adb_tap

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

With no annotations provided, the description is the only source of behavioral information. It states that the tool taps at the specified coordinates, which is clear but does not disclose any potential side effects (e.g., unintended UI interactions) or prerequisites (e.g., device must be awake). Since this is a low-risk, simple action, the lack of nuance is not egregious, so a score of 3 reflects adequacy without extra depth.

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 a single sentence that is immediately front-loaded with the action. It contains no wasted words and is appropriate for the tool's simplicity.

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 tool's simplicity, the description combined with the schema is nearly complete. It lacks mention of the coordinate system (e.g., screen pixels) and any required device state, but these are common assumptions in ADB tools. The absence of an output schema is fine since the tool likely returns nothing, and the parameter schema is fully documented. Overall, the context is sufficient for an agent to invoke the tool correctly in most scenarios.

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 input schema describes all three parameters with 100% coverage, including x, y, and deviceId, so the description does not need to add param details. The phrase 'specified coordinates' merely echoes the x/y descriptions. The deviceId parameter is left entirely to the schema, and the description provides no additional meaning beyond what the schema already gives, resulting in a baseline score of 3.

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 action ('Tap') and the resource ('screen') with the specific coordinate parameter, which distinguishes it from sibling tools like adb_swipe and adb_long_press. It is a specific and unambiguous statement of the tool's function.

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 provides no guidance on when to use this tool versus other input tools such as adb_swipe, adb_long_press, or adb_type_text. There are no stated preconditions like screen-on requirements or device connection, and no exclusions for contexts where a tap would be inappropriate.

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