capture_widget

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

With no annotations, the description must disclose all behavioral traits. It states the tool returns a PNG image, but does not mention side effects, error conditions, read-only nature, or performance characteristics.

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 moderately sized but includes an Args section which is atypical for tool descriptions. It could be more concise by integrating the parameter info naturally into the prose.

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 no output schema, the description mentions the PNG return type. It covers prerequisites but lacks information about error handling, performance, or additional context needed for a complete understanding.

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 only parameter 'widget_name' is explained as the widget's objectName with guidance on discovering valid names via 'list_capturable_widgets'. This adds substantial meaning beyond the schema's minimal 'Widget Name' title. Schema coverage is 0%, so description compensates well.

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', the resource 'Qt widget', and the method 'objectName via the proxy agent'. It distinguishes from sibling tools like 'capture_window' and 'capture_region' by specifying widget-specific targetting.

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?

Prerequisites are explicitly listed (Qt application with start_agent, connected to Unix domain socket). It directs users to 'list_capturable_widgets' for valid names. However, it does not mention when not to use this tool or compare with alternatives like 'capture_window'.

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