Skip to main content
Glama

Read pages by URL

extract
Read-only

Fetch supplied URLs and return their page content as Markdown, HTML, or text for reading or processing; use when you already have URLs rather than needing to discover pages.

Instructions

Read pages you have URLs for, as markdown, HTML or text, in a few seconds. It reads, it does not find: URLs come from search, the user or a page. A page behind a login or clicks is browser_open's. provider='max' races every backend, one fetch each: only when the user wants speed over cost. data_apis: its site's vendor APIs, for call_vendor.

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": {
      "urls": "<urls>"
    },
    "name": "extract"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlsYesThe URLs to fetch, in the order the documents come back.
formatNoA backend that cannot produce it refuses rather than return another.
providerNo
data_apisNoAlso list each page's site's vendor data APIs; free, never run. On by default.
configured_onlyNoOnly data APIs whose credentials are set here.

Output Schema

NameRequiredDescriptionDefault
noteNo
handleYes
providerNo
documentsNo
truncatedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.13.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already establish readOnly and openWorld, and the description adds real behavior beyond them: relative latency ('in a few seconds'), the fan-out/cost profile of `provider='max'` ('races every backend, one fetch each'), and the read-vs-discover boundary that routes elsewhere. It does not cover failure modes (partial failures, per-URL errors) or limits on how many URLs can be submitted, 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and output formats, then routing rules — every clause carries information and nothing is padded. The telegraphic fragments ('A page behind a login or clicks is `browser_open`'s.') are slightly clipped but readable.

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?

An output schema exists, so return values need not be described; the description instead spends its space on routing, the provider cost tradeoff, and the data_apis chain. For a 5-parameter read tool with strong annotations, an agent has everything needed to select and call it correctly.

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 80%, and the description targets the gap: `provider` has no schema description, yet the description explains what 'max' actually does and its cost tradeoff. It also explains the purpose of `data_apis` (site's vendor APIs, feeding `call_vendor`), adding intent beyond the schema's mechanical wording. `configured_only` and the ordering nuance are left to 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 ('Read pages you have URLs for') plus the return formats (markdown, HTML, text), and explicitly draws the boundary against `search`: 'It reads, it does not find.' An agent can distinguish this from search/answer/browse without opening any schema.

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?

Gives concrete when-to-use (URLs come from `search`, the user, or a page), an explicit when-not/alternative (login-walled or click-requiring pages belong to `browser_open`), a conditional for `provider='max'` (only when speed matters more than cost), and the follow-on route for `data_apis` (use `call_vendor`).

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