app_click_at

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

No annotations are provided, so the description carries the full burden. It states the tool clicks at coordinates and specifies the button options, but does not disclose potential side effects (e.g., whether it triggers a page load, waits, or modifies state). The behavior is largely implied, but some details are missing.

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 extremely concise, with two sentences that front-load the purpose and immediately provide key details. No extraneous information.

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 coordinate click tool with no output schema, the description is mostly complete. It covers the essential purpose, parameters, and when to use. However, it lacks information about return values or behavior after clicking (e.g., whether it waits for a result), which would be helpful for planning.

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 already describes x and y as 'CSS pixels from the viewport's top-left', providing good coverage. The description adds value by clarifying the 'button' parameter with its options and default. With 67% schema description coverage, the description effectively compensates for the missing schema description on 'button'.

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 clicks at raw viewport coordinates, specifically for canvas/native-drawn UI where no element handle exists. This distinguishes it from element-based clicks, and the sibling tool 'app_click' reinforces that distinction.

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 explicitly mentions the use case (canvas/native-drawn UI) and contrasts with element clicking, but does not explicitly state when not to use it or name the alternative tool (app_click) for element-based clicks. Still, the context is clear enough for an agent.

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