adb_key

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

With no annotations, the description carries the burden. It discloses that it sends a key event, accepts aliases, full key names, numeric codes, and explains device auto-selection. It does not describe side effects, failure modes, or whether the key event is verified, leaving some behavioral ambiguity.

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 well-structured, front-loaded with the core purpose, then lists accepted input formats, then documents arguments. Every sentence adds useful information with no filler or redundancy.

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 simple two-parameter tool, the description covers input formats and device selection sufficiently. Since an output schema is reported to exist, return-value documentation is not required. Minor gaps around error handling and multi-device behavior when device is omitted do not prevent correct usage.

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 coverage is 0%, so the description must compensate. It thoroughly explains the key parameter with examples of aliases and numeric codes, and describes the device parameter's default behavior when omitted. This adds significant meaning beyond the bare schema.

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 states a specific action: send a key event to the Android device, and distinguishes the tool's scope by listing accepted aliases and full KEYCODE names. This clearly separates it from sibling tools like adb_tap, adb_swipe, and adb_type_text.

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 explains accepted key formats and device selection behavior, including auto-selection when only one device is connected. However, it does not explicitly say when to prefer this over similar siblings such as app_key or adb_tap, or mention prerequisites like requiring a connected device.

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