tap

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

No annotations are supplied, so the description carries the full behavioral burden and largely drops it. It does not say whether the call blocks until the UI settles, what it returns (no output schema exists either), whether a screenshot is required beforehand, or what happens if y/x fall outside the screen bounds.

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?

A single sentence with zero filler, front-loading the action and coordinates before the frame qualifier in parentheses. It is efficient but borders on under-specification rather than being padded.

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 4-parameter input device tool with no annotations and no output schema, the definition leaves too much for the agent to infer: return behavior, preconditions, off-screen handling, and the relationship between a tap and subsequent UI state. Only the coordinate frame is settled.

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 50%: count and device are already documented, but x and y have empty schemas, and the description supplies exactly the missing semantics for them by declaring the units/frame as screenshot pixels. It could still say more, such as whether x and y are top-left origin or what range is valid, but the essential meaning is added.

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 a specific verb (tap) and resource (a point at x, y), and pins down the coordinate frame as screenshot pixels. That frame is the key disambiguation from abstract screen coordinates, though it never explicitly contrasts itself with siblings such as longpress or swipe.

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?

Usage is only implied: a tap gesture is obviously for activating UI elements, and the '(screenshot pixels)' note implicitly tells the agent to source coordinates from a prior screenshot. There is no explicit when-to-use, when-not-to-use (e.g. versus longpress for press-and-hold, or swipe for dragging), and no prerequisite statement about needing a screenshot first.

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