Tap

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

No annotations exist, so the description carries the behavioral burden. It adds useful context that a numbered-mark tap targets the center and that the id source is perceive_screen. However, it does not disclose whether coordinates are screen-relative, what happens when both coordinate and som_id are supplied, or side effects beyond the obvious tap action.

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?

One sentence delivers the action, both targeting modes, and the source of som_id with no filler. It is front-loaded and every word contributes meaning.

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?

The description is not complete enough for robust agent selection and invocation. It lacks sibling differentiation, device semantics, the required relationship between x/y and som_id, and any note on what happens when no parameters are provided. The presence of an output schema offsets return-value explanation, but structural selection guidance is still missing.

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?

With 0% schema coverage, the description must explain parameters itself. It does clarify x/y as coordinates and som_id as a mark center from perceive_screen, but it omits the device parameter entirely and does not state whether x/y and som_id are mutually exclusive.

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 names the action ('tap') and the two target modes: coordinates '(x, y)' or the center of a numbered mark identified by 'som_id from perceive_screen'. It is distinct from obvious siblings like double_tap and long_press, though it does not explicitly name alternatives.

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?

There is no guidance on when to choose tap over double_tap, long_press, swipe, or scroll variants, and no exclusions or prerequisites are given. The only implicit clue is that som_id comes from perceive_screen, but this is not developed into a usage recommendation.

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