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

Annotations declare a non-readOnly, non-destructive, non-idempotent operation but do not explain why. The description fills that gap well: it discloses that each run terminates and relaunches the app, that timing runs until the app is 'running and idle', and that an auto-started on-device agent plus a required method are involved. This is meaningful side-effect and prerequisite disclosure beyond the annotations.

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, each carrying distinct information (what is measured, how each run works, and the required environment). The core measurement is front-loaded with no filler.

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 3-param tool with no output schema and full annotation coverage, the description supplies the measurement unit, the cold-launch procedure, and the agent prerequisite. Only the return shape (e.g., per-run vs aggregate values) and failure behavior are left implicit, which is a minor gap.

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 udid, bundleId, and runs are already documented with defaults and bounds. The description reinforces 'N cold launches' and the ms unit but adds no syntax, format, or constraint detail beyond the schema, so the baseline 3 applies.

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+resource+measurement unit ('Measure COLD app-launch time (ms) for a bundle id') and pins down the exact semantics (cold, averaged over N launches). An agent can distinguish it from ios_fps, ios_performance_snapshot, and android_app_launch_time without opening any 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?

It gives an implied usage context (cold-launch benchmarking) and a prerequisite ('the agent runner must include the device.perf.launchTime method'), which is genuinely useful. However, it never states when to prefer this over siblings like ios_performance_record_start or ios_performance_snapshot, nor any when-not conditions, so usage is mostly inferred.

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