Skip to main content
Glama

AI summary of text or a web page

text_summarize
Read-only

AI summary of up to 8,000 characters of text, or of a public web page URL (main content fetched through SSRF-validated redirects and converted to Markdown, first 30,000 characters). Length short, medium or long; format paragraph, bullets or json. Returns summary, key points, detected language, source URL and title, input size and truncation flag. Generated by Anthropic Claude under a fixed Kit Rx prompt; AI-generated text may omit or misstate details. Price: $0.006 per successful call, paid in USDC with x402 v2; failed calls and calls that match nothing are not charged. AI-generated answer; a call with no arguments returns the stored example answer without a model call.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "text_summarize"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNohttp or https URL of a public page to summarize instead of text. Default ports only; credentials, IP addresses, localhost and private or single-label names are rejected.
textNoText to summarize, up to 8000 characters (URL-encoded). Give text or url, not both.
formatNoparagraph (prose, default), bullets (summary as a Markdown bullet list) or json (plain-text summary without Markdown; key_points as standalone factual sentences).
lengthNoshort (one or two sentences, up to 3 key points), medium (about 80-150 words, 3-5 key points, default) or long (about 250-400 words, 5-8 key points).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations only supply readOnlyHint and openWorldHint, and the description adds substantial context beyond them: SSRF-validated redirects, a 30,000-character fetch cap, a fixed Anthropic prompt, an explicit accuracy disclaimer, and a per-call price with x402 v2 USDC payment where failures are not charged. The no-argument case returning a stored example answer without a model call is a genuinely useful behavioral disclosure, though the absence of output schema means expected latency/response shape is left implicit.

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-loads the purpose and input modes, then moves to output fields, provenance and pricing. It is a single dense block with little waste, though the pricing and example-answer sentences could be tightened without losing information.

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 contract itself and does so fully — summary, key points, detected language, source URL and title, input size, and a truncation flag. Combined with the input-mode rules and accuracy/charging caveats, an agent has everything needed to call it correctly and interpret results.

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% and both enum parameters (length, format) are fully documented in the schema, so the description mostly restates them. It adds minor value by pairing length with key-point counts and tying the 30,000-character limit to URL fetching, but nothing beyond the schema's own wording.

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 — 'AI summary' — and enumerates the two mutually exclusive input modes (text up to 8,000 chars, or a public web page URL). This cleanly separates it from sibling extractors like web_markdown, web_read and web_extract, which return content rather than a summary.

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?

The description establishes the input contract ('Give text or url, not both' in the schema, echoed in the intro) and notes the zero-argument behavior, but never explicitly says when to pick this over web_markdown or web_answer. Usage is implied rather than stated, so an agent must infer the routing decision from the verb alone.

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.

Resources