desktop_windows

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

Annotations declare readOnlyHint=false and openWorldHint=false, so the agent already knows this touches the live desktop; the description explains why (focusing a window mutates foreground state) only by implication. It adds nothing about what happens when a window is missing, whether focusing requires elevation, or what an enumeration returns, so beyond the annotations it contributes little behavioral context.

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 sentence that front-loads the primary operation and appends the alternative mode with its parameter named inline. No filler, no repetition of the tool name.

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 both operating modes and the non-obvious parameter, which is reasonable for a 3-parameter tool with no output schema. It is still silent on the shape of the enumeration result (e.g., that hwnds are returned) and on how `filter` combines with `focus_hwnd`, leaving the agent to infer the listing-to-focus workflow.

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 coverage is 67% and the one gap is `include_minimized`, which the description explains semantically (it broadens enumeration to minimized windows), adding meaning beyond the bare `default: false`. `focus_hwnd` is also framed as the trigger for the foreground mode rather than just an integer, though the interplay with `filter` is never clarified.

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 two specific operations on a specific resource: enumerate visible Windows application windows, or bring a window to the foreground. The dual-mode phrasing plus the named parameters makes the behavior unambiguous, though it does not explicitly contrast itself with siblings like desktop_ui or desktop_screenshot.

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 parenthetical 'optionally minimized ones with `include_minimized`' and 'via `focus_hwnd`' implicitly tell the agent how to select each mode, which is genuine conditional guidance. However, there is no explicit when-to-use-this-vs-alternative statement and no warning about which sibling to reach for when listing versus interacting with windows.

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