screenshot

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

With no annotations provided, the description carries the full burden. It discloses the return format (JSON with image_format and image_base64), the specific JPEG format, and the dispatch logic by device type. It does not explicitly state side effects, but 'Capture' implies a non-destructive read. It adequately informs the agent of output structure and behavior.

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 well-structured with clear sections (Args, Returns) and front-loads the purpose. It is slightly verbose with the server-dispatch explanation, but every sentence adds value, such as the platform behavior and return format. It remains concise relative to its informational density.

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 covers all necessary information for an agent to invoke the tool: the single required parameter, where to get it (list_devices), the output format (JSON with image_format and image_base64), and platform-specific behavior. It is complete for a simple, read-only screenshot operation.

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 schema provides only a 'serialno' string with no description coverage. The description's Args section explains that serialno is 'The device serialno, from list_devices,' adding crucial sourcing information and meaning beyond the schema. This fully compensates for the zero schema coverage and leaves no ambiguity about the parameter.

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 'Capture a screenshot of a device' with a specific verb and resource, and further details platform-specific behavior (full-desktop, CDP, device image queue). It distinguishes itself from sibling tools by being the only screenshot tool, and the added platform dispatch detail reinforces its unique scope.

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 gives context on when to use it ('Works for any platform') and explains that it automatically selects the capture method based on device type. It does not explicitly name alternatives or say when not to use it, but since no sibling offers screenshot functionality, this is acceptable. It lacks explicit exclusions but is clear enough for an agent to select it for visual state capture.

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