Upload README.md with huggingface_hub

README.md

@@ -88,6 +88,15 @@ Every platform folder in this repo holds an engine under 1 MB that loads `needle
 ./needle --model needle3.cact --tools tools.json --serve
 ```
 
+Tool schemas share the model context with the system prompt and conversation.
+`needle_init` returns the tokenized static-prefix length on success and fails
+when that prefix does not fit the model context. In the C API, call
+`needle_last_error()` after a negative return to get the measured prefix tokens
+and context limit. Reduce tool descriptions/schema text, split large catalogues,
+or declare more than five tools so Needle can keep only retrieved tools in the
+per-turn prefix. At completion time, `max_new_tokens` also reserves context room,
+so larger generation caps leave less space for the current turn and history.
+
 The [devices guide](https://cactuscompute.com/blog/needle-supported-devices) covers the runner flags, the C API, the WASI component and air-gapped setup.
 
 ## Citation