Skip to main content
Glama

Web page or PDF to Markdown

kairos_page_markdown
Read-onlyIdempotent

Web page, PDF or text file to clean Markdown: main content kept (headings, lists, links, tables, code), navigation and ads removed, links made absolute; PDFs as text with page count. JavaScript-only pages are refused, not charged. Honours robots.txt, refuses private addresses; limits 2 MB HTML, 8 MB PDF, 15 s; output capped at 200,000 characters (marked truncated). Nothing is stored. Read-only. Free for MCP clients up to 3 reports per client per day; beyond the quota the response lists the paid access options (x402 on the HTTP route, or a prepaid credit key) instead of a report. Never pays or signs anything itself. Automated conversion; the content belongs to its publisher and may be incomplete.

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": "kairos_page_markdown"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesPublic http(s) URL of a web page or PDF
credit_keyNoOptional prepaid credit key for use beyond the free daily quota.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations, which already declare readOnly/openWorld/idempotent/non-destructive. It discloses refusal conditions, honouring of robots.txt, size limits (2 MB HTML, 8 MB PDF, 15 s), a 200,000-character output cap with a truncation marker, no storage, a free quota of 3 reports per client per day, and what happens beyond quota (paid options listed instead of a report).

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 core purpose is front-loaded in the first clause and every subsequent clause adds operational fact (limits, refusals, quota, output cap). The semicolon-chained density makes it feel like a single run-on block rather than a structured summary, which costs it a point.

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?

No output schema exists, and the description still conveys the return shape: clean Markdown with absolute links, PDFs as text with a page count, and a truncation marker past 200,000 characters. Combined with quota and refusal behavior, an agent has everything needed to call it correctly and interpret the result.

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

Parameters4/5

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

Schema coverage is 100% and only two parameters exist, so the baseline would be 3. The description nonetheless adds meaning for credit_key by explaining that it is a prepaid key used beyond the free daily quota, connecting the parameter to the quota behavior described in prose.

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?

Opens with a specific verb-and-resource statement: 'Web page, PDF or text file to clean Markdown,' then enumerates exactly what is preserved (headings, lists, links, tables, code) and what is stripped (navigation, ads). The sibling tools (catalog, wallet activity) are unrelated in function, so an agent can route here unambiguously.

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?

Gives clear use conditions and hard exclusions: JavaScript-only pages are refused, robots.txt is honoured, private addresses are refused, with explicit size and time limits. It does not name an alternative tool for the refused cases (e.g., a browser-rendering tool), which is the only gap.

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.