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

Annotations only cover safety/idempotency; the description adds genuinely new behavioral context: the download link expires in 30 minutes, and the format fidelity caveat that STEP is only a solid B-Rep when the source was read exactly, otherwise a non-editable triangulated STEP. That is exactly the kind of downstream consequence an agent needs before choosing a target format.

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 front-loaded sentences: action + return value first, then the fidelity caveat. Every sentence carries information an agent needs; 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?

With no output schema, the description responsibly describes the return (expiring download link) and the format trade-offs. Missing coverage of wait_seconds and of the ref input constraint keeps it short of complete for a four-parameter tool.

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 coverage is only 25%, so the description must compensate. It usefully clarifies the target enum semantics (solid vs triangulated STEP; STL/GLB always mesh), which illuminates the step_kind options. However, wait_seconds is never explained and the ref-vs-upload_ticket distinction lives only in the schema, leaving a real gap.

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 (Convert) and resource (a CAD file opened with inspect_cad), names the three output formats, and discloses the return value (a download link). An agent can distinguish this from inspect_cad, open_in_workspace and refresh_view_token without opening any schema.

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?

Clearly establishes the prerequisite that the file must already be opened via inspect_cad, which routes the agent along the correct workflow. It does not, however, state any when-not-to-use conditions or contrast explicitly with sibling tools for choosing alternatives.

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