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

With no annotations, the description carries the full behavior disclosure burden. It discloses the mechanism (APP_SWITCH keycode, shell, policy-gated), the wait for UI settle, and the swipe action. It also mentions the return shape. It does not detail failure cases or the exact effect of the 'all' flag on navigation, but the core behavior is transparent.

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 crisp, information-dense sentences with no filler. The primary action is stated first, followed by use cases, implementation details, and return value. Each sentence adds value and nothing is redundant.

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 tool with no output schema and no annotations, the description is quite complete: it covers what happens, how, and what is returned. It doesn't address edge cases (e.g., package not in Recents, screen lock), but for the given complexity, it is sufficient. A slightly more detailed return contract or error behavior would improve it.

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 covers all parameters with descriptions (100% coverage), so the baseline is 3. The description adds little beyond the schema: it mentions 'Close all' and 'first/frontmost card' behavior, but these are also in the schema. It does not clarify interactions like what happens if 'all' is true and 'packageName' is set, so it does not exceed the baseline.

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 tool's purpose: opening the Recents screen and dismissing an app card, with an optional 'Close all' action. It distinguishes this from generic swipe/terminate tools by specifying the exact UI context and action ('dismiss an app card on Recents'). The mechanism (keycode 187) further clarifies its 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 gives a clear use case: 'Useful for clearing background apps or verifying an app was killed.' This provides context for when to invoke it. However, it does not explicitly name alternatives (e.g., device_terminate_app for force-stop, device_swipe for generic swipes) or state when not to use it, leaving some room for inference.

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