inspect_scene

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

With no annotations present, the description carries the full burden, yet it only states the operation's purpose. It does not disclose whether the operation is read-only, what side effects occur, how the camera is selected, or what output the agent should expect.

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 entire description is one front-loaded sentence with no wasted words. It states the main action, the target resource, and the useful camera-recommendation outcome efficiently.

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 tool with one parameter and no annotations or output schema, this is thin: it omits the expected response shape, what 'authored camera' means in practice, and any prerequisites such as a loaded or resolved USD stage. An agent could invoke it, but it would be guessing about behavior and return value.

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?

Schema coverage is 0%, so the description must explain the lone 'scene' parameter; it adds only that the tool summarizes a 'USD stage,' giving a general domain but no format, path, or identifier requirements. The agent still has to guess what string value to pass beyond the parameter name.

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 names a specific action—'Summarize a USD stage'—and a concrete deliverable, 'recommend an authored camera for rendering,' so an agent can tell it apart from validation or material-inspection tools. It doesn't explicitly name sibling alternatives, so it misses the highest bar for differentiation.

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 phrase 'for rendering' implies the tool is used when preparing a render needs a scene overview and a camera suggestion, but no explicit when-to-use or when-not-to-use guidance is provided. Siblings like validate_scene and inspect_materials are not mentioned, so the agent must infer routing.

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