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

Annotations already declare read-only, idempotent, non-destructive behavior, so safety is covered elsewhere. The description adds genuine interpretation context that the schema cannot: Android stats are aggregated from recent reviews while iOS reports the current version plus release notes — a caveat that materially affects how results should be read.

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?

The returns are front-loaded and every clause carries information; the platform-specific fragments are terse but purposeful. The telegraphic style is slightly dense but wastes no sentences.

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 must convey what comes back, and it names the three key metrics plus the per-platform aggregation behavior. An agent could call this correctly; only ordering/pagination and version-listing depth are unaddressed.

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%, and the schema itself explains appId formats, store inference, and the country default. The description adds nothing about parameters, which is acceptable given the schema does the work — baseline 3.

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 the resource precisely — per-version review stats with the three returned fields (review count, average rating, first/last seen) — so it's clearly distinct from get_app_reviews. It doesn't name a sibling explicitly, but the version-granularity scope makes the split obvious.

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?

The phrase 'spot a rating crash right after a bad release' gives a concrete use scenario, which is more than many tools offer. However, it never says when to prefer get_app_reviews or get_pain_trend instead, nor any exclusion criteria, so the routing decision is left to inference.

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