Skip to main content
Glama

radveo

check_ai_visibility

Score how ready a local business is to be named when people ask AI engines (ChatGPT, Gemini, Google AI) for a recommendation in its category, and get a shareable Radveo report with the exact fixes to improve its odds. Scores readiness from the business's own site; it does not query an engine live. Honest answer-engine optimization: improves the odds of being cited, never guarantees a placement.

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": "check_ai_visibility"
  }
}

Input Schema

NameRequiredDescriptionDefault
websiteNoThe business website URL, e.g. https://joesplumbing.com. Optional if business_name is given; improves accuracy.
locationNoCity or region, e.g. "Seattle, WA". Optional but improves accuracy.
business_nameNoThe business name, e.g. "Joe's Plumbing". Provide this OR a website.

Output Schema

NameRequiredDescriptionDefault
okYesFalse when the check could not be completed (bad input, rate limit, or the audit engine timed out).
noteYesHonesty framing: an indicative, measured read of how AI assistants tend to answer, never a guarantee of placement.
verdictYesWhether AI engines named this business when asked customer-style recommendation questions. 'named' = at least one query named it; 'absent' = confidently not named; 'unknown' = the engines could not give a confident read; 'not_checked' = the live AI-answer probe did not run for this call (the on-page audit still did).
businessNoThe business name or website that was checked.
seoGradeNoLetter grade (A-D) for the readiness score, when measured.
seoScoreNo0-100 on-page AI-visibility readiness score, when measured.
topFixesNoThe top fixes to improve the odds of being named (max 3 here; full list in the report).
reportUrlYesShareable, public report URL for this check.
enginesCheckedNoThe AI engine panel the probes consult: an indicative read of how AI assistants tend to answer, not a live probe of every public engine.
queriesCheckedNoThe customer-style questions asked to the AI engines (empty when the probe didn't run).
competitorsNamedNoBusinesses surfaced instead of this one (deduped). Same list the public shareable report shows.
aiVisibilityScoreNo0-100: the share of customer-style AI queries that named the business. Null when the probe didn't produce a measured score.
competitorsSourceNo'ai' = an AI engine named them; 'places' = real local leaders from Google's local results (shown when the engines named none). Null when no competitors surfaced.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / reportUrl / description
      Previous value: -"Free, shareable, public report URL for this check."New value: +"Shareable, public report URL for this check."
  2. Changed1 schema field changed
    • changedOutput schema / properties / note / description
      Previous value: -"Honesty framing: results improve odds and show what AI says today, never a guarantee of placement."New value: +"Honesty framing: an indicative, measured read of how AI assistants tend to answer, never a guarantee of placement."
  3. Changed2 schema fields changed
    • changedOutput schema / properties / enginesChecked / description
      Previous value: -"The AI engine panel the probes consult — an indicative read of how AI assistants tend to answer, not a live probe of every public engine."New value: +"The AI engine panel the probes consult: an indicative read of how AI assistants tend to answer, not a live probe of every public engine."
    • changedOutput schema / properties / note / description
      Previous value: -"Honesty framing: results improve odds and show what AI says today — never a guarantee of placement."New value: +"Honesty framing: results improve odds and show what AI says today, never a guarantee of placement."
  4. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Beyond the annotations, the description discloses that scoring is based on the business's own site, that no live engine query occurs, that it produces a shareable report, and that placement is never guaranteed. It does not fully explain the side effects or persistence implied by readOnlyHint=false when generating that report.

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 description is three sentences and front-loads the purpose before stating the critical live-query limitation. It is mostly efficient, though the closing 'Honest answer-engine optimization' sentence is slightly marketing-oriented and could be tighter.

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

Completeness4/5

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

An output schema exists, so return-value details need not be explained in the description. The description covers purpose, data source, limitation, and expectation setting; the main gap is explicit routing against the sibling 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 description coverage is 100%, and the schema already documents website, location, and business_name with their optionality and examples. The description reinforces that website data is the source, but it adds no further parameter constraints or meanings beyond the schema.

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 action, scoring a local business's readiness to be named by AI engines, and a concrete outcome, a shareable Radveo report with fixes. It is clearly distinct from a live engine query, but it does not explicitly distinguish itself from the sibling how_to_appear_in_ai_search.

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 gives an important usage boundary: it scores readiness from the business's own site and does not query an engine live. However, it does not explicitly say when to choose this tool versus the sibling guidance tool, nor does it state prerequisites or alternatives.

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