{
  "description": "Extract content from web page URLs. Returns clean page content in markdown/text (no LLM summarization — fast). Also works with PDF URLs (arxiv papers, documents) — pass the PDF link directly. Pages within the char budget (default 15000) return whole; larger pages return a head+tail window with a footer telling you the full text's saved file path and the read_file call to page through the omitted middle. Inline images appear as [IMAGE: alt] placeholders; real image URLs are kept as links. If a URL fails or times out, use the browser tool instead.",
  "name": "web_extract",
  "parameters": {
    "properties": {
      "char_limit": {
        "description": "Optional per-page character budget sent back (default 15000). Pages larger than this are head+tail truncated with the full text stored to disk. Raise it when you need more of a long page inline.",
        "minimum": 2000,
        "type": "integer"
      },
      "urls": {
        "description": "List of URLs to extract content from (max 5 URLs per call)",
        "items": {
          "type": "string"
        },
        "maxItems": 5,
        "type": "array"
      }
    },
    "required": [
      "urls"
    ],
    "type": "object"
  }
}