rescue_start_otg

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

With no annotations provided, the description carries the full disclosure burden and does it well: no image/sound, forwards the caller's physical USB keyboard/mouse, requires visible screen, and explicitly disclaims automatic guessing. It does not cover session lifecycle or failure modes, but the most important behavioral traits are 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?

The description is moderately sized and front-loaded: purpose first, then a clearly labeled limitation, then a concrete use case. Every sentence adds value, though the scenario explanation could be tightened; it remains readable and well structured.

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 single-optional-param start command with an output schema, the description covers purpose, constraints, and the exact human-in-the-loop scenario. It does not mention prerequisites (USB/AOA support) or how the session is stopped, but these are secondary and partially inferable from the rescue_* sibling group.

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 only parameter, serial_hint, is never mentioned in the description, and the schema provides no description for it beyond the name and a null default. With 0% schema description coverage, the description was expected to compensate but does not; the agent must guess that serial_hint selects the target device.

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?

Description opens with a specific verb and object: starting AOA-based keyboard/mouse control without ADB ('scrcpy --otg'). It also differentiates itself from sibling rescue_start_mirror by explicitly stating there is no image and no sound, so the mode's scope is 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?

It clearly defines when this mode is appropriate: when the phone screen is still visible but touch/fingerprint is dead, and the owner can enter PIN/pattern with physical input. It also states a limitation ('no image/sound') that implicitly steers away from using this when mirroring is needed, though it does not explicitly name alternatives.

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