tap

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

With no annotations, the description fully carries the behavioral burden. It discloses that refs re-resolve against the live tree, that missing elements return the current tree instead of blind tap, that scroll:true triggers scrolling, and that the return is a mini-diff. This is thorough, though it does not explicitly cover error handling or permission requirements.

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 reasonably concise, with key information front-loaded. It uses multiple sentences but each adds value, covering targeting methods, re-resolution, scrolling, and return value. A slight reduction in redundancy could improve score.

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 complexity of the tool (multiple targeting methods, scrolling, re-resolution) and the lack of output schema, the description covers all essential behaviors and return format. It lacks only a note on prerequisites or failure states, but is otherwise complete.

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 description coverage is low (33%), but the description explains that ref comes from get_ui_tree/wait_for and describes the selector object implicitly. However, it does not add detailed semantics for each parameter beyond what the schema already provides, leaving some parameters (x, y, ref) with minimal guidance.

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 specifies the action (tap), the targets (element by ref, selector, or coordinates), and distinguishes from sibling tools like press_button by listing multiple targeting methods.

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 implies when to use the tool (tapping a UI element) but does not explicitly state when to prefer it over siblings like press_button or when not to use it (e.g., when tap is not appropriate). It provides context on scrolling but lacks exclusion statements.

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