Skip to main content
Glama

Web Fetch

web_fetch

Fetch a web page, convert HTML to markdown, and answer questions about its content using Claude.

Instructions

Fetch a web page and answer questions about its content.

Fetches the URL, converts HTML to markdown, and uses Claude to answer the prompt based on the page content.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>",
      "prompt": "<prompt>"
    },
    "name": "web_fetch"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe URL to fetch content from. HTTP URLs are auto-upgraded to HTTPS.
promptYesQuestion or instruction about the page content.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

B3.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full load. It does add genuinely useful behavioral context: the URL is fetched, HTML is converted to markdown, and Claude answers the prompt from the page content — meaning the agent gets an answer rather than raw markup. It omits important traits such as page-size/truncation limits, handling of unauthenticated or blocked pages, and failure behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the capability before the mechanism. There is mild redundancy between "Fetch a web page" and "Fetches the URL," but nothing extraneous enough to warrant trimming beyond that.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with an output schema, the description covers the essential mechanics: input is a URL plus a prompt, and the output is an answer derived from the page. The main gap is operational caveats (size limits, blocked or paywalled pages) given the lack of annotations, which keeps it from a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, including the note that HTTP URLs are auto-upgraded to HTTPS, so the schema already explains both parameters. The description adds no further meaning about the prompt parameter (e.g. whether multiple questions are supported or how the answer is shaped) beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Fetch a web page and answer questions about its content" gives a specific verb (fetch) plus the added value (answering a prompt), so the agent knows this is not a raw-page-retrieval tool. There are no siblings to differentiate against, so full marks for sibling disambiguation aren't in play, but the purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states what the tool does but never says when to reach for it, when not to, or what alternative exists (e.g. raw fetching vs. summarization). With an empty sibling list there's nothing to route against, yet the definition gives no conditions, prerequisites, or exclusions either.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools