create_remesh_task

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

With no annotations, the description carries the full burden. It does disclose a meaningful behavioral mode (format-only conversion skips remeshing) and enumerates accepted input formats, but says nothing about the async task lifecycle, whether the source model is modified or preserved, cost/credit implications, or what create returns. Enough to call it correctly, not enough to predict consequences.

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?

Four dense sentences, purpose first, then input sourcing, then enum vocabularies, then the special mode. No filler and no repetition of anything a structured field already provides.

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 unannotated creation tool with no output schema, the description should at least hint at the return value (a task ID to poll) and that the operation is long-running. Inputs are fully covered, the result contract is not, and the mismatch with the empty input schema is left unexplained.

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 declared schema has zero properties, so the description is the only source of parameter meaning: it names five inputs, gives two enum vocabularies ('quad'/'triangle', 'bottom'/'center'), lists file extensions, and flags the either/or constraint. The only deduction is that these parameters are absent from the schema, leaving an agent unsure whether to trust the description or the empty object.

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 verb+resource pair is precise: 'Remesh and optimize an existing 3D model', with the operand further narrowed to either a completed task ID or a model URL. That cleanly separates it from the many create_* siblings that originate models (text-to-3d, image-to-3d) rather than post-processing an existing one.

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?

It states the two mutually exclusive input paths (input_task_id OR model_url) and when to choose the degenerate mode (convert_format_only=true for format conversion without remeshing). It stops short of naming the follow-up tools (retrieve_remesh_task / stream_remesh_task) or any when-not-to-use condition, so no explicit alternative routing.

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