Skip to main content
Glama

Ask ChatGPT a buyer question

check_chatgpt_answer
Idempotent

Ask ChatGPT one question a buyer would ask (for example "What is the best invoicing tool for freelancers?") and see whether a brand is named in the answer, in which position among the options it lists, what it says about it, whether it cites the brand's site, and which sites it cites. The question runs once in ChatGPT's web app (logged out, through a collection service) and takes a few minutes: the first call starts it, then call again with the same domain and question to get the answer (no extra cost). One free new question a day per user; an answer someone already got today is shared. Use this for "does ChatGPT recommend us?" or "why does ChatGPT pick our competitor?".

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>",
      "question": "<question>"
    },
    "name": "check_chatgpt_answer"
  }
}

Input Schema

NameRequiredDescriptionDefault
brandNoThe brand name as written in answers, if it differs from the site's own name
domainYesThe brand's website, for example acme.com
countryNoTwo-letter country to ask from, default US
questionYesThe buyer question, in the buyer's words; don't name the brand in it

Output Schema

NameRequiredDescriptionDefault
statusYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Goes far beyond the annotations by disclosing that the query runs in ChatGPT's web app logged out via a collection service, that it takes minutes, and that the call is asynchronous — first call starts it, a repeat call with the same domain+question retrieves the result. It also discloses quota and caching behavior (one free question a day, answers already fetched today are shared). These details are exactly what explains readOnlyHint=false and idempotentHint=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?

Front-loaded with the outcome, then the async mechanics and quota, then the use cases. The long first sentence is justified by the number of distinct outputs it must signal, though the enumeration could be tightened slightly.

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 an async, quota-limited, open-world tool this covers everything an agent needs: the required polling protocol, latency expectation, cost/quota rules, and shared-answer semantics. Return shape is handled by the existing output schema, so nothing essential is missing.

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%, so the schema already documents domain, brand, country, and the buyer-voice question constraint. The description adds only one parameter-adjacent detail — that polling must reuse the same domain and question — so the baseline of 3 applies.

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?

States a specific action (ask ChatGPT one buyer question) and enumerates exactly what is returned: brand named, position, what it says, whether it cites the brand site, and which sites it cites. The parenthetical example question plus the 'does ChatGPT recommend us?' framing make it immediately distinguishable from retrieval siblings like get_answer.

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?

Gives concrete use contexts ('does ChatGPT recommend us?', 'why does ChatGPT pick our competitor?') and explains the operational condition that governs usage: one free new question per day per user, shared answers, no extra cost on the polling call. It never explicitly names an alternative sibling (e.g., get_answer vs get_answers), so routing against those remains inferred.

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