model_export

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

With no annotations, the description itself supplies important safety and environment behavior: export writes to disk without changing the model, the server operates on an already-open Creo through CREOSON, and actions other than save do not invoke file/save. It does not disclose overwrite handling, directory creation, or failure and result behavior.

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?

Most of the opening Chinese paragraph concerns dimensions, feature listing, selectors, suppression, and layers rather than model_export, so the relevant export guidance is not front-loaded. The five action bullets also largely repeat information already conveyed by the action names and schema.

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?

Together with the rich variant schema, the description supports basic selection and invocation by covering export kinds, non-mutation, environment constraints, and image sizing. For a five-action disk-writing tool with no annotations or output schema, the unsupported STL example and missing overwrite and result guidance remain meaningful operational gaps.

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%, establishing a baseline of 3; the description adds useful image units, a practical size/DPI recommendation, and notes that dirname is optional for file export. Those gains are offset by listing STL as a file-type example even though the file variant's enum does not permit STL, which could induce an invalid call.

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 states a specific operation and resource: "Write a model to disk without changing it," then enumerates file, PDF, 3D PDF, image, and plot exports. It does not explicitly distinguish native saving through model_save or previewing through preview_image, so some sibling differentiation is left to inference.

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 action list provides clear output-oriented contexts, and the recommendation to use about 4 x 6 inches at dpi 100 gives practical guidance for image export. There is no explicit when-not guidance or routing to alternatives such as model_save, preview_image, or feature_xml_export.

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