Skip to main content
Glama
hellstein-dev

fusion-mcp

by hellstein-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

surface_offset

Creates new surface bodies offset from selected faces by a signed distance, leaving the original faces unchanged.

Instructions

Offset surface: new surface bodies at a distance from faces (Offset feature).

The source faces stay unchanged. This differs from feature_offset_faces (c07), which moves faces of a solid; to give the result a thickness use body_thicken (c08). Units: distance in units (default mm). Refs: faces from inspect_query.

Errors: distance 0, a non-face ref, join/cut -> INVALID_PARAMS; offset_type rounded on an API without offsetType -> FUSION_API_ERROR "not available".

Returns {"feature", "health", "created_bodies" / "modified_bodies": [{ref, type, name, is_solid}], "removed_bodies"}.

Example: surface_offset(faces=[], distance=2)

Input Schema

NameRequiredDescriptionDefault
chainNoAdd tangent-connected faces
facesYesFace refs (inspect_query); re-query after later features
unitsNoUnit of plain-number lengths and pointsmm
distanceYesSigned offset (not 0): positive along the face normal
operationNonew_body (default) or new_componentnew_body
offset_typeNosharp (default) or rounded corners (newer API)sharp

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it states the source faces stay unchanged, maps error conditions to INVALID_PARAMS and FUSION_API_ERROR, discloses the rounded-offset API limitation, and describes the return shape.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose and key distinction, then compactly covers units, refs, errors, return shape, and an example. Every section provides operational value without waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter surface tool with no annotations and no output schema, the description gives the agent enough to call it correctly: scope, alternatives, ref sourcing, error cases, return structure, and an example.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 all six parameters in detail. The description adds useful error context and reiterates units and face-ref sourcing, but does not add much beyond the schema for chain, operation, or offset_type semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource — creating offset surface bodies from faces — and immediately distinguishes this from feature_offset_faces and body_thicken. An agent can identify the tool's role without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly names alternatives and when to use them: feature_offset_faces moves solid faces, while body_thicken adds thickness to the result. It also routes the agent to inspect_query for face refs, giving clear usage context.

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

Deploy Server

Other Tools