Irmu

Ask ChatGPT

chatgpt

Ask ChatGPT a question through a browser on chatgpt.com and return its answer as structured nodes in conversation -- paragraphs, headings, lists, tables and the sources it cited. Useful to see what ChatGPT tells its users about a topic or brand. Spends a flat number of credits, refunded if ChatGPT does not answer. Answers can take a minute or two: if status is "queued" or "running", call crawl_poll with the job_id to collect it.

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": {
      "prompt": "<prompt>"
    },
    "name": "chatgpt"
  }
}

Input Schema

Name	Required	Description
`city`	No	The city inside that country to appear to browse from, as the pool spells it: letters, digits, hyphens or underscores, e.g. berlin or new_york. Requires country. Doubles the price of the crawl.
`prompt`	Yes	What to ask ChatGPT, as a person would type it.
`country`	No	The country to appear to browse from, as a two-letter ISO 3166-1 code such as es, us or de. Free. Required to use city.
`premium`	No	Fetch through the premium proxy pool instead of the standard one. Costs more; use it for targets that refuse ordinary requests.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 1, 2026

TDQS

A4/5.0

Behavior4/5

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

Goes well beyond the annotations: flat credit cost with refund if ChatGPT does not answer, expected latency of a minute or two, and the async queued/running status model. Missing auth/rate-limit context and what a failed-but-charged case looks like, but the cost and async behavior are the operationally important disclosures.

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 what the tool does and what it returns, then cost, latency, and the polling escape hatch — each sentence carries information. Slightly dense in one paragraph but 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 still describes the return payload (typed conversation nodes plus cited sources), the async completion path, cost and refund behavior, and latency expectations. An agent has everything needed to call it and handle the non-terminal status.

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 100%, so `prompt`, `country`, `city` and `premium` are already fully documented in the schema, including pricing effects. The description adds no parameter-level detail of its own beyond a generic mention of flat credits, so the baseline 3 applies.

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?

States a specific verb+resource ('Ask ChatGPT a question through a browser on chatgpt.com') and even the return shape ('structured nodes in `conversation` -- paragraphs, headings, lists, tables and the sources it cited'). It does not contrast with the closest sibling, `google_ai_overview`, so an agent must infer which answer-engine tool to pick.

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 a concrete use case ('see what ChatGPT tells its users about a topic or brand') and an explicit handoff rule: if `status` is queued or running, call `crawl_poll` with `job_id`. No explicit when-not-to-use condition relative to `google_ai_overview` or `crawl`.

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

All Irmu tools Inspect

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

Need Help?