Skip to main content
Glama

Read a web page

read_page
Read-onlyIdempotent

Read a public web page as clean text, with headings kept as Markdown, plus title, description, language, canonical URL, Open Graph, schema.org types, outline and optionally links. Use it when you need the content of a page now. robots.txt is respected and results are cached 10 minutes; long pages are paginated.

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
urlYesPublic http(s) URL of the page.
max_lengthNoCharacters of text to return (default 8000).
start_indexNoCharacter offset to continue a long page (default 0).
include_linksNoAlso return the links found on the page (default false).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / include_links / description
      Previous value: -"Return the list of links (default false)"New value: +"Also return the links found on the page (default false)."
    • changedInput schema / properties / max_length / description
      Previous value: -"Characters of text to return (default 8000)"New value: +"Characters of text to return (default 8000)."
    • changedInput schema / properties / start_index / description
      Previous value: -"Character offset for long pages (default 0)"New value: +"Character offset to continue a long page (default 0)."
    • changedInput schema / properties / url / description
      Previous value: -"Public http(s) URL"New value: +"Public http(s) URL of the page."
  2. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly, openWorld, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely non-structured behavior: robots.txt is respected, results are cached for 10 minutes, and long pages are paginated. It does not say what happens on robots.txt block, non-public URLs, or fetch failure, which keeps it from a 5.

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?

Two sentences, front-loaded with the core purpose, then the returned metadata, then operational constraints. Every clause carries information an agent needs, and there is no filler or restatement of the name.

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?

With no output schema, the description properly takes on the job of describing return values and adds pagination, caching and robots.txt constraints for a network-facing tool. The only real gap is error/blocked-page behavior, which is minor for a read tool whose annotations already signal open-world access.

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 url, max_length, start_index and include_links are each already documented, which sets the baseline at 3. The description's note that long pages are paginated adds a little connective meaning to start_index but no format or interaction detail beyond the schema.

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?

The description gives a specific verb and resource ("Read a public web page") and enumerates what comes back: clean text, Markdown headings, title/description/language/canonical URL, Open Graph, schema.org types, outline, optional links. That is far more specific than the bare title. It stops short of naming a sibling (e.g. watch_page or request_resource) to contrast against, so it lands at 4 rather than 5.

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?

"Use it when you need the content of a page now" gives an implicit timing cue that hints at a watch/monitor alternative, but the alternative is never named and no exclusion is stated. An agent can infer the general context but must reason about the "now" vs. "watch" split on its own.

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.