blender_inspect_scene

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description states it 'retrieves' metadata, which implies a non-destructive read, but it does not explicitly say whether it mutates the scene, requires permissions, or has side effects. It also does not describe the output format or behavior on failure (e.g., empty scene). For a tool with zero annotations, this is a significant gap.

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 a single sentence, concise and front-loaded with the main action. The list of data types is useful but could be seen as slightly dense; still, every word adds value and nothing is redundant. It could be restructured to separate the core purpose from the details, but it is not overlong.

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 the tool's complexity (a read-only inspector) and the fact that it has no parameters and no output schema, the description should explain what the tool returns and when to use it. The description covers the return content well but lacks guidance on preconditions, error scenarios, or alternative tools. It is adequate for a simple read, but an agent might not know if the scene can be empty or what happens then.

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 tool has zero parameters, so the schema provides no parameter semantics. The description compensates by enumerating the specific data that will be returned (mesh objects, transforms, polygons, vertices, materials, modifiers), giving the agent a clear idea of what to expect. Although it doesn't cover everything an output schema might, for a no-parameter tool this is sufficient.

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 starts with a clear verb ('Retrieves') and resource ('complete inspection metadata from the 3D scene'), and enumerates the specific content (mesh objects, transform coordinates, polygon counts, etc.). It is distinct from sibling tools, which focus on creating, modifying, exporting, or capturing, so an agent can infer it is a read-only inspection tool. However, it does not name a sibling explicitly as an alternative, which would have made its uniqueness even clearer.

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 usage as a read-only inspection snapshot, and given the sibling list (e.g., blender_execute_bpy, blender_capture_viewport), an agent can roughly guess when to use it. But there is no explicit guidance on when to use this tool versus alternatives, nor any mention of prerequisites (e.g., must have an open scene) or what happens if no scene is loaded. The context is clear enough for a basic read operation, but it lacks explicit routing.

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