Skip to main content
Glama
onshape-jamcp

onshape-jamcp

Mirror

mirror

Copies selected parts, features, or faces across a plane in Onshape to build symmetric geometry, with options to merge, cut, or intersect the copies.

Instructions

Mirror parts, features or faces across a plane. Mirroring a part gives a second part (operation 'new') or merges the copy into the original ('add'); mirroring the feature that makes one half builds a symmetric part. The default name shows the plane ('Mirror (Right)'). The reply says what changed (parts, volume).

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": {
      "document_id": "<document_id>",
      "element_id": "<element_id>",
      "plane": "<plane>"
    },
    "name": "mirror"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
planeYesMirror plane: 'Top', 'Front' or 'Right' (the origin planes) or the ID of a planar face (from get_body_details).
verifyNoMeasure the Part Studio before and after (two extra requests) and report what changed: part count and total volume, plus a warning when nothing changed (Onshape can accept a feature that does nothing). Set false to save requests.
face_idsNoRepeat these faces (IDs from get_body_details). Give exactly one of part_ids, feature_ids and face_ids.
part_idsNoRepeat these whole parts (IDs from list_parts). Give exactly one of part_ids, feature_ids and face_ids.
operationNoOnly for part_ids: 'new' makes each copy a separate part (default); 'add' merges the copies into existing parts; 'remove' cuts with them; 'intersect' keeps the overlap.new
element_idYesElement (tab) ID: the string after /e/ in the Onshape URL. Get it from get_document.
merge_withNoPart IDs the copies merge with when operation is 'add', 'remove' or 'intersect' (default: every part they touch).
document_idYesOnshape document ID: the 24-character hex string after /documents/ in the document URL. Get it from list_documents.
feature_idsNoRepeat these features (feature_id of an extrude or other feature, e.g. one spoke of a wheel); each copy merges the way the feature does. Give exactly one of part_ids, feature_ids and face_ids.
workspace_idNoWorkspace ID (the string after /w/ in the URL). Optional - defaults to the document's main workspace.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.1

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only, non-idempotent, open-world mutation that is not flagged destructive. The description adds real context beyond that — the default feature name derives from the plane, and the reply reports what changed — but the claim about the reply reporting parts and volume is only true when verify=true, which the description doesn't qualify.

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

Conciseness4/5

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

Four sentences, front-loaded with the action and its two outcomes before secondary details like naming and reply contents. A small amount of space is spent restating what the schema already explains about 'new' and 'add'.

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

Completeness4/5

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

An 11-parameter mutation with an output schema and high schema coverage is well served here: the description covers what gets mirrored and how copies are treated, and return values are legitimately deferred to the output schema. Missing is any note that part_ids, feature_ids and face_ids are mutually exclusive, though the schema states it.

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 coverage is 91% and the schema already documents plane formats, the mutually exclusive id parameters, operation semantics, and verify. The description reinforces the operation and feature-vs-part distinction but adds little that the schema does not already carry, so the baseline 3 applies.

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 verb and resource — mirror parts, features or faces across a plane — and immediately distinguishes the two outcomes (a new part vs. a merged copy vs. a symmetric feature build). It does not name a sibling alternative such as boolean or linear_pattern, so it falls short of a 5, but the operation is unmistakable.

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?

Gives useful within-tool guidance on 'new' vs. 'add' and on the difference between mirroring a part and mirroring the feature that makes one half. It offers no guidance on when to choose mirror over sibling operations like boolean or circular_pattern, so tool selection is still left to inference.

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