export_model

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

With no annotations, the description carries the transparency burden. It discloses default behavior (temp directory for output_path, 'stl' default format), how variables map to -D flags, include_paths to OPENSCADPATH, and return fields. It stops short of failure modes or prerequisites, leaving room for improvement.

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 well organized with labeled Args and Returns, one line per parameter. It is front-loaded with the main purpose, and every sentence adds value without redundancy.

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?

The description covers all six parameters, clarifies their semantics, and specifies the return contract. For a tool with no schema descriptions and no annotations, this is comprehensive, though it could mention error handling or OpenSCAD prerequisites.

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?

The description adds critical meaning beyond the bare schema: mutual exclusivity of scad_content and scad_file, allowed output_format values, output_path fallback, and the semantic mapping for variables and include_paths. With 0% schema coverage, this is essential and well executed.

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 identifies the tool's action: 'Export OpenSCAD code or file to STL, 3MF, AMF, OFF, DXF, or SVG.' This specific verb and output format list distinguish it from sibling rendering tools like render_single.

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 clear context for when to use: whenever OpenSCAD code or a file needs conversion to a supported export format. It does not explicitly exclude use cases or reference alternatives, but the scope is evident from the format list.

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