Skip to main content
Glama
Agency MCP Server

Agency MCP Server

Answer-engine visibility

answer_engine_visibility
Read-only

Measures how often a client is named in repeated language-model responses, with confidence intervals and baseline variance checks; uses a labelled mock provider when no endpoint is configured.

Instructions

Sends each prompt N times to the configured language-model endpoint and reports how often the client is named, with 95% intervals, and whether a change from a baseline exceeds run-to-run variance. Without an endpoint a mock provider is used and labelled as such.

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": {
      "client": "<client>",
      "prompts": "<prompts>"
    },
    "name": "answer_engine_visibility"
  }
}

Input Schema

NameRequiredDescriptionDefault
runsNoRuns per prompt, default 5.
clientYesClient id from the server's config (dental, cafe, plumber).
promptsYes
baselineNo
brandTermsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the agent knows external calls are involved and nothing is mutated. The description adds genuinely useful context beyond that: repeated sampling per prompt, statistical intervals, a baseline comparison against run-to-run variance, and a mock provider that is explicitly labelled when no endpoint is configured. It still omits cost/latency implications of fanning out N runs per prompt and the cap behavior on runs and prompts.

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?

Two tight sentences, front-loaded with the primary action and its output, followed by the fallback caveat. No filler, though the second sentence packs two distinct ideas (mock provider and labeling) into one clause.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter statistical tool with no output schema and only 40% schema coverage, the description covers the measurement mechanics well but leaves brandTerms undefined and gives no sense of result shape beyond "mention rate plus intervals." An agent can call it correctly but may pass brandTerms blindly.

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 only 40%, so the description has to carry weight. It explains runs ("N times"), prompts ("each prompt"), baseline ("whether a change from a baseline exceeds run-to-run variance"), and client ("how often the client is named"). brandTerms is never mentioned and would be opaque from the schema name alone, which is a real gap given the low coverage.

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 concrete verb chain and resource: it sends each prompt N times to a language-model endpoint and reports how often the client is named, with 95% intervals, plus a baseline-vs-variance comparison. That is far more specific than the title, though it never contrasts itself with the sibling tools (score_answerability, audit_page, etc.), so the agent gets an accurate purpose but no explicit differentiation.

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

Usage Guidelines2/5

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

There is no when-to-use statement, no prerequisites, and no alternative named. The agent can infer this is for measuring brand mention rates in LLM answers, and the mock-provider sentence hints at what happens without configuration, but nothing says when to pick this over score_answerability or when not to run it.

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