list_windows

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

No annotations exist, so the description carries the full burden. It does add meaningful scoping — 'visible top-level' tells the agent that hidden/minimized windows and child windows are excluded, and 'foreground state' discloses that focus status is reported. However, it leaves common behavioral questions open for a list operation: ordering, result-size limits, and whether handles are live/current. Decent but not comprehensive disclosure.

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 front-loaded sentence with zero waste: action verb first, resource scope next, then the full output field list. Every element earns its place and no wording is redundant.

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?

With no output schema and no annotations, the description is the only channel conveying the return shape, and it does so thoroughly by enumerating all returned data fields. The operation is simple and zero-arg, so nothing essential is missing; only minor details (ordering, blocking behavior) go unmentioned.

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 tool takes zero parameters, so the schema has nothing to explain and there is nothing the description needs to add. Per the rubric baseline for 0-param tools, a 4 is appropriate — the description correctly focuses on behavior rather than parameters.

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 a specific verb ('List') and a precisely scoped resource ('visible top-level windows'), then enumerates the exact output fields (HWND, title, process info, bounds, foreground state). This clearly differentiates it from siblings like get_foreground_window (single focused window) and focus_window (changes focus), so an agent can tell operations apart without opening schemas.

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?

Usage is implied rather than stated. An agent would infer this tool answers 'what windows are open?' queries, and the foreground-state field hints it complements get_foreground_window, but the description never explicitly says when to prefer it over a sibling (e.g., when you need a specific window's handle vs. enumerating all). No exclusions or alternatives are named.

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