window_action

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

Annotations already indicate destructiveHint=true. The description adds that the 'close' action sends a close request and may prompt to save, and that the return is a JSON string confirming the action or an error. This goes beyond the annotations by detailing behavior and output.

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 concise, with a clear first sentence listing actions, a caution about 'close', identification guidance, and a structured Args/Returns section. Every sentence serves a purpose.

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 complexity of five actions and four parameters, the description covers purpose, identification, return format, and the destructive nature of close. However, it omits the 'display' parameter's Linux-only context and does not address openWorldHint implications.

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 description adds meaning by stating the window can be identified by handle or title, linking these two parameters as alternatives. This supplements the individual schema descriptions, which are already present but do not convey the identification strategy.

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 performs five window actions (focus, minimize, maximize, restore, close) on a target window, distinguishing it from sibling tools like show_window, hide_window, move_window, and resize_window by covering these specific 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 explains that the window is identified by handle or title, and the action is specified via the action parameter. However, it does not explicitly mention when to use an alternative (e.g., show_window for showing a window) or provide exclusion criteria.

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