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

Adds real context beyond the annotations: it is free, Apple publishes no volumes so a suggested search is used as a proxy ('a suggested search is one people make'), and the latest check per country is retained for the grow flow — which also explains why readOnlyHint is false. It does not disclose rate limits or the shape of the returned rows.

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

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

Front-loaded with what is checked, then the verdict taxonomy, then the parameter guidance. It is dense and semicolon-heavy, and the closing 'Free; the latest check per country is kept for grow' is cryptic, but essentially every clause carries information.

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

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

No output schema exists, and the description compensates by defining all seven verdicts and the four signals reported per search. The only gap is that nothing explains what appId defaults to or how results are keyed when the app is not passed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Goes well past the 75% schema coverage: it constrains the search strings to the country's language, gives the recommended 3-10 count (versus the schema's looser 1-20), and explains that expand adds Apple's longer suggestions 'up to 20 in all' — a total cap the schema does not express.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a precise verb and resource — checking App Store searches in one country and reporting rank, suggestion status, competitor naming, and top-5 ratings — and enumerates the verdict vocabulary. An agent can tell this apart from keyword_research or search_positions 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.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It says to pass 3 to 10 searches in the country's language sourced 'from the listing, the repo and the reviews' own words', and notes expand is on by default. That is concrete usage context, but it never names an alternative sibling (keyword_research, search_positions) or states when not to use this tool.

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