shape_import_meshImport STL or OBJ files as mesh nodes in metres; use y_up=true to convert Y-up files to Z-up.
Shape Studio: import an STL or OBJ file as a mesh node (metres). y_up=true if the file is Y-up (converted to Z-up). For GLB/FBX use the Shape Studio UI import button.
| Name | Required | Description | Default |
|---|---|---|---|
| at | No | ||
| name | No | ||
| path | Yes | Absolute file path (.stl/.obj) | |
| y_up | No | ||
| scale | No | Uniform scale (e.g. 0.001 for mm files) | |
| surf_id | No |
Changes observed during successful MCP inspections.
v4.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is a non-read-only, non-destructive, non-idempotent, closed-world operation, so safety is covered. The description adds genuinely useful behavior beyond that: the metres unit convention and the automatic Y-up to Z-up axis conversion, which is a real data transformation the caller must know about. It still omits preconditions (must a document be open?) and whether repeated imports stack new nodes.
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 short sentences, front-loaded with the action and scope, then the coordinate-flag explanation, then the unsupported-format redirect. No filler and nothing buried.
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 should say what an import produces (a node id? a tree entry?) so the agent can chain into shape_edit_node or shape_set_params, and it should state whether an existing document is required. It covers formats, units, and axis handling but leaves those integration points unaddressed.
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 33%, and the description compensates for two gaps: it defines the unit system (metres) and explains y_up as 'true if the file is Y-up (converted to Z-up)', which the schema leaves completely undescribed. However, at, name, and surf_id get no explanation in either place.
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 ('import an STL or OBJ file as a mesh node') and scopes the supported formats explicitly, which cleanly separates it from the shape_export_stl/shape_export_obj siblings that move data the other direction. The 'Shape Studio:' prefix identifies the owning subsystem.
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?
Gives a concrete routing condition: for GLB/FBX use the Shape Studio UI import button, which tells the agent when this tool does not apply. It does not name any MCP sibling alternative, but no sibling tool performs mesh import, so the gap is minor.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.