Skip to main content
Glama
kompas-mcp

kompas-mcp

by biryak

Shell

part_shell

Hollows a solid body to specified wall thickness and opens selected faces, returning created object handles, volume/mass changes, and a backup path for single-step undo.

Instructions

Hollow the body leaving walls of the given thickness; listed faces become openings. 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>",
      "faces": "<faces>",
      "thickness": "<thickness>"
    },
    "name": "part_shell"
  }
}

Input Schema

NameRequiredDescriptionDefault
docYesDocument handle from doc_list/doc_open, e.g. 'doc:12001:0a1b2c3d'
nameNoMeaningful feature name for the tree, e.g. 'Отв_крепёжные_6xD11'
facesYestopo: faces to remove (openings)
outwardNo
thicknessYeswall, mm

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.2

TDQS

A4/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses the return receipt contents (created object handles, volume/mass before and after, backup path), the single-undo semantics, and the failure path where the model is restored and VERIFY_FAILED is returned. This is exactly the behavioral context the terse annotation set (destructiveHint=false, idempotentHint=false) does not supply.

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?

Two dense sentences with zero filler: the operation is front-loaded and the return/undo/failure contract follows in a single compact clause. Nothing repeats or pads.

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?

With no output schema, the description properly covers the receipt and error behavior, so the big gap is closed. It still omits which body/document context the operation applies to and the meaning of the outward flag, which matters for a 5-parameter modeling call.

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 80% and the schema already documents doc, name, faces ("faces to remove (openings)") and thickness ("wall, mm"), so the description's restatement of "faces become openings" and wall thickness adds little. The outward flag — the one genuinely ambiguous parameter — is not explained anywhere.

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?

"Hollow the body leaving walls of the given thickness; listed faces become openings" names a specific CAD verb (shell), its resource (the body), and its precise geometric effect, which an agent can distinguish from siblings like part_hole or part_extrude without inspecting schemas.

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

Usage Guidelines2/5

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

The description never states when to choose shelling over a hole/extrude workflow, what preconditions apply (which body is targeted, whether a selection is required), or any when-not case. Usage is only inferable from the mechanical explanation of what the call does.

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