create_text_to_3d_task

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

With no annotations, the description carries the load and does it well: it discloses that the operation is a two-step asynchronous task (draft then texture), imposes a prerequisite state (SUCCEEDED) and enumerates model-specific restrictions (ultra_mode preview-only for meshy-7, art_style deprecated for meshy-6). It does not mention credit cost or that the task must be polled via the retrieve/stream siblings, which an agent would need to know.

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 workflow, then the mode-specific requirements, then a compact enum list. Dense but every sentence carries information; no filler.

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?

Rich on inputs and workflow, but there is no output schema and the description never says what is returned (presumably a task id) or that the caller must then use retrieve_text_to_3d_task / stream_text_to_3d_task. Given the empty schema and missing output contract, the description leaves a real gap for an agent trying to complete the operation.

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 declares zero properties, so the description is the sole source of parameter meaning and it delivers enum values for ai_model, model_type, art_style, topology, symmetry_mode, pose_mode and origin_at plus cross-parameter constraints. Gaps: no defaults, and it names many parameters that do not appear in the schema at all, leaving the agent unsure what it can actually pass.

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 and resource ('Generate a 3D model from a text prompt') and front-loads the two-step workflow. The phrase 'from a text prompt' implicitly separates it from the image-based siblings (create_image_to_3d_task, create_multi_image_to_3d_task) that otherwise share the same verb.

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?

Explicitly sequences the two modes: preview first, then refine gated on a SUCCEEDED preview_task_id. It doesn't cover when to use this tool versus the image-to-3D or retexture siblings, but the internal workflow guidance is clear and actionable.

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