summarize_reviews

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

Goes well beyond the annotations: annotations only flag readOnlyHint=false and idempotentHint=false, while the description explains the credit/allowance billing model, the caching-by-day-and-batch behavior, and the 'too_few' state response. This is exactly the kind of cost/side-effect detail an agent needs to avoid surprise charges.

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 purpose, then cost behavior, then edge case. Generally tight, though the credit/allowance sentence is dense and could be split for readability.

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 helpfully sketches the return shape (themes with quoted evidence) and the 'too_few' state with a count. Missing only explicit return/failure semantics beyond that one state, but strong overall for a 4-param tool.

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 description coverage is 100%, so the schema already documents lang, appId, store, and country including defaults. The description adds only 'one app in one storefront', which reinforces single-target scoping but no syntax or format detail beyond the schema's baseline.

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?

States a specific verb (summarize) and resource (reviews) scoped to 'one app in one storefront', and the sub-detail (themes — complaints, requests, praise — with quoted evidence) clearly separates it from sibling get_reviews/search_reviews, which return raw reviews rather than an AI summary.

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?

Gives explicit usage context: cache reuse (same day + same batch = stored summary at no allowance) vs a new summary (one Review AI credit), plus the 'too_few' fallback. However, it never names an alternative tool for raw or filtered review reading, leaving the get_reviews/search_reviews choice to inference.

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