computer.list_windows

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

No annotations are provided, so the description carries the burden. It clearly indicates a non-destructive listing operation, but it does not disclose edge cases such as whether all window states are included, whether minimized windows are listed, or what 'top-level' excludes. This is adequate but not rich.

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, focused sentence that front-loads the action and resource, then lists the returned fields. Every word earns its place with no redundancy.

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 zero-parameter listing tool with no output schema, the description adequately conveys what an agent gets back. The absence of output schema means the description's field list is the main contract; it is sufficient, though it could mention sorting or window visibility caveats.

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 has zero parameters and the schema coverage is 100%, so nothing is missing from the input side. The description adds meaning by clarifying that the result includes title, application, pid, and state, which is valuable beyond the empty schema.

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 a specific verb ('List') and resource ('all top-level OS windows') and specifies return fields (title, application, pid, state). It clearly distinguishes the tool from siblings like get_active_window and focus_window, although it does not explicitly name them.

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 context implies this is a read-only enumeration tool for top-level windows, useful before actions like focus, close, or observe. However, it does not explicitly state when to prefer this over computer.get_ui_tree or computer.find_text, nor any exclusions or caveats.

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