Skip to main content
Glama

AI answer from web pages with verified quotes

web_answer
Read-only

AI question answering over 1 to 3 web page, PDF or DOCX URLs: grounded, cited RAG answers for research or fact checks. Pages are fetched with SSRF checks and read as Markdown (about the first 8k tokens each). Returns an answer of at most 150 words, claims with source URL and verbatim quote (checked in code against the page; unverified claims dropped) and confidence. 404, not charged, when the pages do not support an answer. AI-generated by Anthropic Claude. Price: $0.01 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

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": {
      "q": "<q>",
      "urls": "<urls>"
    },
    "name": "web_answer"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesQuestion to answer from the pages, 3 to 300 characters. Answered only from the pages' text.
urlsYes1 to 3 comma-separated http or https URLs of public pages or documents (HTML, PDF, DOCX, ODT, plain text). Default ports only; credentials, IP addresses, localhost and private or single-label names are rejected.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Discloses behavior well beyond the readOnly/openWorld annotations: fetching goes through SSRF checks, each page is truncated to about the first 8k tokens, output is capped at roughly 150 words, quotes are verified in code and unverified claims are dropped, and failures return 404 without charge. It even states the billing model ($0.01 per successful call via x402 v2/USDC) and which calls are free, which an agent cannot infer from any structured field.

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 purpose, then consequences (truncation, verification, cost, failure behavior) in a dense but scannable sequence. Minor waste: 'AI-generated by Anthropic Claude' and the closing 'AI-generated answer' repeat the same point.

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, and the description fully compensates by describing the return payload (answer capped at ~150 words, claims with source URL and verbatim quote, confidence score). For a paid, single-purpose RAG tool it leaves nothing an agent needs unknown.

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 the schema already documents both the question and the URL list, including the SSRF-related rejections. The description echoes the 1–3 URL limit and adds the useful constraint that pages are read only to ~8k tokens, but adds little else at the parameter level; baseline 3 applies.

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 question answering over 1 to 3 web page, PDF or DOCX URLs,' with the output shape named ('grounded, cited RAG answers'). This is clearly distinct from the extract/read/markdown siblings, which return page content rather than a synthesized answer.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an intended context ('for research or fact checks') and an implicit exclusivity rule ('Answered only from the pages' text'), plus a notable edge case where a no-argument call returns a stored example without a model call. It does not state when to prefer an extract or read sibling instead, so it stops short of full alternative routing.

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