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

Annotations already declare read-only, idempotent, non-destructive and open-world, and the description layers on real operational context: an API key or connected account is required, billing is 1 credit per call, and it is excluded from the free tier. It also discloses accuracy limits per storefront (never above medium for review-derived iOS installs) and enumerates the returned fields, which annotations cannot express.

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 purpose and the return-field list are front-loaded, then the store-specific caveats follow in a logical order. The single dense paragraph is slightly heavy, and the `source` values are mentioned twice, but no sentence is filler given the absence of an output schema.

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 full burden of explaining return values, and it does so field by field (`monthly_range`, `installs` with estimate/low/high/source, confidence grade with factors, methodology). Combined with auth, cost, and per-store accuracy caveats, an agent has everything needed to call it and interpret the result responsibly.

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 goes further by explaining why `store` matters — iOS installs come from rating counts (`source: review_derived`) while Android exposes a public count with no range. It adds nothing extra for `country` beyond the schema's own ISO-code explanation.

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 — "Estimate monthly revenue for an app" — plus the signals the model uses (installs, ratings, category benchmarks). The closing line "The figure is a model estimate, not reported revenue" implicitly separates it from the actual-sales sibling, so an agent can pick between them without opening a 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?

Gives strong situational guidance: on iOS the install base is derived and estimates are capped at medium confidence, so the caller is told to "quote the range rather than the point figure"; on Google Play there is no install range. It never names a specific sibling alternative (e.g. sonar_app_sales) by name, which keeps it short of a 5.

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