Top apps by downloads, revenue or active users

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

Goes well beyond readOnlyHint and openWorldHint by disclosing that revenue is returned in cents and converted to *_usd, that the 213-key custom_tags blob making up 94% of each row is dropped unless requested, and that iOS device_type defaults to iphone. These are non-obvious output and defaulting behaviors. It stops short of covering pagination behavior (offset/limit interactions) or error modes.

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?

Four dense sentences, each carrying a distinct behavioral fact (routing, cents conversion, blob dropping, iOS default). No filler, and the measure-routing rule is front-loaded. The unusual multi-clause sentences are justified by the density of 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?

For a 16-parameter read-only tool with no output schema, the description covers the highest-value surprises: measure-based endpoint switching, currency conversion, cost/width of custom_tags, and the iOS device_type default. It omits any coverage of limit/offset/pagination semantics and end_date behavior, which is a gap for a leaderboard tool that expects date ranges.

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 75%, and the schema itself already documents many parameters. The description adds real value for measure routing and device_type defaults, but it doesn't address the remaining parameters like limit, offset, time_range, comparison_attribute, resolve_names, dry_run, or format beyond what the schema says. Baseline 3 given the partial schema coverage and mixed added value.

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 the exact resource (the estimate-based leaderboard) and splits behavior by measure value, distinguishing the sales-estimate leaderboard from the active-user leaderboard. This is a precise verb+resource framing that sets it apart from sibling tools like sensortower_top_charts or sensortower_app_estimates.

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?

Explains the internal measure routing and notes iOS device_type is de-facto required, which implies when certain options must be set. However, it never says when to choose this tool over siblings such as sensortower_top_charts, sensortower_app_estimates, or sensortower_app_active_users. Usage is implied rather than explicitly contrasted with alternatives.

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