fix: vision tool cannot process videos, clarify image-only capability

Removed misleading statement about video files. Vision tool ONLY processes
image files (JPEG, PNG, GIF, BMP, WebP), not videos.

Changes:
- Changed "Analyze images or videos" to "Analyze image files"
- Added explicit image format list (JPEG, PNG, GIF, BMP, WebP)
- Removed "For video files...file must be downloaded first"
- Added "Cannot process videos" NOTE
- Added guidance to use youtube_transcript/transcribe_audio for videos

Co-Authored-By: Claude <noreply@anthropic.com>

src/tools/__init__.py

@@ -66,10 +66,10 @@ TOOLS = {
     },
     "vision": {
         "function": analyze_image,
-        "description": "Analyze images using multimodal AI vision models. Describe visual content, identify objects, read text from images, answer questions about photos or screenshots. Use when question mentions images, photos, pictures, screenshots, or visual content. NOTE: For YouTube videos, use youtube_transcript tool instead. For video files (MP4, AVI, etc.), the file must be downloaded first.",
+        "description": "Analyze image files using multimodal AI vision models. Describe visual content, identify objects, read text from images, answer questions about photos or screenshots. Use when question mentions images, photos, pictures, screenshots, or visual content. Supports JPEG, PNG, GIF, BMP, WebP formats. NOTE: Cannot process videos. For YouTube videos or video files, use youtube_transcript or transcribe_audio tools instead.",
         "parameters": {
             "image_path": {
-                "description": "Path to the image file to analyze",
+                "description": "Path to the image file to analyze (JPEG, PNG, GIF, BMP, WebP)",
                 "type": "string"
             },
             "question": {