get_viewport_screenshot

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

The description explains behavioral aspects: it returns a file path, uses OpenGL for speed, and is for visual verification. With no annotations provided, it carries the full burden but does not mention potential limitations (e.g., viewport must be active) or read-only nature explicitly. It is sufficient but not exhaustive.

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 three concise sentences, front-loaded with the main action. Each sentence adds distinct value: action, output, and use case. No wasted words.

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 the core purpose, output, and a use case, but misses explaining the only parameter (max_size). Given no output schema, it partially fills gaps but lacks completeness for a tool with one undocumented parameter.

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 input schema has one parameter (max_size) with 0% description coverage. The description does not explain its meaning or effect, leaving the agent to guess that it controls the maximum dimension or file size. This is a critical gap for a simple tool.

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 action ('Capture a screenshot of the 3D viewport'), the output ('Returns the file path'), and the method ('Uses OpenGL render for speed'). It distinguishes the tool from siblings, as no other sibling tool explicitly captures viewport screenshots.

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 provides context by stating 'Useful for visual verification of scene state,' which implies a use case. However, it does not explicitly differentiate from similar tools like render_still or render_image, nor does it state when not to use this tool.

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