desktop_windows

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

Since there are no annotations, the description must carry the behavioral disclosure burden. 'List' strongly implies a read-only, non-mutating operation, and the returned data is stated. However, it does not disclose potential permission requirements, whether all or only visible windows are included, or any output formatting assumptions. There is no contradiction with annotations.

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?

The description is a single tight sentence with no filler. The action and return content are front-loaded, and every word contributes useful information.

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 parameter-less read tool, the description is largely complete: it states the operation and the exact data returned. It lacks explicit scope and usage-boundary details, but the absence of parameters and output schema means an agent can still invoke it correctly based on this description.

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 is empty, so there are no parameter semantics to document. The baseline of 4 applies because nothing is lost by omitting parameter details.

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?

Uses a specific verb ('List') and names the exact resource ('windows'), then enumerates the fields returned: identities, titles, process identity, focus, and native client bounds. It does not explicitly distinguish itself from observation siblings like desktop_observe or desktop_inspect, but the window-level scope is clear from the name and description.

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 phrase 'List window...' implies use when the agent needs to enumerate open windows, but there is no explicit when-to-use or when-not-to-use guidance. It does not mention that desktop_observe or desktop_inspect should be used for UI element inspection, leaving usage context to inference.

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