focus_window

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

With no annotations, the description must carry the full burden, but it only states the action without covering side effects (e.g., what if the window is minimized), error behavior, or whether it activates vs merely raises. Minimal behavioral disclosure beyond the verb itself.

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?

A single, dense sentence that front-loads the core action and identification methods with no wasted words. Highly concise and appropriately structured.

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 omits crucial contextual details: behavior when neither parameter is provided, behavior when both are provided, and what happens if no window matches. No output schema or annotations to fill gaps, leaving the agent uncertain about edge cases.

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 by mapping 'handle' to HWND and 'titleIncludes' to partial title match, but provides no details on format, case sensitivity, or precedence when both are given. Partial compensation but not thorough.

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 verb 'bring to foreground' and the resource 'target window', and specifies two identification methods (HWND or partial title match). This distinguishes it from siblings like list_windows (listing) and get_foreground_window (querying).

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?

No guidance on when to use this tool versus alternatives like list_windows or get_foreground_window. It does not explain when to prefer a handle vs titleIncludes, or any preconditions. The intended usage is implied but not explicitly stated.

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