ui_take_screenshot

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

The description goes far beyond the annotations by disclosing persistence side effects ('retain a raw PNG for the active debug session'), the fallback BitBlt behavior with a distinct evidence grade, and constraints such as 'Crop coordinates require evidence mode and are applied to the accepted raw PNG.' These behaviors are not visible in the schema or annotations and give the agent a realistic picture of what invoking the tool will do.

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 dense but structured: main behavior, output shape, evidence behavior, and an Args list that matches all 10 parameters. The fallback BitBlt sentence is long and has an overly technical wording, but it still adds material behavioral information. No sentence feels purely redundant.

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?

With no output schema, the description sufficiently describes both outputs: ImageContent and TextContent with metadata and file path. It explains return format, edge-case fallback, evidence persistence, crop behavior, and all parameter constraints. For a 10-parameter tool with zero schema descriptions, this is a near-complete operational specification.

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 itself is empty of descriptions, so all parameter meaning is supplied by the description's Args section. It explains relationships, constraints, and ranges (crop arguments must all be provided, expected_hwnd requires matching physical raster, max useful width is 1568). It loses some credit because the description says 'Default is 1280; max useful is 1568' while the schema default for max_width is 1568, creating a direct conflict for an agent that relies on the description.

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 first sentence states exactly what the tool does: 'Take a screenshot of the debugged application's window.' It is a specific verb+resource statement and the following sentences clarify the output delivery. However, it does not explicitly differentiate this tool from the sibling ui_take_annotated_screenshot, so the distinction is left to the name.

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 implies its main use case: when raw visual state is needed, via 'Returns inline ... directly to your vision pipeline.' It also gives conditional usage guidance such as 'Set evidence to retain a raw PNG' and crop-requires-evidence-mode. It never explicitly says when not to use it or names a better alternative, such as using ui_take_annotated_screenshot when visual labels are required.

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