tap

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

No annotations exist, so the description carries the full behavioral burden and does not deliver: it never says this injects input into a live device, how the target device is resolved, or that recordAudio changes the timing/environment of the tap. The recordAudio mechanics are described only in the schema, not here.

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?

A single front-loaded sentence with no waste. It is efficient, though its brevity borders on under-specification for a device-input tool.

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 mutating device-input tool with no annotations, no output schema, a device-selection fallback, and a nested audio-recording side effect, one sentence about coordinates leaves critical context unaddressed at the tool level.

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 100% and every parameter, including the nested recordAudio object and device resolution, is fully documented in-schema. The description's only added semantics is the '(points)' unit hint, which the schema already repeats for x and y.

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 (tap) and resource (screen coordinates) with the unit qualifier 'points'. It implicitly separates itself from tap_element by specifying coordinates rather than an element, but never names the sibling explicitly.

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?

Usage is only implied: the coordinate-based phrasing hints at raw-position tapping versus element-based alternatives like tap_element, long_press, or double_tap, but no when/when-not guidance or alternatives are stated.

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