Skip to main content
Glama
xhighhongo41

crawl4tools

by xhighhongo41
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Fetch web pages

fetch
Read-only

Retrieve one or more web pages and get their content as Markdown, HTML, or a PNG screenshot; PDFs are converted to Markdown.

Instructions

Fetch one or more web pages and return their content directly: Markdown (default), HTML, or a PNG screenshot. PDFs are transcribed to Markdown and images are returned as images. When several URLs are given, each result starts with a '' header. Failed URLs are reported as 'error: ...' lines; the call fails only if every URL fails. Use download to save other formats to files.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fitNoKeep only the main content (drops menus, footers, and the like); falls back to the full page when nothing is left. Markdown only.
urlsYesURLs to fetch (http or https), at most the server's per-call limit (see the server instructions); duplicates are fetched once.
formatNoOutput format: 'markdown' (default), 'html' (rendered page HTML), or 'screenshot' (full-page PNG image).markdown
citationsNoTurn links into numbered references listed at the end. Markdown only.
timeout_sNoPage load timeout per URL in seconds; defaults to the server setting.
ignore_linksNoDrop links from the Markdown output. Markdown only.
ignore_imagesNoDrop images from the Markdown output. Markdown only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the readOnly/openWorld annotations, the description discloses concrete non-obvious behavior: PDFs are transcribed to Markdown, images are returned as images, multi-URL results include header markers, failed URLs become 'error: ...' lines, and the call only fails if every URL fails. This is exactly the kind of behavioral detail an agent needs to interpret results.

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?

Four sentences, each earning its place: core purpose and formats, special content handling, multi-URL/error semantics, and sibling routing. The description is front-loaded with the main action and contains no filler.

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?

Even without an output schema, the description explains what the caller receives: direct content in the chosen format, result headers for multiple URLs, and error lines for failed URLs. Combined with the fully documented schema and read-only annotations, an agent has enough to invoke and interpret results correctly.

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?

The input schema already describes every parameter in detail, so the baseline is 3. The description reinforces the format choices and adds context about PDF/image handling, but it does not add new parameter-level meaning beyond what the schema provides.

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

Purpose5/5

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

The description opens with the verb 'Fetch' plus the resource 'web pages' and immediately enumerates the three output formats: Markdown, HTML, and PNG screenshot. It also distinguishes itself from the sibling tool by pointing to `download` for saving other formats, so an agent can tell them apart.

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

Usage Guidelines5/5

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

It explicitly states when to use fetch for web content and routes other output needs to the `download` sibling. It also provides operational context for multi-URL calls, failure reporting, and the condition under which the call fails, giving an agent clear decision guidance.

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