Export Shape

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

The description goes beyond annotations by detailing the auto-selection behavior when object is omitted: it skips inputs consumed by other features, prefers solids over sketches, and raises an error if ambiguity remains. It also clarifies that the tool never picks one for you. This is valuable behavioral context that annotations (only destructiveHint true) do not convey. It does not contradict the destructive hint, as exporting to disk could overwrite files.

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?

The description is efficiently structured: the main purpose is front-loaded, and the object parameter details are organized in a clear block. Every sentence earns its place, explaining format inference and selection rules without fluff. It is slightly longer than strictly necessary but remains concise and readable.

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 a tool with only two parameters and no output schema, the description covers the essential aspects: formats, how format is determined, object selection logic, and error handling. It does not explicitly state prerequisites like an active document being open, but that context is likely implied by the document reference. Overall, it is complete enough for correct invocation.

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?

With 0% schema description coverage, the description must compensate fully. It explains the path parameter's format inference and the object parameter's meaning (FreeCAD object name, NOT a handle), optionality, selection algorithm, and error behavior. This adds substantial semantics beyond the bare schema field names and types, making the parameters understandable and usable.

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 clearly states the tool exports a shape to specific formats (STEP/IGES/BREP/STL) and infers format from the path extension. This gives a clear verb+resource+target. It doesn't explicitly contrast with sibling export tools like export_drawing or sheet_flat_export, but the purpose is unambiguous from the description and name.

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 description provides usage guidance for the object parameter (optional, selection rules, error behavior) and path extension format inference, but it does not explicitly tell the agent when to choose this tool over alternative export tools. There is no mention of alternatives or conditions that would route to a different export function, so the when-to-use guidance is incomplete.

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