android_press_key

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states it will 'press' a key but does not disclose potential side effects (e.g., navigating away from the current screen), whether the call blocks, error conditions, or the role of deviceId. The list of supported keys is helpful but does not address behavioral consequences. The description is too sparse for a tool that directly manipulates device state.

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 a single sentence with a list of examples, which is concise and to the point. It front-loads the core action and then lists specifics. No wasted words, but it could be slightly better structured by separating the enumeration from the action. Still, it is appropriately short and scannable.

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 tool with only two parameters and no output schema, the description covers the essential input expectations. However, it lacks usage context (when to choose this over tap/swipe), behavioral outcomes, and any edge-case handling. Given the absence of annotations, more explanatory depth (e.g., deviceId semantics, or that pressing navigation keys may alter the app state) would be warranted. It is minimally complete but leaves gaps.

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 input schema already covers both parameters (key and deviceId) with clear descriptions, and the schema description coverage is 100%. The description adds examples of supported keys (HOME, BACK, etc.) which are partially redundant but confirm the 'valid keycode' allowance. This matches the baseline of 3 where the schema does the heavy lifting; the description does not introduce novel semantic meaning beyond the 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?

The description clearly states the action ('Press an Android hardware or navigation key') and enumerates supported keys, making it distinct from sibling tools like android_tap (screen touches) and android_type_text (text entry). However, it does not explicitly contrast with siblings, so a slight deduction. It is specific and 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?

The description provides no guidance on when to use this tool versus alternatives such as android_tap or android_swipe. It does not mention prerequisites, context, or exclusions. An agent would need to infer that this is for physical/navigation keys rather than on-screen interactions. Lacks any 'when to use' or 'when not to use' statements.

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