Auto-fix a 3D model

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

Describes autonomous self-critique behavior and mentions slowness, but no info on side effects or permissions. With no annotations, description does reasonable job.

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?

Three short, focused sentences; no fluff; effectively front-loaded with purpose.

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?

Missing details on parameters, return values, error conditions, and model mutation behavior. 5 parameters with no explanation is inadequate.

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?

No parameter information in description despite 0% schema coverage. Key parameters like submission_id, dest, wait, max_iters, project_id are left unexplained.

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?

Clearly states it runs an automatic refinement pass on a model and distinguishes from sibling tool thrixel_edit_model.

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 tells when to use (model roughly right but can't articulate) and when not to use (use thrixel_edit_model if you can describe the issue).

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