tap_coordinates

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

With no annotations, the description carries the behavioral burden. It does disclose that tapping is done by exact pixel coordinates rather than by element, but it does not mention device targeting, coordinate-origin assumptions, or side effects of tapping arbitrary screen positions. It is not contradictory, just thin.

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 short sentences with no filler; the action and the when-not-to-use condition are both front-loaded. Every word earns its place.

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 tap tool, purpose and selection condition are present, and an output schema exists so return values are covered elsewhere. However, the description leaves the device parameter and coordinate-system details undocumented, which are necessary for reliable invocation in a multi-device context.

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 0%, so the description must compensate for x, y, and device. It gives some meaning to x and y ('exact pixel position') but does not explain the coordinate origin, units, or the device parameter at all. This is insufficient for the optional third parameter.

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 and resource ('Tap an exact pixel position') and immediately differentiates from element-indexed tapping by saying it is only for elements with no index, such as screenshot-derived targets. This is enough for an agent to distinguish it from siblings like tap or tap_text.

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?

Explicitly says when to use it ('Only use this when an element has no index') and gives a concrete example (something found in a screenshot). It does not name the alternative tool to use when an index exists, but the condition is clear enough to prevent misuse.

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