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

With no annotations provided, the description carries the full behavioral burden. It discloses that each run terminates and relaunches the app (a side effect), times until the app is running and idle, and requires a specific automation agent and method. This goes beyond a mere definition and provides actionable behavioral context. No contradictions with any annotations (none exist).

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-loads the core purpose and key behavior (terminates/relaunches, averages over N runs), and includes the prerequisite method. Every sentence earns its place with no redundant or vague wording.

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?

There is no output schema, so the description should clarify what the tool returns. It says 'Measure COLD app-launch time (ms)' and mentions averaging over N runs, which strongly implies the return value is an average time in milliseconds, but it does not explicitly state the output format or whether additional data (e.g., per-run times) is provided. It also covers the key prerequisite (agent method). Given a simple measurement tool, this is a minor gap but still leaves some ambiguity about the response structure.

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 fully describes all three parameters (udid, bundleId, runs) with 100% coverage, including the default for runs. The description adds minimal extra meaning beyond the schema, such as clarifying that runs refer to cold launches and that each run terminates the app. It does not provide syntax or format details beyond what the schema already specifies, so a baseline score of 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?

The description states a specific verb ('Measure'), resource ('COLD app-launch time'), and scope ('for a bundle id, averaged over N cold launches'). It clearly distinguishes itself from the sibling android_app_launch_time by specifying iOS and cold launch semantics, leaving no ambiguity about what the tool does.

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 provides context on how it works (each run terminates and relaunches the app, times until idle) and mentions a prerequisite (on-device automation agent with device.perf.launchTime method), which helps an agent decide when to use it. However, it does not explicitly name alternatives or state when not to use this tool, leaving some inference to the agent given the sibling list. No exclusions are given.

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