start_adb_activity

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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is covered. The description's genuine addition is output behavior: "the activity manager's Starting/Error verdict is preserved verbatim" — valuable because there is no output schema. It stops short of describing failure/permission semantics or what happens on a non-zero am exit.

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 sentences, front-loaded with the operation and its parameter surface, closing with the behavioral caveat. 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 6-parameter mutating tool with a fully documented schema and no output schema, the description covers what it does, the shape of the intent it builds, and how results are reported. Remaining gaps — no guidance on sibling selection (start_adb_app/stop_adb_app) and no note on failure modes — are minor but real.

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%, so every parameter (including serial and analysis_project_id) is documented in the schema, making 3 the baseline. The description restates the parameter surface (action, data URI, component, 16 typed extras) but adds nothing the schema doesn't already say, and omits serial and analysis_project_id entirely.

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 specific verb+resource ("Start an intent with `am start`") and enumerates the supported intent surface: action, data URI, explicit component, typed extras. An agent can tell this is raw intent dispatch rather than a package-launch helper, though it never names the nearest sibling (start_adb_app) to draw the line explicitly.

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?

No explicit when-to-use / when-not-to-use or alternative routing is given; the choice between this and start_adb_app must be inferred from the `am start` framing. The mention that it is "a device-mutating tool" hints at caution but is not a usage rule.

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