get_perf_power_metrics

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

With no annotations provided, the description must carry the behavioral burden, and it does so well: it discloses that the metrics come from real-device MetricKit data, are aggregated, include regression insights, and can be narrowed to a single build. It doesn't discuss error cases or limits, but as a read-style 'get' tool there is no hidden destructive behavior to disclose.

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 packs a large amount of information into a single focused sentence and front-loads the core purpose. It is slightly dense because of the long metric list, but every clause contributes to describing what the tool returns or how to invoke it.

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 a moderate number of optional parameters, a fully covered schema, and no output schema, the description provides enough context to understand the scope, invocation pattern, and returned data categories. The only minor gaps are lack of explicit edge-case behavior when both app_id and build_id are passed and no mention of date or pagination behavior.

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?

The schema already describes all five parameters well, but the description adds meaning beyond it by clarifying the app_id/build_id relationship as an either/or and mapping metric categories to concrete real-world quantities like launch time, hang rate, memory, disk writes, and battery. That is useful semantic context the schema alone does not fully express.

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 uses a specific verb and resource ('Get aggregated power and performance metrics') and adds the concrete data source (MetricKit data from real devices). It also names the exact metrics returned and the Apple regression insights, which makes it easy to distinguish from sibling reporting tools like get_build_usage_metrics.

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 clear context for when to use the tool: for an app's recent versions or for a single build, and states the key dispatch rule 'Pass either app_id or build_id'. It does not explicitly name alternatives or exclusions, but the intended usage is clear enough without leaving the agent guessing.

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