openvsp.export_geometry

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

Goes well beyond the annotations by disclosing that the source is read into a private copy, that CAD/script/log/manifest artifacts are retained, and that validation only covers file structure and unit metadata. The explicit non-caveats (no closed-solid certification, no fusing of intersecting components) prevent false confidence in the output.

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 tight sentences, front-loaded with what the tool produces and its hard requirement, then artifacts, then validation limits. No repetition of schema content and nothing that could be dropped.

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?

Output schema exists, so return values need no explanation, and the description covers the essential gotchas — unit non-rescaling, artifact retention, geometric validity limits. Only marginal gaps remain, such as what happens on timeout or partial-export failure.

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%, so the schema already documents format, unit, tolerance, mode, set and timeout semantics in detail. The description's mention of an explicit source length unit and optional set/mode adds emphasis but no new parameter detail, so the baseline 3 applies.

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 pair — export STEP or IGES from a private model snapshot — plus the two export strategies. An agent can tell what is produced, though it doesn't explicitly distinguish this from openvsp.batch_export, the closest sibling.

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?

Clear preconditions are given: an explicit source length unit is mandatory and set/mode selection is optional, which tells the agent what must be supplied before calling. It stops short of naming when to prefer this tool over batch_export or the other export-capable siblings.

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