Skip to main content
Glama
Sign In

CiteHawk

by com.citehawk
OverviewDiscussionsAdmin

Citation evidence

get_evidence
Read-only

The real AI answers (last 30 days) that cite a given domain, optionally narrowed to answers that also mention a specific brand. Returns provider, the prompt asked, an answer excerpt, the exact cited URL and the date. A row also carries polarity and aspect when that exact citation sits behind an attributed sentiment quote about the brand, and supportedSentences (verbatim from the answer) when the AI model tied the cited page to specific sentences: quote those to show what the source was used for. Use to verify a claim with the underlying AI responses.

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": {
      "domain": "<domain>"
    },
    "name": "get_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
brandNoOptional brand name. Only answers that also mention this brand are returned.
limitNo
domainYesThe cited domain to fetch evidence for, e.g. "g2.com".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare that the operation is read-only, non-destructive, and closed-world, so the description adds meaningful context beyond that: the 30-day window, exact returned fields, conditional polarity/aspect fields, and supportedSentences semantics. It does not discuss ordering or pagination behavior, which leaves a minor gap.

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?

The core operation is front-loaded in the first sentence, followed by return fields and conditional row semantics. The sentence covering polarity, aspect, and supportedSentences is dense but each clause carries useful meaning, and there is no filler.

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 carries the return-value burden and does so thoroughly: provider, prompt, answer excerpt, cited URL, date, conditional polarity/aspect, and verbatim supportedSentences. It also explains how to use supportedSentences to show what the source was used for, which is the key interpretive context for this evidence tool.

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 coverage is 67%, with domain and brand described in the schema but limit not described. The description reinforces that domain is the cited domain and brand narrows to answers that also mention the brand, but it adds little syntax or meaning beyond the schema and does not compensate for the undocumented limit parameter.

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 states a specific retrieval action: real AI answers in the last 30 days that cite a given domain, optionally narrowed by brand, with a listed set of returned fields. It does not name sibling tools, but the citation-level evidence focus distinguishes it from higher-level summary or ranking tools.

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?

It explicitly says to use the tool 'to verify a claim with the underlying AI responses,' giving a clear use case, and explains the optional brand narrowing condition. It does not say when to choose sibling tools such as get_source_gaps or get_rankings instead.

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

All CiteHawk 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