desktop

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

With no annotations, the description carries the full burden. It details what is included (windows, layers, cursor) and what is not (launchers, bars as windows), and mentions best-effort geometry. It does not explicitly state read-only behavior but the snapshot nature implies non-destructive operation.

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 dense sentence that efficiently packs a lot of information. It could be better structured but is not overly long or verbose, earning its content.

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?

Given the presence of an output schema (not shown), the description covers key elements: content, coordinate system, special surfaces, and usage order. It could mention limits or error scenarios, but is sufficiently complete for a snapshot 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 input schema is empty (0 parameters, 100% coverage). Following the baseline guideline for zero parameters, the description adds no parameter details, which is appropriate.

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 clearly states the tool returns a semantic desktop snapshot including monitors, workspaces, windows with coordinates, active window, cursor, and layer-shell surfaces. It distinguishes from sibling tools like screenshot (captures image) and pointer (cursor control) by providing coordinate information for later actions.

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 explicitly advises 'Call first; act on the addresses it returns,' establishing clear usage order. While it does not list when not to use or exhaustive alternatives, the instruction implies it is the initial step for tools that require addresses.

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