app_action

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

Annotations only declare destructiveHint=true, and the description adds real substance: it identifies which actions destroy data (clear_data, uninstall), that uninstall_keep_data preserves data, and that close_window is non-fatal to the process. It stops short of stating prerequisites such as required permissions for uninstall or grant/revoke, or what failure looks like.

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?

A single front-loaded sentence with parentheticals that each carry genuinely distinguishing information (clear_data stops the app, close_window leaves it running). No filler.

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 destructive, three-parameter tool with no output schema, the description covers actions well but omits failure modes, permission prerequisites for uninstall, and the package parameter's meaning. It is adequate but leaves meaningful gaps an agent would hit at call time.

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 only 33% – only the permission parameter is documented in the schema. The description compensates partially by spelling out the semantics of each action enum value and the grant/revoke pairing with permission, but it never clarifies that package is the Android package name or what the pattern enforces.

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 opens with a specific verb and resource ("Changes an app's state") and then enumerates all seven action values, so an agent knows exactly which state mutations are available. It is very clear on its own terms but never explicitly distinguishes itself from siblings such as launch_app or install_apk.

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 provides useful in-tool disambiguation between overlapping actions (clear_data also stops the app; close_window leaves it running), which helps pick the right action value. However, it gives no guidance on when to reach for this tool versus sibling tools like list_apps, install_apk, or launch_app.

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