computer.close_window

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

With no annotations, the description carries the behavioral disclosure burden. It reveals that the close is graceful (WM_CLOSE), that confirm must be set to true, and that modal dialogs stay visible for the agent to handle. It does not discuss potential failure modes or return values, but these are minor for this operation.

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 one tight sentence that front-loads the action and then adds two pieces of high-value behavioral/parameter information. No word is wasted.

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 two-parameter tool, the description covers the action, the required parameter, and an important behavioral side effect. It is complete enough for an agent to invoke it correctly, though it does not specify how to obtain the 'window' identifier in 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. It adds meaning for 'confirm' by stating it is required and explaining the modal-dialog consequence, but it does not define what 'window' expects (ID, title, handle, etc.), leaving a gap for one of the two parameters.

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 uses a specific verb ('Close'), a clear resource ('window'), and the mechanism 'gracefully (WM_CLOSE)', which distinguishes it from a forced termination. This is unique among the siblings, all of which operate at the level of observation, UI interaction, or window management without closing.

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?

It plainly says this tool is for gracefully closing a window and gives the key prerequisite 'Requires confirm=true'. It also tells the agent what to expect afterward (modal confirmation dialogs remain visible), which is actionable context, though it does not explicitly contrast with sibling alternatives such as minimize or focus.

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