Skip to main content
Glama

Sweep

sweep

Creates a solid by moving a profile sketch along a spine sketch to form an additive pipe, with optional mode and transition controls.

Instructions

Sweep a profile sketch along a spine sketch (additive pipe).

profile: handle of the cross-section sketch. spine: handle of the path sketch (in the same body). mode: 'Standard' | 'Frenet' | 'Auxiliary' | 'Binormal'. transition: 'Transformed' | 'Right corner' | 'Round corner'.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "profile": "<profile>",
      "spine": "<spine>"
    },
    "name": "sweep"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoStandard
nameNoSweep
spineYes
profileYes
workspaceNoRun this call in this named workspace
transitionNoTransformed

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.7
    • addedInput schema / properties / workspace
      Added value: +{
      +  "default": "",
      +  "description": "Run this call in this named workspace",
      +  "title": "Workspace",
      +  "type": "string"
      +}
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is largely covered. The description adds real value beyond them by labeling the operation 'additive' — i.e. it grows material rather than cutting — and by constraining the spine to the same body. It stops short of saying whether a new named feature/handle is created or how the result is returned.

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?

One definition sentence front-loads the operation, followed by a tight per-parameter glossary — no filler and no restatement of the tool name. Every line contributes either meaning or allowed values.

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

Completeness3/5

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

For a mutation that builds a solid feature with no output schema, the description covers inputs and the additive nature but not the outcome: whether a feature/handle is created, how to reference the result, or what constitutes failure. Given the surrounding workflow (make_sketch, close_sketch, then feature creation), that omission is the meaningful remaining gap.

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

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 17% (only `workspace` is documented), so the description carries the load for the other five parameters and does so for four of them: it explains the roles of `profile` and `spine` plus the same-body constraint, and it enumerates the allowed values for `mode` and `transition`, which the schema leaves as bare strings. Only `name` is left unexplained.

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

Purpose4/5

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

States a specific CAD verb (sweep) with both operands named: a profile sketch swept along a spine sketch, and the parenthetical '(additive pipe)' disambiguates it from a subtraction. It does not explicitly differentiate itself from nearby additive-sweep siblings such as loft, revolve, pad, or helix, so the agent must infer the distinction from domain knowledge.

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

Usage Guidelines3/5

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

There is one genuine prerequisite embedded in the parameter notes — the spine must be a path sketch 'in the same body' — which tells the agent when the call is valid. However, nothing steers the agent away from loft/revolve/pad/helix when those would be correct, and no failure conditions (open profile, non-planar spine, self-intersection) are given.

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