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

With no annotations provided, the description carries the full burden and excels. It discloses the multi-step process (control channel, fallback to `am force-stop`, verification via `pidof`), handles edge cases (persistent apps like Samsung FGS resurrection), and specifies the exact return shape. This is far more transparent than typical tool descriptions, providing the agent with a clear mental model of behavior.

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 a single, dense sentence that front-loads the core action and then layers in fallback, verification, and return details. It is concise without being terse, though the string of clauses could be slightly easier to parse. Still, it earns its length by covering key behavioral aspects.

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?

The description covers the process, fallback, verification, error handling (persistent apps), and return value. It does not mention prerequisites like device connectivity or app installation, but these are likely implicit for a force-stop tool. The absence of an output schema is mitigated by explicitly describing the return object. Overall, it's nearly complete for an agent to use correctly, with minor gaps around environmental assumptions.

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% for both parameters, so the schema already explains 'udid' and 'packageName' adequately. The description does not add additional meaning beyond what's in the schema, such as format requirements or interplay between parameters. Per the baseline rule for high schema coverage, a 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 clearly states the verb ('Force-stop'), resource ('Android app by package name'), and specifies it's Android-specific. It distinguishes from siblings like device_clear_app_data or device_uninstall_app by focusing solely on force-stopping. The return object and fallback details further clarify its exact scope.

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 does not explicitly mention when to use this tool versus alternatives such as device_clear_app_data or device_uninstall_app. Usage is implied by the tool's name and purpose, but there is no guidance on when not to use it or which alternative might be preferred for specific scenarios. Given the narrow purpose, the lack of explicit routing is acceptable but not exemplary.

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