tap

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

No annotations are provided, so the description must disclose behavior. It mentions the matching order for label (exact, case-insensitive, substring) but does not describe side effects, error handling (e.g., element not found, out-of-bounds coordinates), or the nature of the interaction beyond 'tap'.

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 sentences that are front-loaded with the core purpose and provide essential parameter guidance without extraneous information. Every sentence is necessary and well-structured.

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 simple action tool with no output schema and four parameters, the description is largely sufficient. It covers the main usage scenarios and parameter constraints. Minor gaps include not explaining the return value or failure modes, but these are less critical for a tap action.

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?

The description adds value beyond the schema by clarifying the mutual exclusivity of label vs x/y and the preferred/fallback order. The schema covers 50% of parameters with descriptions (label and udid), and the description compensates for the undocumented x and y by stating they must be used together.

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 states the tool taps an element, specifying two methods: by accessibility label (preferred) or by raw x,y coordinate (fallback). It distinguishes from sibling tools like press_button, swipe, and type_text which are different interactions.

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 tells when to use each method ('preferred' vs 'fallback') and that either label or both x and y should be provided. However, it does not explicitly state when not to use this tool or compare it to alternatives like press_button.

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