Skip to main content
Glama
Sign In

Vouch

by com.clawhard
OverviewDiscussionsAdmin

Check whether a web page really contains a quote

vouch_check_quote
Read-onlyIdempotent

Use when a quote, a statistic or a claim is attributed to a web page and the user asks whether the source says it, or before a citation goes into an answer, report, article or essay (signals: "does this article actually say", "verify this quote", "is this citation real", "check the source", "did they really write that", "fact-check this quote against the link"). Fetches the page once, extracts its visible text and returns per quote a verdict: exact (word for word), normalized (same words in order; only punctuation, capitals, spacing or curly quotes differ), close (similarity 0.85 or more, wording differs), partial (0.5 to 0.85) or not_found, with the matching passage, surrounding context, the words that differ and numbers_differ when a number changed (for example 1914 in the quote, 1912 on the page). Quotes with "..." are checked part by part. Example: {"url":"https://en.wikipedia.org/wiki/Alan_Turing","quotes":["widely regarded as the father of theoretical computer science"]}. Limits: a match shows the words are on the page, not that the claim is true; pages built by JavaScript may have little text in their HTML; PDFs and paywalled or bot-blocked pages cannot be read; up to 10 quotes of 1000 characters, at least 3 words each.

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>",
      "quotes": "<quotes>"
    },
    "name": "vouch_check_quote"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe http or https address of the source page (an article, doc, blog post, Wikipedia page or plain-text file).
quotesYes1 to 10 quotes or claims to look for, as written in the draft (at least 3 words each).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare read-only, open-world, idempotent and non-destructive; the description goes far beyond by disclosing the verdict taxonomy with numeric thresholds (exact/normalized/close at 0.85/partial 0.5-0.85/not_found), the numbers_differ signal, and that '...' quotes are checked piecewise. It also states the key epistemic limit that a match proves the words are on the page, not that the claim is true.

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?

Content is front-loaded and nearly every sentence carries information — triggers first, then behavior and verdict scale, then an example, then limits. The long parenthetical list of signal phrases is somewhat verbose and could be trimmed without losing routing value.

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?

With no output schema, the description fully compensates by enumerating each verdict value and the returned artifacts (matching passage, surrounding context, differing words, numbers_differ). Limitations and a concrete example round it out so an agent can call it and interpret results without further information.

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 the baseline is 3, but the description adds real meaning: quotes are 'as written in the draft', capped at 10 quotes of 1000 characters and at least 3 words each, and elaborates the multi-segment '...' behavior that the schema does not express. The url parameter itself gets no added detail beyond 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?

The description states a specific verb and resource (check whether a web page contains a quote) and elaborates the mechanism: fetch once, extract visible text, return a per-quote verdict. It is clearly distinguishable from the sibling vouch_check_links, which is about links rather than text presence.

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?

It names explicit trigger conditions ('quote, statistic or claim attributed to a web page', 'before a citation goes into an answer') and lists concrete user phrasings that should route here. It also states where the tool cannot help (PDFs, paywalled or bot-blocked pages, JS-rendered pages), which functions as clear when-not-to-use guidance.

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

All Vouch toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources