Skip to main content
Glama
kompas-mcp

kompas-mcp

by biryak

Bodies: boolean / cut off / move

part_body

Combine, subtract, intersect, plane-cut, or move 3D bodies to build multi-body parts from extruded or revolved features, with volume verification and single-step undo.

Instructions

Multi-body parts (bodies come from part_extrude/part_revolve with new_body=true; list them with inspect_model(sections=['bodies'])). kind=boolean: base body + tool bodies, operation union | difference (base minus tools) | intersect. kind=cut_off: cut the part by a plane and keep the side with keep_point. kind=move: shift bodies by offset [dx, dy, dz] mm, copy=true keeps the originals. Verified by volume/bodies. Returns a receipt: created object handles, volume/mass before and after, backup path. The whole call is ONE Ctrl+Z for the user; if verification fails the model is restored and VERIFY_FAILED is returned.

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": {
      "doc": "<doc>",
      "kind": "<kind>"
    },
    "name": "part_body"
  }
}

Input Schema

NameRequiredDescriptionDefault
docYesDocument handle from doc_list/doc_open, e.g. 'doc:12001:0a1b2c3d'
baseNoboolean: obj: of the base body
copyNomove: keep the originals (copy)
kindYes
nameNoMeaningful feature name for the tree, e.g. 'Отв_крепёжные_6xD11'
planeNocut_off: XY|ZX|ZY | obj: plane | topo: face
toolsNoboolean: obj: of the tool bodies
bodiesNomove: obj: of the bodies
offsetNomove: mm
operationNounion
keep_pointNocut_off: [x, y, z] mm of the part that must remain

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.0

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (which only say the call mutates, is not idempotent and is not open-world), the description discloses that the return is a receipt with created handles, before/after volume and mass, and a backup path, and that the entire call collapses into one undo step. It also states the failure contract: on verification failure the model is restored and VERIFY_FAILED is returned, which directly qualifies the destructiveHint=false claim by explaining recoverability.

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?

It is dense and front-loaded: the body-source sentence comes first, then each kind, then the return and failure behavior. The telegraphic phrasing ('Verified by volume/bodies') is efficient rather than wasteful, though a couple of fragments could be read ambiguously by a weaker model.

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?

With 11 parameters, three operating modes, no output schema, and mutation semantics, the description covers everything an agent needs: where bodies come from, how each kind's parameters combine, what is returned (including a backup path), and how failures are reported. Nothing essential to a correct call is left unstated.

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 coverage is 82%, so the schema already carries most parameter meaning and the baseline is 3. The description adds real value on top by grouping parameters by kind (base/tools for boolean, plane/keep_point for cut_off, bodies/offset/copy for move) and by stating units (offset in mm) and the semantics of copy=true keeping the originals, which an agent would otherwise have to infer from terse schema titles.

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 names the resource (multi-body parts) and enumerates the three concrete operations it multiplexes: kind=boolean with union/difference/intersect, kind=cut_off with a plane plus keep_point, and kind=move with an offset/copy. It also anchors the tool in the workflow by naming part_extrude/part_revolve as the producers of bodies and inspect_model as the way to list them, so an agent can separate it from those siblings without opening any schema.

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

Usage Guidelines4/5

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

It gives clear preconditions (bodies must already exist, created with new_body=true, discoverable via inspect_model(sections=['bodies'])) and maps each kind to its required inputs. What is missing is an explicit statement of when not to use this tool, e.g. which sibling handles a body operation this one does not cover, so the routing guidance is strong but not exhaustive.

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