OpenWebSearch

web_fetch

Fetch and read a specific web page as clean markdown. Accepts a url or a doc_id from web_search. Use after web_search finds candidate sources, or when the user provides a URL.

Remote caesar/web-search

Remote (network-hosted)

Other tools also called web_fetch? See providers with this name

Input Schema


            {
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "URL of the page to read. Provide either url or doc_id."
    },
    "query": {
      "type": "string",
      "description": "Optional question to focus content selection on the most relevant sections."
    },
    "doc_id": {
      "type": "string",
      "description": "Caesar doc_id from a previous search result. Provide either url or doc_id."
    },
    "max_chars": {
      "type": "integer",
      "description": "Maximum content characters to return. Default 12000, max 50000."
    },
    "start_char": {
      "type": "integer",
      "description": "Resume a truncated read from this character offset of the same document. Default 0."
    }
  }
}