list_windows

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

No annotations exist, so the description must carry the full load. It discloses ordering (topmost-first), the significance of the returned ids, and the semantics of the frame/content geometry fields in screen pixels — real behavioral value. It says nothing about whether the list is empty or truncated in large desktops, or about permissions, which is a gap.

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?

Two short paragraphs; the scope and ordering come first, then the geometry glossary. The fragmentary first sentence (no verb) is slightly awkward, but nothing is padded.

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?

An output schema exists, so return values needn't be explained, yet the description still supplies the frame/content distinction and pixel units that make the results interpretable. What remains missing — workspace numbering and empty-list behavior — is minor for a one-parameter, read-only list tool.

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 single workspace parameter has 0% schema description coverage, so the description must compensate. Its parenthetical "(or those on one workspace)" does clarify that the parameter filters the list, but it never explains what workspace identifiers mean or that null means all workspaces.

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 states the resource (all windows, or those on one workspace), the ordering (topmost first), and the key output value (ids for the window tools). It lacks an explicit verb like "list", but the scope is specific enough to separate it from siblings such as view_workspace or desktop_info.

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 value of this call as a prerequisite for the window tools is only implied by "with ids for the window tools"; there is no explicit guidance to call it before focus_window, move_resize_window or close_window, and no sibling alternatives are named or ruled out.

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