num_qubits=10)\n```",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a quantum experiment.\n\nExample spec:\n{\n    \"experiment_type\": \"bell_pair\",\n}\n{\n    \"experiment_type\": \"ghz_state\",\n    \"num_qubits\": 4\n}\n{\n    \"experiment_type\": \"custom_circuit\",\n    \"operations\": [\n        {\"gate\": \"h\", \"qubit\": 0},\n        {\"gate\": \"cnot\", \"control\": 0, \"target\": 1}\n    ]\n}"
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get information about current backend and state."
      },
      {
        "tool_name": "h",
        "args": [
          "qubit"
        ],
        "doc": "Apply Hadamard gate"
      },
      {
        "tool_name": "x",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-X gate"
      },
      {
        "tool_name": "y",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-Y gate"
      },
      {
        "tool_name": "z",
        "args": [
          "qubit"
        ],
        "doc": "Apply Pauli-Z gate"
      },
      {
        "tool_name": "rx",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RX rotation"
      },
      {
        "tool_name": "ry",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RY rotation"
      },
      {
        "tool_name": "rz",
        "args": [
          "qubit",
          "theta"
        ],
        "doc": "Apply RZ rotation"
      },
      {
        "tool_name": "cnot",
        "args": [
          "control",
          "target"
        ],
        "doc": "Apply CNOT gate"
      },
      {
        "tool_name": "cz",
        "args": [
          "control",
          "target"
        ],
        "doc": "Apply CZ gate"
      },
      {
        "tool_name": "measure",
        "args": [
          "qubit"
        ],
        "doc": "Measure single qubit"
      },
      {
        "tool_name": "measure_all",
        "args": [],
        "doc": "Measure all qubits"
      },
      {
        "tool_name": "get_probabilities",
        "args": [],
        "doc": "Get probability distribution"
      },
      {
        "tool_name": "expectation_value",
        "args": [
          "observable"
        ],
        "doc": "Compute expectation value of observable.\n\nArgs:\n    observable: Pauli string like 'Z0' or 'X0Y1Z2'\n\nReturns:\n    Expectation value <\u03c8|O|\u03c8>"
      },
      {
        "tool_name": "fidelity",
        "args": [
          "target_state"
        ],
        "doc": "Compute fidelity with target state.\n\nF = |<\u03c8|\u03c6>|\u00b2"
      },
      {
        "tool_name": "chemistry",
        "args": [],
        "doc": "Access quantum chemistry module"
      },
      {
        "tool_name": "materials",
        "args": [],
        "doc": "Access quantum materials module"
      },
      {
        "tool_name": "sensors",
        "args": [],
        "doc": "Access quantum sensors module"
      },
      {
        "tool_name": "reset",
        "args": [],
        "doc": "Reset quantum state to |0\u27e9^n"
      },
      {
        "tool_name": "print_state",
        "args": [
          "top_n"
        ],
        "doc": "Print quantum state"
      },
      {
        "tool_name": "get_backend_info",
        "args": [],
        "doc": "Get information about current backend"
      }
    ]
  },
  {
    "id": "chemistry_lab.py",
    "name": "Chemistry",
    "description": "Unified chemistry laboratory interface.\n\nProvides access to:\n1. Molecular Dynamics (100k atoms @ 1fs)\n2. Reaction Simulation (TST, NEB, catalysis)\n3. Synthesis Planning (retrosynthesis, optimization)\n4. Spectroscopy Prediction (NMR, IR, UV-Vis, MS, XRD)\n5. Solvation Models (PCM, COSMO, SMD, pH effects)\n6. Quantum Chemistry (DFT, HF, MP2, CCSD(T))\n\nTarget accuracy: <5% error on reaction energetics, <10% on spectroscopy",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a chemistry experiment."
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Returns a summary of the lab's configuration and capabilities."
      },
      {
        "tool_name": "calculate_dissolution_enthalpy",
        "args": [
          "salt",
          "solvent",
          "temperature_K"
        ],
        "doc": "Compute the dissolution enthalpy for an ionic solid using the Born-Haber cycle.\n\nArgs:\n    salt: Salt formula (e.g., \"NaCl\")\n    solvent: Solvent identifier\n    temperature_K: Temperature in Kelvin\n\nReturns:\n    Dictionary with \u0394H (kJ/mol) and source metadata."
      },
      {
        "tool_name": "create_md_simulation",
        "args": [
          "atoms",
          "box_size",
          "force_field",
          "ensemble",
          "timestep"
        ],
        "doc": "Create molecular dynamics simulation."
      },
      {
        "tool_name": "run_md_simulation",
        "args": [
          "n_steps",
          "temperature",
          "output_interval"
        ],
        "doc": "Run MD simulation."
      },
      {
        "tool_name": "simulate_reaction",
        "args": [
          "reactants",
          "products",
          "conditions",
          "reaction_name",
          "materials_lab",
          "environment_simulator"
        ],
        "doc": "Simulate chemical reaction and predict kinetics."
      },
      {
        "tool_name": "get_reaction_metadata",
        "args": [
          "reaction_name"
        ],
        "doc": "Expose reaction metadata summary."
      },
      {
        "tool_name": "plan_synthesis",
        "args": [
          "target",
          "max_depth"
        ],
        "doc": "Plan synthesis route to target compound."
      },
      {
        "tool_name": "analyze_synthesis_safety",
        "args": [
          "route"
        ],
        "doc": "Analyze safety of synthesis route."
      },
      {
        "tool_name": "predict_nmr",
        "args": [
          "molecule",
          "nucleus"
        ],
        "doc": "Predict NMR spectrum."
      },
      {
        "tool_name": "predict_ir",
        "args": [
          "molecule"
        ],
        "doc": "Predict IR spectrum."
      },
      {
        "tool_name": "predict_uv_vis",
        "args": [
          "molecule"
        ],
        "doc": "Predict UV-Vis spectrum."
      },
      {
        "tool_name": "predict_mass_spectrum",
        "args": [
          "molecule"
        ],
        "doc": "Predict mass spectrum."
      },
      {
        "tool_name": "calculate_solvation_energy",
        "args": [
          "solute",
          "solvent_name",
          "model"
        ],
        "doc": "Calculate solvation free energy."
      },
      {
        "tool_name": "predict_logP",
        "args": [
          "solute"
        ],
        "doc": "Predict octanol-water partition coefficient."
      },
      {
        "tool_name": "calculate_pH_effect",
        "args": [
          "solute",
          "pH",
          "pKa"
        ],
        "doc": "Calculate pH effects on ionization."
      },
      {
        "tool_name": "quantum_calculation",
        "args": [
          "molecule",
          "method",
          "basis_set"
        ],
        "doc": "Perform quantum chemistry calculation."
      },
      {
        "tool_name": "optimize_geometry",
        "args": [
          "molecule",
          "method"
        ],
        "doc": "Optimize molecular geometry."
      },
      {
        "tool_name": "calculate_vibrational_frequencies",
        "args": [
          "molecule"
        ],
        "doc": "Calculate vibrational frequencies."
      },
      {
        "tool_name": "complete_molecule_characterization",
        "args": [
          "molecule"
        ],
        "doc": "Complete characterization of molecule:\n- Spectroscopy (NMR, IR, UV-Vis, MS)\n- Solvation (logP, solubility)\n- Quantum properties (HOMO-LUMO, dipole)"
      },
      {
        "tool_name": "reaction_optimization_workflow",
        "args": [
          "reactants",
          "products",
          "catalysts"
        ],
        "doc": "Optimize reaction conditions:\n- Find optimal catalyst\n- Determine best temperature/pressure\n- Predict yields"
      }
    ]
  },
  {
    "id": "universal_lab.py",
    "name": "Universal",
    "description": "",
    "capabilities": [
      {
        "tool_name": "get_lab_info",
        "args": [
          "lab_id"
        ],
        "doc": "Introspects a lab file to find classes and methods."
      },
      {
        "tool_name": "combine_materials",
        "args": [
          "materials",
          "conditions"
        ],
        "doc": "Simulates the combination of materials under given conditions."
      }
    ]
  },
  {
    "id": "vpd_lab.py",
    "name": "Vpd",
    "description": "Virtual Product Development Laboratory.\n\nA comprehensive simulation laboratory for virtual product development\nthat enables multi-discipline design integration, real-time collaboration,\nand design optimization across the entire value network.\n\nKey Capabilities:\n- Multi-discipline design integration (mechanical, electrical, systems, software)\n- Product configuration and variant management\n- Bill of Materials (BOM) management with cost rollup\n- Value network collaboration and change management\n- Multi-objective design optimization\n- Trade-off studies and sensitivity analysis\n- Design space exploration\n\nThis lab transforms the innovation process by providing a unified platform\nfor connecting all stakeholders and design domains, reducing design cycle\ntimes and revealing collaboration opportunities early in development.",
    "capabilities": [
      {
        "tool_name": "run_experiment",
        "args": [
          "experiment_spec"
        ],
        "doc": "Run a virtual product development experiment.\n\nSupported experiment types:\n- 'create_product': Create a new product definition\n- 'add_component': Add a component to a product\n- 'create_variant': Create a product variant\n- 'generate_bom': Generate Bill of Materials\n- 'optimize_design': Run design optimization\n- 'trade_off_study': Perform trade-off analysis\n- 'sensitivity_analysis': Analyze parameter sensitivities\n- 'explore_design_space': Explore the design space\n\nArgs:\n    experiment_spec: Dictionary with 'type' and type-specific parameters\n\nReturns:\n    Dictionary with experiment results"
      },
      {
        "tool_name": "get_status",
        "args": [],
        "doc": "Get the current status of the laboratory."
      },
      {
        "tool_name": "get_capabilities",
        "args": [],
        "doc": "Get the capabilities of the laboratory."
      },
      {
        "tool_name": "create_product",
        "args": [
          "name",
          "description",
          "product_family"
        ],
        "doc": "Create a new product definition."
      },
      {
        "tool_name": "get_product",
        "args": [
          "product_id"
        ],
        "doc": "Get a product by ID or the active product."
      },
      {
        "tool_name": "add_component",
        "args": [
          "product_id",
          "name",
          "component_type",
          "discipline",
          "parent_id"
        ],
        "doc": "Add a component to a product."
      },
      {
        "tool_name": "create_variant",
        "args": [
          "product_id",
          "name",
          "description"
        ],
        "doc": "Create a product variant."
      },
      {
        "tool_name": "generate_bom",
        "args": [
          "product_id",
          "variant_id",
          "bom_type"
        ],
        "doc": "Generate Bill of Materials for a product."
      },
      {
        "tool_name": "get_bom_csv",
        "args": [],
        "doc": "Export current BOM as CSV."
      },
      {
        "tool_name": "get_bom_json",
        "args": [],
        "doc": "Export current BOM as JSON."
      },
      {
        "tool_name": "add_stakeholder",
        "args": [
          "name",
          "email",
          "role",
          "organization"
        ],
        "doc": "Add a stakeholder to the collaboration hub."
      },
      {
        "tool_name": "create_task",
        "args": [
          "title",
          "description",
          "assigned_to",
          "priority"
        ],
        "doc": "Create a collaboration task."
      },
      {
        "tool_name": "schedule_review",
        "args": [
          "title",
          "review_type",
          "reviewers",
          "presenter",
          "components"
        ],
        "doc": "Schedule a design review."
      },
      {
        "tool_name": "submit_change_request",
        "args": [
          "title",
          "description",
          "justification",
          "change_type",
          "affected_components"
        ],
        "doc": "Submit an engineering change request."
      },
      {
        "tool_name": "setup_optimization",
        "args": [
          "variables",
          "objectives",
          "constraints"
        ],
        "doc": "Setup optimization problem.\n\nArgs:\n    variables: List of dicts with name, min, max, current values\n    objectives: List of dicts with name, expression, type (minimize/maximize)\n    constraints: List of dicts with name, expression, limit, type"
      },
      {
        "tool_name": "run_optimization",
        "args": [
          "method"
        ],
        "doc": "Run optimization with specified method."
      },
      {
        "tool_name": "run_trade_off_study",
        "args": [
          "objective_x",
          "objective_y",
          "num_points"
        ],
        "doc": "Run a trade-off study between two objectives."
      },
      {
        "tool_name": "run_sensitivity_analysis",
        "args": [
          "solution"
        ],
        "doc": "Run sensitivity analysis around a solution."
      },
      {
        "tool_name": "run_demo",
        "args": [],
        "doc": "Run a demonstration of the Virtual Product Development Lab.\n\nCreates a sample product with components, generates BOM,\nsets up collaboration, and runs a simple optimization."
      }
    ]
  },
  {
    "id": "oncology_lab.py",
    "name": "Oncology",
    "description": "Main laboratory for conducting cancer experiments\nIntegrates tumor simulation, drug testing, and intervention protocols",
    "capabilities": [
      {
        "tool_name": "administer_drug",
        "args": [
          "drug_name",
          "dose_mg"
        ],
        "doc": "Administer a drug to the tumor\n\nArgs:\n    drug_name: Name of drug from database\n    dose_mg: Dose in milligrams"
      },
      {
        "tool_name": "apply_intervention_protocol",
        "args": [
          "protocol"
        ],
        "doc": "Apply a multi-field intervention protocol\n\nArgs:\n    protocol: Intervention protocol to apply"
      },
      {
        "tool_name": "step",
        "args": [
          "dt"
        ],
        "doc": "Advance simulation by one time step\n\nArgs:\n    dt: Time step in hours (default: from config)"
      },
      {
        "tool_name": "run_experiment",
        "args": [
          "duration_days",
          "report_interval_hours"
        ],
        "doc": "Run experiment for specified duration\n\nArgs:\n    duration_days: How long to run (days)\n    report_interval_hours: How often to print progress"
      },
      {
        "tool_name": "get_results",
        "args": [],
        "doc": "Get comprehensive experimental results\n\nReturns:\n    Dictionary with all experimental data"
      },
      {
        "tool_name": "print_summary",
        "args": [],
        "doc": "Print experimental summary"
      }
    ]
  },
  {
    "id": "universal_lab.py",
    "name": "Universal",
    "description": "",
    "capabilities": [
      {
        "tool_name": "get_lab_info",
        "args": [
          "lab_id"
        ],
        "doc": "Introspects a lab file to find classes and methods."
      },
      {
        "tool_name": "combine_materials",
        "args": [
          "materials",
          "conditions"
        ],
        "doc": "Simulates the combination of materials under given conditions."
      }
    ]
  }
]