Skip to main content
Glama

Read a web page as clean text

read_page
Read-only

Read any public web page and get its visible text back: the words a person would see, with navigation and boilerplate stripped, plus the title and final URL after redirects. JavaScript pages are rendered in a real browser first. Up to 50,000 characters.

Use it to read an article, a doc, a policy or any page you were given a link to. Chain it with a summarizer when the page is long.

$0.002 USDC per page over x402. A page that fails to load, returns an error or has no text costs nothing. Call without payment to get a quote.

When to use: You have one page URL and need its words: an article, doc, policy or listing. Use instead: read_pages for 2-5 URLs (one payment); page_brief for a summary instead of the full text; pdf_to_text for a PDF; screenshot_page for how it looks; attest_page if you may need to prove what it said. Parameters: url must be absolute http(s) and public (no logins, no private addresses). Returns: title, final_url after redirects, text (visible text, up to 50,000 characters), text_length and truncated.

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": "read_page"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesAbsolute http(s) URL of a public page.
paymentNoBase64 x402 payment payload. Omit it to receive a quote; sign that and call again.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations cover read-only and open-world, but the description adds substantial context they don't: a live browser render for JS pages, the 50k truncation cap, redirect resolution in final_url, and a full cost model ($0.002/page, failures and empty pages free, quote-then-sign payment flow). It does not discuss rate limits or anti-bot blocking, which for a scraper is the notable remaining gap.

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 outcome, then progressively detail on cost, alternatives, params and returns — easy to scan. Slightly verbose, since the 'Returns' line partially repeats the opening sentence and the payment flow is stated twice (cost sentence and payment parameter).

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 compensates by enumerating the return fields (title, final_url, text, text_length, truncated). Combined with cost, failure semantics and limits, an agent has everything needed to call this 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% so baseline is 3, but the description adds real meaning: url must be absolute http(s) and public, with no logins and no private addresses — a constraint that shapes URL selection. It also explains the quote-then-sign two-call pattern for payment, which the schema only hints at.

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 ('Read any public web page and get its visible text back') plus scope detail: boilerplate stripped, title, final URL after redirects, JS rendering, 50,000 character cap. It is immediately distinguishable from read_pages, page_brief, pdf_to_text and screenshot_page.

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?

Explicit 'When to use' (one page URL, need its words) and an explicit 'Use instead' routing table naming five siblings with the condition that selects each (2-5 URLs, summary, PDF, visual, proof). Nothing is left to inference.

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.