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

Annotations already cover read-only/idempotent/no-destructive, and the description layers on real behavioral context: it is free, returns no review text, counts only reviews Rivioo holds in the window (not all reviews ever), and auto-collects newer reviews when held data is older than max_age_hours. The store-specific scoping (App Store per country vs Google Play per language across all countries) is information an agent could not infer from the schema alone.

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 the core purpose and tightly packed with no filler sentences, but it is a single long run-on paragraph where bullet-style grouping of store semantics and freshness rules would read faster. Every sentence still carries distinct 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?

An output schema exists so return values need no explanation; the description instead supplies the surrounding context an agent needs to call it correctly: window semantics, store-dependent country/language behavior, week boundaries, freshness/auto-collection, and cost. Nothing material is missing for an 8-parameter analytical read 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 coverage is 100%, so the baseline is 3, but the description adds cross-parameter meaning: how country behaves differently for ios versus android, that App Store results are per country, and that version/week groupings are ordered (newest first, weeks start Monday UTC). It does not restate the days/posted_from/max_age_hours mechanics, which the schema already handles.

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 and resource ('Exact rating distribution for one app over a window') and enumerates exactly what the distribution contains: total reviews, average rating, reviews per star, developer replies, breakdowns by version and by week. The closing 'returns no review text' cleanly separates it from rivioo_get_reviews.

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 use cases ('for ratings, versions and weekly trends, and before reading reviews to see when ratings changed'), which effectively routes the agent toward this tool before get_reviews. It never names an alternative sibling or states a when-not-to-use condition, so it stops short of the top mark.

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