screenshot

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

With no annotations provided, the description carries the burden. It discloses a key non-obvious behavior: the image is downscaled, so coordinates read off it are not the device's own. This gives the agent actionable knowledge to avoid incorrect tap targets. It does not mention other behavioral aspects like permission requirements, but the core risk is 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 front-loaded with purpose, immediately followed by the critical downscaling warning, then the parameter details. Every sentence earns its place; there is no filler or repetition of schema 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 simple tool with two optional parameters and no output schema, it covers the behavior and parameters well. The only minor gap is not explicitly stating the return format (e.g., image data type), but the phrase 'The image is downscaled before sending' implies it returns an image, so this is acceptable.

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?

Schema description coverage is 0%, and the description fully compensates by explaining both parameters: max_width as 'longest edge of the returned image in pixels' and serial as 'device serial when several are attached'. This adds meaning beyond the schema's bare type/default declarations.

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 'what is currently on screen', and positions it as a pre-action observation tool. It distinguishes itself from ui_dump and tap by noting they are needed for real tap targets, though it does not explicitly contrast with capture_* siblings which could be ambiguous.

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?

It gives a clear 'when to use': 'see the app before acting on it'. It also provides a 'when not to rely on it' by warning that coordinates from the image are not device coordinates and directing the agent to ui_dump/tap instead. This is useful but could be stronger by naming all relevant alternative tools.

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