Skip to main content
Glama

Visibility Genies

Find questions people ask

find_questions

Buys Questions: up to 200 questions people search about a topic (found by question words in the market's language: English, German, French, Spanish, Italian, Dutch and Portuguese have their own, and other languages use the English ones), most searched first, each with Google search volume, difficulty, AI search volume, and the People Also Ask question on the topic's saved SERP analysis it rewords (about 70% of its words shared), with each People Also Ask question listed. Estimated price up to $0.14 per topic: the questions, then AI search volume only for questions with none saved. Questions bought in the last 24 hours, and AI search volume already bought for a keyword in this project and market, are read at no charge, and every purchase opens free on the Questions page. The SERP is only read, never bought. Each call may spend up to the workspace's agent spend limit ($2.00 unless changed in Settings) without asking: it holds at most its estimate plus a margin while it runs and is charged what it bought, never more. A call whose maximum is above the limit is refused before anything is bought, with its estimate and maximum: ask the user, then call again with approvedMaxCostUsd set to the amount they approved.

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": {
      "projectId": "<projectId>",
      "topic": "<topic>"
    },
    "name": "find_questions"
  }
}

Input Schema

NameRequiredDescriptionDefault
topicYesThe topic, such as a product, service or subject: 'coffee', 'running shoes'.
projectIdYesRequired. The Visibility Genies project this call works in and is billed to. Call list_projects to find one.
languageCodeNoLanguage code such as en, es or vi. When left out, the language of the project's default market is used (see list_projects).
locationCodeNoMarket location code, for example 2840 for the United States. When left out, the project's default market is used (shown by list_projects and changed in project settings). A few countries, Iceland (2352) among them, only have Google Ads data: search volume, CPC and trends are available there, but keyword difficulty, search intent and domain analytics are not.
approvedMaxCostUsdNoThe most, in USD, the user approved for this call after seeing its estimate and maximum. Only needed after a call was refused for costing more than the workspace's agent spend limit; never set it without asking the user.

Output Schema

NameRequiredDescriptionDefault
costNo
metaNo
boughtYes
savedAtYes
questionsYes
savedResultIdNo
aiSearchVolumeErrorYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Far beyond the annotations: it states the estimated price (up to $0.14 per topic), what is charged versus read free, that the SERP itself is only read and never bought, that the call holds its estimate plus a margin, and that a call above the spend limit is refused before anything is purchased. The refusal-then-approve flow is exactly the kind of spend behavior an agent must know before invoking a paid tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded with the payload (what is bought) and word-efficient, but it is delivered as one very long run-on sentence with deeply nested parentheticals, which makes the cost and approval rules hard to extract on a first read. The information earns its place; the packaging does not.

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?

For a paid, open-world search tool with an output schema and full parameter documentation, nothing material is missing: the description covers what is returned, what is billed, what is free, what happens on limit refusal, and the exact follow-up call. Return format is left to the output schema, as appropriate.

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 description coverage is 100%, so baseline is 3; the description adds genuine meaning on top by explaining that approvedMaxCostUsd should only be set after showing the user the refused call's estimate and maximum, and by tying languageCode to the market's question-word language set. It does not, however, add anything to topic or locationCode 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 opens with a specific verb and resource ("Buys Questions") and immediately bounds the scope: up to 200 questions people search about a topic, ranked by search volume, each carrying volume, difficulty, AI search volume and People Also Ask data. That is much more than a restatement of the name and lets an agent tell this apart from a plain question-retrieval sibling such as get_saved_questions.

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 gives real operating guidance: which calls are free (questions bought in the last 24h, AI search volume already bought for the keyword in this project and market) versus billed, and a concrete escalation path when the call exceeds the workspace spend limit. What it lacks is explicit routing to alternatives, e.g. when to read already-saved questions instead of buying new ones.

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