Skip to main content
Glama

Convert any web page into clean Markdown for LLMs

page_markdown
Read-only

Convert any web page into clean Markdown for LLMs: main content only (no nav, footer, scripts, cookie banners), with headings, lists, links, images, tables and code blocks preserved. Optional maxChars (1,000-200,000, default 50,000). Fast (1-3 s). Free: 20 calls/day per user across free tools, no payment needed. Above that: $0.003 per call (x402, USDC on Base).

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": "page_markdown"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesPublic http(s) URL
paymentNox402 payment: the base64 PAYMENT-SIGNATURE value signed for the requirements returned by an unpaid call (USDC on Base, gasless). Omit on the first call to get the price and requirements.
maxCharsNoMax characters returned (1000-200000)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only declare readOnly and openWorld, but the description adds substantial operational context beyond them: latency (1-3 s), a free tier of 20 calls/day across free tools, and a paid path at $0.003 per call via x402/USDC on Base. What it omits is what happens when content exceeds maxChars (truncated vs. error), a behavioral detail relevant to a read tool that returns large payloads.

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?

Front-loaded with the core action and output contract, then cost and speed, all in one tight paragraph with no filler. It is dense but readable; the pricing and payment clauses are compressed near telegraphic, which is acceptable but slightly crowded for a single sentence run.

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 carries the return-format burden and does so completely: it enumerates preserved structures (headings, lists, links, images, tables, code blocks) and excluded boilerplate. Combined with latency, quota, and the payment handshake, an agent has everything needed to call this correctly on the first attempt.

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%, so the baseline is 3, and the description adds value on top by supplying the maxChars default of 50,000, which the schema omits. It also frames the payment parameter's sequencing (omit on first call to obtain price and requirements), reinforcing rather than merely restating the schema.

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 and resource ("Convert any web page into clean Markdown for LLMs") and immediately scopes the output (main content only, boilerplate stripped). This clearly separates it from extraction siblings like page_text or headings, which return narrow slices rather than a full Markdown rendering.

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 implied by "for LLMs" plus the note that nav/footer/scripts/cookie banners are removed, which hints at when full-page capture is preferable to targeted extraction tools. However, no sibling is named and there is no explicit when-not or alternative-selection statement, so routing remains inferential.

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.