crawl4tools

Download web pages to files

download

Idempotent

Fetch multiple URLs and save each as Markdown, HTML, PDF, screenshot, MHTML, or raw source files, returning saved paths. Choose format and options like fit, citations, and timeouts.

Instructions

Fetch one or more URLs and save each result as a file in a directory on the server, returning the saved paths. Supports Markdown (default), HTML, PDF, PNG screenshot, MHTML, and the raw source. PDFs are transcribed to Markdown unless format is 'raw'; non-web content (images, archives, ...) is saved as served. Existing files are overwritten. The call fails only if no file was saved.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`fit`	No	Keep only the main content (drops menus, footers, and the like); falls back to the full page when nothing is left. Markdown only.
`urls`	Yes	URLs to fetch (http or https), at most the server's per-call limit (see the server instructions); duplicates are fetched once.
`format`	No	File format: 'markdown' (default), 'html', 'pdf' (page printed to PDF), 'screenshot' (PNG), 'mhtml' (single-file web archive), or 'raw' (the original response bytes, e.g. a PDF or image as served).	markdown
`citations`	No	Turn links into numbered references listed at the end. Markdown only.
`directory`	No	Subdirectory of the server's download directory to save into; must stay inside it. Defaults to the download directory itself.
`timeout_s`	No	Page load timeout per URL in seconds; defaults to the server setting.
`ignore_links`	No	Drop links from the Markdown output. Markdown only.
`ignore_images`	No	Drop images from the Markdown output. Markdown only.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Sep 24, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations carry no behavioral hints (readOnly=false, destructive=false), so description must carry the burden. It does: mentions overwrites, failure condition (fails only if no file saved), PDF transcription, and non-web handling. Good coverage, though it omits details like per-call URL limits (but schema covers that).

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?

The description is a single, dense paragraph but front-loaded with the main action and result. It covers formats and key behaviors efficiently without fluff. Could be slightly more structured but is highly readable.

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?

Given 8 parameters and no output schema, the description covers critical behaviors: success/failure, format specifics, and side effects. It does not explicitly state return format, but that's a minor gap. The 'raw' and PDF transcription details add completeness. Overall sufficient for an agent to call 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?

Schema description coverage is 100%, so baseline is 3. The description adds context for 'raw' format and 'fit/citations' being Markdown-only, which is useful, but not extensive; the schema already explains each parameter's meaning.

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?

States a specific verb ('Fetch') and resource ('URLs') and explains it saves files to the server, returning paths. Explicitly distinguishes from sibling by listing supported formats and mention of server-side saving.

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

Usage Guidelines4/5

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

Describes the tool's function and when it applies (fetching URLs to files), but does not explicitly contrast with the sibling 'fetch' tool. The 'raw' format and non-web content handling give context, but no direct 'use this instead of fetch' 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

downloadA
fetchA