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

With no annotations, the description carries the behavioral burden. It discloses the command, the averaging over N runs, and launcher-activity resolution. It stops short of stating that the -S flag force-stops the app and may disrupt running state, but the mechanism is explicit enough for an Android-aware agent.

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?

One dense sentence front-loads the outcome and then supplies method and scope. No filler or repetition of schema content.

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 no output schema, it tells the agent what the metric is (ms, averaged) and how it is obtained. It lacks an explicit statement of which am start timing field is reported (e.g., TotalTime vs WaitTime) and the force-stop side effect, but remains sufficient for basic invocation.

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 100%, so the schema already explains pkg, runs, and serial meaning. The description's 'averaged over N runs' and launcher resolution reinforce the parameters but add no new semantic detail beyond the schema.

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 measurable outcome ('Cold app-launch time (ms)'), names the exact command mechanism ('am start -W -S'), and distinguishes itself from sibling performance tools by focusing on launch latency rather than FPS, traffic, or general snapshots.

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 clearly implies when to use it: whenever cold app-launch duration is needed. It does not explicitly name alternatives or exclusions (e.g., warm launch or rendering FPS), but the cold-launch qualifier and measurement description provide enough context to select it.

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