press_key

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

With no annotations provided, the description does some of the burden-carrying work: it discloses the device-mode/Expo Go environment and the Android-only restriction on 'back'. It omits what the keypress actually does (navigation side effects of back, deletion effects of delete) and any failure modes when not in device mode.

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 compact clauses with the mode restriction front-loaded and the allowed values enumerated at the end. Nothing redundant and nothing padded.

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-enum-parameter tool with no output schema, the description supplies the environment constraint, the valid value set, and the platform caveat — everything needed to invoke it correctly. Return values are not needed since there is no output schema.

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%, so the description must carry meaning, and it does: it restates the allowed values and adds the non-obvious constraint that 'back' is Android-only, which the enum alone cannot convey. It stops short of saying how the keypress is dispatched or what happens on invalid input.

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?

States a specific verb and resource ('presses a hardware key') plus the runtime scope ('inside Expo Go', 'device mode only'), which distinguishes it from text entry or screen clicking. It does not name a sibling tool explicitly, so differentiation is implied rather than stated.

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?

'Device mode only' functions as a usage precondition and rules out non-device contexts. However, it never names alternatives such as type_text for character input or explains when a hardware key press is preferable to those siblings, leaving the choice to inference.

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