vroid_screenshot

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

With no annotations present, the description carries the full behavioral burden and does so thoroughly. It discloses that every capture is saved to a captures directory, returned images may be downscaled, coordinates use native image pixel space, and there are driver quirks around modals and viewport dithering. This is unusually transparent.

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 long but every section earns its place: purpose, return behavior, coordinate system, and practical gotchas. It is front-loaded with the core action and then layers important operational details so an agent can use the tool correctly without skimming irrelevant 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?

For a screenshot tool with no output schema and no annotations, this is complete: the agent learns what is returned, where it is written, how coordinates should be scaled, what mode to use for verification, and what UI regions are reliable to observe. I see no important calling context missing.

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 already describes all four parameters, so the baseline is 3; the description adds meaningful coordinate-space and downscale context that directly affects how region and full_resolution should be interpreted. It does not separately expand on tag or whole_screen, but the schema handles those sufficiently.

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 opens with a specific verb and resource: 'Screenshot VRoid and return the image, plus the path it was saved to.' This clearly states the tool's purpose and main outputs, and the later coordinate-space discussion differentiates it from related perception tools like vroid_find_text and vroid_find_button.

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 explicit usage context: look at the returned image before deciding anything, capture the whole window when verifying changes, avoid relying on the dithered 3D viewport, and prefer vroid_find_text / vroid_find_button for coordinates. This goes far beyond a generic description and routes the agent to the right behavior and alternatives.

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