get_perf_power_metrics

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows this is a safe read. The description adds useful context: metrics are aggregated from devices that opted into sharing diagnostics, and it covers 'recent versions', implying data scope. However, it does not disclose response size, pagination, or any other operational traits beyond these caveats. The added context is valuable but not extensive.

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 description is two sentences, front-loaded with the main purpose, and the second sentence adds relevant context (metric coverage and data source). No fluff or repetition. Every word earns its place.

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?

Given the tool's moderate complexity (4 parameters, 1 required) and the existence of an output schema, the description covers the core purpose, data scope, and aggregation source. It does not mention potential pitfalls or usage scenarios, but the schema and annotations fill most gaps. Slightly more detail on result granularity could push it to 5, but it is adequate as is.

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 all four parameters are well-documented in the input schema. The description repeats some metric names but adds little beyond the schema's own details (e.g., app_id is already explained as from list_apps, metric_type enum already lists options). Per calibration, with high schema coverage the baseline is 3, and the description doesn't compensate with extra meaning.

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?

The description clearly states the verb 'get' and the resource 'Xcode power and performance metrics of an app's recent versions'. It also enumerates the specific metric categories (launch time, hangs, memory, disk writes, battery, terminations), making it unambiguous what the tool retrieves. This distinguishes it from the sibling report/list tools which focus on reports, sales, finance, and 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?

The description implies usage when power/performance metrics are needed, but it does not explicitly state when to use this tool versus alternatives like fetch_analytics_report or other analytics tools. No exclusions or conditions are provided. The agent can infer the purpose but lacks explicit routing guidance.

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