Downloads and revenue estimates

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

Annotations cover the safety profile (readOnlyHint, openWorldHint), but the description adds substantive behavior the annotations cannot: the three per-OS key sets are collapsed to a common shape, revenue is converted from cents to USD, and a request's cost is independent of the date span. That cost/pricing disclosure is genuinely useful context beyond the structured fields, though permissions or rate limits are not addressed.

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?

Three sentences, zero padding: purpose first, then the normalization/unit contract, then the cost-driven batching rule. Each sentence carries distinct, decision-relevant information and nothing is repeated.

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?

For an 11-parameter, read-only, open-world tool with no output schema, the description supplies the key missing context: what the returned rows look like after normalization and how units are expressed. Pagination/truncation behavior (the limit param) is only covered by the schema, keeping it just short of complete.

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 all 11 parameters, including the raw flag's effect, the os id formats, and the fields allowlist. The description restates the normalization/units behavior that the raw parameter toggles but adds little parameter-level detail beyond it; baseline 3 is appropriate.

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?

Names a specific resource and scope: 'Download and revenue estimates per app, country and period', and even enumerates the normalized output columns (app_id/country/date/downloads/revenue_usd). An agent knows exactly what data this returns, but the description never names or contrasts a sibling (e.g. app_active_users or app_rank), so it stops short of a 5.

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 strong operational guidance about batching ('Widen the date range rather than looping: one request covering three months costs exactly what one covering a day costs'), which tells the agent how to call it efficiently. However, there is no explicit when-to-use-this-vs-alternatives statement or prerequisite guidance; selection among the many sensortower_app_* siblings 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.