window_at

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

The readOnlyHint annotation already signals safety, and the description adds meaningful behavior: the compositor pick respects input shapes, sees through click-through overlays, and the result includes every window whose rectangle covers the point. This is beyond what annotations convey.

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 sentences deliver the purpose, the usage trigger, and the key output distinction, front-loading the main idea. No filler or repetition.

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?

With no output schema, the description still explains what the tool reports: the compositor's pick and all covering windows. The only notable gap is the undocumented coordinate system, but for a simple read-only hit-test tool it is otherwise sufficient.

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 carries the burden for x and y. It only refers to 'this point' and does not specify coordinate space, units, or whether coordinates are screen-relative vs image-relative, which is essential for correct use with screenshots.

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 operation: determine what a click at a coordinate would hit. It disambiguates from sibling tools by promising both the compositor's input-shape-aware pick and all covering windows, which no sibling name suggests.

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 tells the agent when to use it: before clicking a location inferred from a screenshot. It does not spell out exclusions or alternatives, but the use-before-clicking context is clear.

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