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

Annotations declare destructive/idempotent/non-readOnly, but the description goes well beyond them: it discloses the control-channel-first strategy, the `am force-stop` fallback, `pidof` verification, and that diagnostics surface when an app persists (Samsung FGS resurrection). That is exactly the kind of failure-mode context an agent cannot get from structured fields.

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?

Two tightly packed sentences with zero filler; the core action leads and the mechanism/return details follow. Every clause carries information.

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?

With no output schema, the description helpfully enumerates the return fields (stopped, wasRunning, transport, retryRecommended) and explains the fallback behavior. It omits prerequisites such as required device permissions or whether root is needed for the force-stop path, leaving a small gap for a destructive operation.

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% and both parameters are documented with an example (com.android.chrome), so the schema carries the semantic load. The description adds only the phrase 'by package name', which is baseline-level reinforcement.

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 precise verb and resource ('Force-stop an Android app by package name'), which cleanly separates it from ios_terminate_app, device_uninstall_app, and device_clear_app_data without needing to name them. The platform and package-name scoping make the target unambiguous.

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 explains the internal fallback chain but never states when to choose this tool over alternatives like device_uninstall_app (remove) or device_clear_app_data (reset state). Usage is implied by the verb rather than explicitly guided, so a 3 is warranted.

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