Tap

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

The description discloses that the tool combines action and observation ('act+observe'), which is a behavioral trait beyond what a simple tap implies. With no annotations to rely on, this adds useful context about the tool's side effect of returning screen state.

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, concise sentence that is front-loaded with the action 'Tap'. It includes the key benefit in the second clause without unnecessary verbosity.

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 10 parameters and detailed schema, the description provides a helpful overview and the crucial act+observe behavior. It does not explain the observe parameter options, but the schema handles those details, making the description reasonably 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 coverage is 100%, so the baseline is 3. The description mentions key selection methods (id/text/resource_id/accessibility) already in the schema without adding significant new meaning beyond the schema's parameter 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?

The description clearly states the tool taps an element by selector or absolute coordinates, using specific verbs and resources. It distinguishes itself from siblings like long_press and swipe by focusing on standard tap actions.

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 mentions the benefit of returning the screen state, implying when to use it (when you want action+observation), but it does not explicitly discuss alternatives (e.g., long_press) or when not to use it. Usage context is implied rather than explicit.

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