desktop_screenshot

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

Without annotations, the description carries the full burden of transparency. It clearly mentions the side effect of writing a PNG file under state/screenshots/ and that it returns the path, which informs the agent about the persistent output and the return value. It does not describe potential overwriting behavior or naming conventions in detail, but the essential behavioral aspects are covered.

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 exceptionally concise—two sentences that fully communicate the tool's purpose, output, and usage context. Every word contributes meaning, with no redundancy or fluff.

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 description provides sufficient context for an agent to decide when and why to use the tool, including the output location and the return value. It does not mention potential edge cases like screen resolution, multi-monitor setups, or file overwrite behavior, but these are not critical for typical usage in the given ecosystem. Overall, the description is complete for the intended purpose.

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 already provides complete descriptions for both parameters: 'name' is an optional filename hint, and 'region' is an optional [x, y, width, height] crop. The description does not add any additional semantics beyond what the schema states. Since schema coverage is 100%, the baseline score of 3 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 verb 'capture' and the resource 'the current screen (or a region)', and explicitly mentions the output file location and that it returns the path. This unambiguously distinguishes it from other desktop_* tools like desktop_click or desktop_key which perform actions rather than capturing visual state.

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 a specific and actionable when-to-use: 'to verify that a UI action had the expected effect before sending the next.' This gives clear guidance on when to invoke this tool. It does not explicitly state when not to use it or suggest alternatives, but the sibling list includes other tools like desktop_wait that might be relevant in similar contexts, so a slightly fuller comparison would have been ideal.

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