1Fetches content from a specified URL and processes it using an AI model to extract information or answer questions.
 2
 3<when_to_use>
 4Use this tool when you need to:
 5- Extract specific information from a webpage (e.g., "get pricing info")
 6- Answer questions about web content (e.g., "what does this article say about X?")
 7- Summarize or analyze web pages
 8- Find specific data within large pages
 9- Interpret or process web content with AI
10
11DO NOT use this tool when:
12- You just need raw content without analysis (use fetch instead - faster and cheaper)
13- You want direct access to API responses or JSON (use fetch instead)
14- You don't need the content processed or interpreted (use fetch instead)
15</when_to_use>
16
17<usage>
18- Takes a URL and a prompt as input
19- Fetches the URL content, converts HTML to markdown
20- Processes the content with the prompt using a small, fast model
21- Returns the model's response about the content
22- Use this tool when you need to retrieve and analyze web content
23</usage>
24
25<usage_notes>
26
27- IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead of this one, as it may have fewer restrictions. All MCP-provided tools start with "mcp_".
28- The URL must be a fully-formed valid URL
29- HTTP URLs will be automatically upgraded to HTTPS
30- The prompt should describe what information you want to extract from the page
31- This tool is read-only and does not modify any files
32- Results may be summarized if the content is very large
33- For very large pages, the content will be saved to a temporary file and the agent will have access to grep/view tools to analyze it
34- When a URL redirects to a different host, the tool will inform you and provide the redirect URL. You should then make a new fetch request with the redirect URL to fetch the content.
35- This tool uses AI processing and costs more tokens than the simple fetch tool
36  </usage_notes>
37
38<limitations>
39- Max response size: 5MB
40- Only supports HTTP and HTTPS protocols
41- Cannot handle authentication or cookies
42- Some websites may block automated requests
43- Uses additional tokens for AI processing
44</limitations>
45
46<tips>
47- Be specific in your prompt about what information you want to extract
48- For complex pages, ask the agent to focus on specific sections
49- The agent has access to grep and view tools when analyzing large pages
50- If you just need raw content, use the fetch tool instead to save tokens
51</tips>