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

Annotations cover the safety profile (readOnly=false, destructive=false, non-idempotent), and the description adds genuinely new behavior: it returns immediately, rendering takes ~30-60s (longer for 'realistic'), a preview fills in inline, and a link allows open/edit/export. It does not mention rate limits, cost, or how to poll status, which keeps it short of a 5.

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?

Front-loaded with the core action and output format, followed by async behavior, then usage guidance — a sensible ordering with no filler. It is dense at four clauses in the second sentence, but each clause carries distinct information (latency, preview, edit link, export formats).

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 an async generation tool with a full output schema and annotations, the description covers the essentials an agent needs: input modes, latency expectations, the deferred preview, and downstream edit/export options. The only omission is how the agent should later check on the render, which the sibling check_3d_model presumably handles.

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 description coverage is 100%, so the schema already documents all four parameters, including the draft/realistic quality modes and the imageUrl image-to-3D path. The description restates the prompt/image duality and adds only the rough timing for 'realistic', so the baseline 3 applies.

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?

States a specific verb+resource ('Generate a 3D model (glTF/GLB)'), names the destination workspace, and enumerates both input modes (text prompt or reference image). This clearly separates it from siblings like create_image, create_video, and create_diagram without needing to name them.

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?

'Use when the user asks for a 3D model, mesh, or asset' gives explicit triggering context, and 'Best for a single object' sets a scoping limit. However, it never names an alternative (e.g. create_image for 2D, or check_3d_model for polling status), so the routing guidance is contextual rather than exclusionary.

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