Skip to main content
Glama

Read a web page

web_fetch
Read-onlyIdempotent

Read one page of the public web, given its address: its words as Markdown, with the e-mail addresses, phone numbers and named people the page publishes. A long page comes back in parts (next_start), or as only the passages that hold the words in find. Reads pages, not files: a PDF is not read. Members only.

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>"
    },
    "name": "web_fetch"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe page's full address: one a search returned, one on a record in the database, or one the person gave.
findNoWords to look for on the page; several ways of saying it split with "|" ("managing partner|founder|principal"). Only the passages that hold them come back, each with the lines around it. Use it on a long page when one thing is wanted.
startNoWhere to start reading, in characters: the next_start of a page that was cut, to read on.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, openWorld, idempotent and non-destructive, so the safety profile is covered. The description still adds real behavior the agent could not infer: the return is Markdown plus extracted e-mail/phone/person data, long pages are truncated with a next_start, PDFs are refused, and access is restricted ("Members only"). That last point is useful but cryptic about whose membership and what happens on failure.

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

Conciseness5/5

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

Front-loaded with the core action and return shape, then modes, then exclusions, then access. Every sentence carries information (Markdown output, PII extraction, pagination, PDF exclusion, membership) with no filler or repetition.

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

Completeness5/5

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

There is no output schema, so the description must carry the return contract itself, and it does: format (Markdown), payload (words plus e-mail/phone/people), truncation and continuation (next_start), and filtered-passage mode. Combined with an annotations-covered safety profile and a fully documented 3-parameter schema, nothing an agent needs to call this correctly is missing.

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%, and the schema already explains `url`, `find` (with the pipe-splitting convention and an example) and `start` as the next_start continuation. The description restates the find/long-page relationship and the next_start mechanism but adds no syntax or format detail beyond the schema, so the baseline of 3 applies.

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?

A specific verb and resource ("Read one page of the public web, given its address") plus a concrete statement of what comes back: the page's words as Markdown, with e-mail addresses, phone numbers and named people. It carves out scope ("Reads pages, not files: a PDF is not read"), but it never names or contrasts with the crawl/search siblings, so the agent must infer the boundary between reading one page and crawling a site.

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

Usage Guidelines3/5

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

The guidance present is about modes rather than tool choice: long pages arrive in parts via next_start, or as filtered passages, and "Use it on a long page when one thing is wanted" tells the agent when to reach for `find`. There is no explicit statement of when to prefer this over web_crawl or web_search, and no prerequisites beyond the trailing "Members only".

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources