Send Android input

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

Annotations already declare readOnlyHint=false, openWorldHint=true and destructiveHint=true, so the safety profile is covered by structured data. The description adds no behavioral context beyond the operation list already present in the enum — it does not clarify device targeting, what 'destructive' means for a tap, or successful-injection side effects. With annotations carrying the load, the description's near-zero added value warrants a low score.

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 no wasted words, which is good for structure. But for an 11-parameter, four-operation tool it is under-specified rather than genuinely concise, mirroring the calibration case where sparseness is penalized as under-specification.

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 multi-operation mutation tool with 11 conditional parameters and no output schema, the description leaves major gaps: which parameters select which operation, how the device is targeted (serial/deviceId/deviceName), and what a call returns. It is far short of complete enough for correct invocation.

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 0% across 11 parameters, so the description carries the full burden — but it only echoes the four `type` enum values (tap, swipe, text, keyevent) without mapping which of x/y/x2/y2/text/keyCode/serial/deviceId/deviceName/durationMs apply to which operation. An agent gets no help resolving conditional or overlapping parameters.

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 names a specific verb (Send) and enumerates the resource/operations (tap, swipe, text, keyevent) plus the transport (adb). An agent can tell it does input injection rather than shell execution. However, it does not differentiate from siblings like adb_find_and_tap (which also taps) or adb_shell (which can run `input` too), so it stops short of a 5.

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?

There is no when-to-use guidance, no mention of prerequisites (a connected device/adb bridge), and no alternatives named. The agent must infer on its own that this is for direct coordinate-based input rather than element-targeted tapping via adb_find_and_tap.

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