tap_on_text

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

With no annotations provided, the description carries the full behavioral burden and reveals substantial non-obvious behavior: it runs describe_ui internally, prefers a clickable match, normalizes typographic punctuation to ASCII, defaults to a coordinate tap, and can switch to a real accessibility click requiring a one-time bridge install. This goes well beyond what the schema alone would convey.

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 front-loaded with the core purpose and each subsequent sentence adds a distinct, valuable behavior or condition: internal describe_ui usage, punctuation normalization, exact-match guidance, and the accessibility fallback. There is no filler or redundant restating of the tool name.

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 5-parameter tool with no annotations and no output schema, the description covers selection criteria, matching semantics, and a failure-recovery path very thoroughly. It does not explicitly describe return values or no-match error behavior, but that is a minor gap given the otherwise complete operational guidance.

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 already 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining the punctuation-folding behavior for text matching and by giving the specific scenario where partial=false matters. via_accessibility is also contextualized with a concrete failure case, while serial and verify_change are adequately left to their schema descriptions.

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 exactly what the tool does: find an element by visible text or content-description and tap its center. It calls itself 'the one-shot way' to press a labelled button or row without computing coordinates, which clearly distinguishes it from coordinate-based taps and related sibling tools like tap.

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?

Gives clear, actionable guidance: use partial=false when labels overlap to avoid hitting the wrong item, and use via_accessibility=true when a coordinate tap lands but nothing happens. It does not explicitly enumerate when to prefer sibling tools like tap_element, but the coordinate-tap contrast and fallback conditions make the intended usage context clear.

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