computer_get_desktop_state

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

With no annotations, the description carries full behavioral burden. It discloses the important backend restriction and an escalation rule, but does not explain side effects such as whether a screenshot file is written, what the capture actually returns, or what 'whole desktop' means operationally. Partial transparency rather than full.

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 tight sentences with the primary action front-loaded and the availability caveat placed immediately after. Every clause carries meaning and there is no filler.

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 tool is simple and an output schema exists, so return values do not need detailed description. However, the parameter's semantics are entirely unexplained and the 'window-focused ladder' allusion is undefined, leaving gaps that an agent would need to resolve before confident use.

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 parameter screenshot_out_file has zero schema coverage, and the description never mentions it. The agent cannot infer whether it is an output path, whether null selects a default behavior, or what file format is produced. The schema provides no help, so the description fails to compensate.

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 action ('Capture the whole desktop') and a resource ('whole desktop') tied to an active Cua Driver session. This is distinct from window-focused capture tools, though it does not explicitly name a sibling tool like computer_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 description provides explicit when-to-use constraints: it is only available when CUA_BACKEND=cua-driver, and in an auto session it should be used only after the window-focused ladder is exhausted. It lacks explicit naming of alternative tools or direct 'when not to use' phrasing, but the conditions are concrete and actionable.

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