Irmu

Google AI Overview

google_ai_overview

Search Google for a query and return the AI Overview Google shows above the results, with the sources it cites. ai_overview is null when Google showed none for that query. Spends a flat number of credits. 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": {
      "query": "<query>"
    },
    "name": "google_ai_overview"
  }
}

Input Schema

Name	Required	Description	Default
`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.
`query`	Yes	What to search Google for.
`domain`	No	The Google domain to search, as its extension: com, de, co.uk, es. Pair it with country so the search exits there too.	com
`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.

First observedOct 31, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already cover openness and non-destructiveness, and the description adds real behavioral context beyond them: flat credit cost, the null-return case, and the async job/status handoff to crawl_poll. It doesn't quantify the credit cost or describe failure modes, so not a 5.

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

Conciseness5/5

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

Four tight sentences, front-loaded with the core action and return value, followed by the null case, cost, and async follow-up. No filler and every sentence carries actionable information.

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?

With no output schema, the description covers the return shape (AI Overview plus cited sources) and the null case, and it explains the async polling path, which is the key operational gap. Minor omissions like error/rate-limit behavior and credit magnitude keep it from 5.

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 each parameter (city, country, domain, premium) is documented with its cost and pattern constraints in the schema. The description adds no parameter-level meaning beyond that, so the baseline 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 verb and resource ('Search Google ... return the AI Overview ... with the sources it cites'), and the AI-Overview focus clearly distinguishes it from the generic crawl/search siblings. An agent can tell what it returns without opening the schema.

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?

Explicitly routes the agent onward: if status is 'queued' or 'running', call crawl_poll with job_id. It also documents the null-result condition. It doesn't explicitly say when to prefer this over the plain crawl tool for non-AI-Overview needs, so it stops short of full when/when-not guidance.

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?