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

Annotations already declare the safety profile (readOnly, idempotent, non-destructive), so the description's job is to add behavior — and it does: response includes real counts and shares, a Revunda page link, and a covered:false outcome with a redirect link for uncovered apps. What's missing is any hint about latency, coverage limits or how many themes come back.

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?

Two sentences, front-loaded with the value proposition, then the input rules and the failure path. Nothing is wasted, though the second sentence strings four input formats together and could be a touch tighter.

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?

With no output schema, the description carries the return-value burden and does it partially — themes, counts, shares, page link, covered flag. An agent would still be guessing whether the store filter changes the result set or just disambiguates, but nothing critical is missing for a correct call.

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?

Schema coverage is 100%, so the baseline is 3; the description earns the bump by giving concrete example values for the app parameter ('AccuWeather', 'com.commbank.netbank', 'judgeme') that show the accepted formats faster than reading the schema alone. The store enum is left entirely to the schema, which is acceptable.

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?

Opens with a specific verb+resource: 'Top complaint themes in an app's low-star reviews, with real counts and shares.' That clearly separates it from list_covered_apps and estimate_one_star_cost, though it never explicitly names what_users_complain_about, which sounds adjacent.

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 gives concrete guidance on accepted input forms and the uncovered-app fallback, which is genuinely useful. But it never states when an agent should pick this over what_users_complain_about or when to set the store filter, so routing between siblings is left implied.

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