Skip to main content
Glama
kompas-mcp

kompas-mcp

by biryak

Thread / rib / draft

part_thread_rib_draft

Creates cosmetic threads, ribs, and face drafts in KOMPAS-3D parts, verifies each change, and returns handles, volume/mass changes, and a backup path.

Instructions

kind=thread: cosmetic thread (условное изображение резьбы, ГОСТ 2.311) on a cylindrical face — a shaft (outer, face Ø = d) or a bore (inner, face Ø = drill d1); designation 'M20' / 'M20x1.5' is looked up in KOMPAS's thread table. kind=rib: rib (ребро жёсткости) from a sketch with an open line running between two walls, symmetric thickness. kind=draft: draft (уклон) of faces about a neutral plane/face, inward (removes material) unless outward=true. Verified: rib adds volume, draft moves it the chosen way, the thread is valid and reads back its designation. 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_thread_rib_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
docYesDocument handle from doc_list/doc_open, e.g. 'doc:12001:0a1b2c3d'
baseNodraft: neutral plane/face (XY|ZX|ZY|obj:|topo:)
faceNothread: topo: cylindrical face
kindYes
leftNothread: left-hand
nameNoMeaningful feature name for the tree, e.g. 'Отв_крепёжные_6xD11'
sideNorib: side the rib grows to; auto tries bothauto
angleNodraft: degrees
facesNodraft: topo: faces to tilt
lengthNothread: mm from the face start (default: whole face)
sketchNorib: obj:/$N sketch with one open line
threadNothread: designation, e.g. 'M20', 'M20x1.5'
outwardNodraft: add material instead of removing it
standardNothread: table name for non-metric threads
thicknessNorib: full thickness, mm

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.0

TDQS

A4.3/5.0
Behavior5/5

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

Substantial disclosure beyond the annotations: verification is performed (rib adds volume, draft moves it the chosen direction, thread reads back its designation), the model is restored with VERIFY_FAILED on failure, a backup path is produced, the receipt carries created handles and volume/mass before and after, and the whole call collapses to one Ctrl+Z. The reversibility and rollback story is exactly the context an agent needs for a mutating tool and is consistent with readOnlyHint=false and reversible-per-call semantics.

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?

Front-loaded and organized by 'kind=', so an agent can scan to the branch it needs, and the verification/receipt sentence closes with the operationally important facts. It is dense with parentheticals, GOST references and Cyrillic terms that add precision but increase reading cost, and the opening sentence is long enough that a reader must parse carefully.

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 15-parameter, three-mode mutation tool with no output schema, the description covers the mode-specific inputs, the failure mode, and the return payload (handles, before/after volume/mass, backup path), which is precisely what the missing output schema would otherwise have to supply. Nothing an agent needs to invoke it correctly appears absent.

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 already 93%, so the baseline is 3; the description still adds real meaning by tying face diameter to thread type (outer d vs inner drill d1), stating that designations are resolved against KOMPAS's thread table, and clarifying symmetric rib thickness and inward-by-default draft direction. Remaining parameters such as name, left and standard are left to the schema, which already documents them.

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?

The description gives a specific verb+resource for each dispatch value: cosmetic thread on a cylindrical face (outer Ø=d shaft vs inner Ø=drill d1 bore), a rib from an open-line sketch between two walls, and a draft of faces about a neutral plane. That is much more than restating the name. It stops short of a 5 because it never contrasts these operations with the plausible siblings an agent will weigh (part_hole for real threads/holes, part_extrude or part_sweep_loft for rib-like geometry).

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?

Prerequisites are stated per kind: thread needs a 'topo:' cylindrical face plus a designation from KOMPAS's table, rib needs an 'obj:/$N' sketch with exactly one open line running between two walls, draft needs a neutral plane/face and the faces to tilt. That is clear context for selecting a kind. It lacks any when-not guidance (e.g. when to prefer part_hole or a profile extrusion instead), so it falls short of a 5.

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