tap

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

Without annotations, the description carries the burden of disclosure and does well by explaining the return evidence (executed, screen_changed, changed_elements[], screen_hash) and the SELECTOR_AMBIGUOUS behavior. It does not cover potential side effects or waiting semantics, but it adds meaningful transparency beyond the bare schema.

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 well-structured with a clear opening, bulleted selector list, and a separate note on return values. It is slightly longer than strictly necessary, but every sentence contributes meaningful guidance, making it efficient and organized.

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?

Given the nested target object and no annotations, the description is thorough: it explains how to specify targets, what return values look like, how ambiguity is handled, and the role of the device parameter. It references get_screen for stable IDs, tying into the sibling toolset, and covers both normal and error cases.

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?

Although schema coverage is 100%, the description enriches each 'by' value with concrete usage examples and semantics (e.g., by=id references get_screen, bounds are last resort). It also clarifies that device is optional on single-device setups, adding value beyond the schema's technical definitions.

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 opens with 'Tap a semantic target and verify the result,' clearly stating both the action (tap) and the resource (a semantic target). It distinguishes itself from sibling tools by emphasizing semantic selection and returning verification evidence, which is unique among the listed siblings.

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 explicit guidance on selector usage: 'Prefer semantic selectors — never compute coordinates yourself', details each constraint type, and marks bounds as a last resort. It also advises retry with by=id on ambiguity. This is strong practical guidance, though it does not explicitly compare against alternatives like swipe or scroll.

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