Kempt Horizon Data Toolkit

Web page to Markdown

page_to_markdown

Read-only

Fetch a public web page (robots.txt honored) or take raw HTML and return the main content as clean Markdown with absolute links.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "page_to_markdown"
  }
}

Input Schema

Name	Required	Description
`url`	No	Public http(s) URL to fetch (robots.txt is honored). Optional if html is given; then used as base URL.
`html`	No	Raw HTML to process instead of fetching (max 3 MB).
`include`	No	Comma list or array of parts to return: metadata, markdown, text, links, images, headings. Default: markdown
`maxChars`	No	Cap on markdown/text length (1,000-500,000).
`mainContentOnly`	No	Strip nav, header, footer, sidebars, cookie banners and ads; keep the main article.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 26, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, so the bar is lower, and the description still adds real behavior: robots.txt is honored and links are rewritten to absolute URLs. It omits failure modes (blocked by robots, oversized HTML, timeouts) but covers the key operational traits.

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?

A single front-loaded sentence that states the two input paths, the constraint (public, robots.txt honored), and the output shape. No filler and nothing trailing.

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 5-parameter, all-optional tool with full schema descriptions and no output schema, the description covers both modes and the transformation contract adequately. A brief note that `include` can return multiple parts (metadata, links, etc.) instead of only Markdown would close the remaining gap.

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 coverage is 100% and every parameter has a descriptive schema entry, so the baseline is 3. The description adds only the notion of 'main content' and 'absolute links,' which are already implied by mainContentOnly and the link handling it mentions; no syntax or format detail is added.

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?

Concrete verb-plus-resource: fetches a URL or accepts raw HTML, then returns main content as clean Markdown. The dual input mode and Markdown output are clear. It does not name or distinguish itself from siblings page_extract and page_metadata, which likely overlap in domain.

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?

Usage is only implied: the agent can infer 'use this to convert a page to Markdown,' and the 'or take raw HTML' clause hints at the two entry modes. There is no explicit statement of when to prefer page_extract or page_metadata, nor any exclusions for non-public/robots-blocked pages.

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

All Kempt Horizon Data Toolkit tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?