window_action

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

The description adds valuable context beyond the destructiveHint annotation by explaining that 'close is destructive - it sends the window a close request and the app may prompt to save.' This clarifies the exact side effect. However, it does not mention the confirm_focus_disruption requirement for focus actions, which is only disclosed in the schema, so the description is not fully transparent about all behavioral traits.

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 four sentences, front-loaded with the primary purpose, includes a critical warning about the destructive close action, and uses a clear Args/Returns structure. Every sentence contributes useful information without redundancy or verbose padding.

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?

The description covers the core purpose, destructive close behavior, window identification, and return format (including error handling). It omits the focus disruption confirmation and platform-specific display parameter, but these are documented in the schema. For a tool with one nested parameter and an output schema, the description is sufficiently complete, though a bit more detail on focus side effects would make it fully robust.

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 schema provides thorough descriptions for all parameters (action, title, handle, display, confirm_focus_disruption), so the baseline is 3. The description adds value by explicitly stating 'Identify the window by handle or title' and by enumerating the allowed actions in the first sentence, which reinforces the semantics of the action parameter and the selection criteria. This lifts it above the baseline.

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 explicitly states the tool's function: 'Focus, minimize, maximize, restore or close a window.' The verb+resource combination is specific and clearly differentiates from sibling window tools like move_window or resize_window, as the enumerated actions are unique to this tool.

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 clearly identifies the target window via 'handle or title' and warns about the destructive nature of 'close'. While it doesn't explicitly contrast with alternatives, the action set (focus/minimize/maximize/restore/close) is distinct enough that usage context is clear. It omits explicit 'when not to use' guidance, but the unique actions make this unnecessary for basic selection.

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