device_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 adds the keycode-acceptance behavior, but that is already restated in the schema's key parameter description. It omits important behavioral context such as platform-specific key support (e.g., 'back'/'home'/'recents' are Android concepts, and 'enter' may behave differently on iOS) and what happens for unsupported key/platform combinations.

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 short sentences with the core action front-loaded; there is no filler. The second sentence about keycodes earns its place as a critical acceptance criterion, though it slightly duplicates the schema's key description.

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 3 required parametersFootnote, no output schema, and no annotations, the description captures the core action but leaves notable gaps: no guidance on platform/key compatibility, no behavior description for invalid or unsupported keys, and no indication of what the tool returns. An agent could easily invoke 'home' or 'back' on an iOS platform without being warned.

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 only 33% (only 'key' is described). The description supplements the 'key' parameter by reiterating that raw numeric Android keycodes are accepted, which adds semantic clarity. However, it offers nothing for the undocumented 'deviceId' and 'platform' parameters, so the low coverage gap is only partially compensated.

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 uses a specific verb ('Press') with a clear resource ('hardware or system key'), and the keycode sentence adds precision about what inputs are accepted. It functionally distinguishes from siblings like device_tap, device_type, and device_swipe, though it doesn't explicitly name any alternative or contrast itself.

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 phrase 'hardware or system key' implies this is for physical/system buttons rather than on-screen UI elements, which loosely signals when to use it over device_tap or tap_on_element. However, no explicit when/when-not conditions or alternative tools are mentioned; the guidance is only implied.

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