Skip to main content
Glama
kompas-mcp

kompas-mcp

by biryak

Embodiments

embodiment

List, create, and activate GOST 2.113 part or assembly variants in KOMPAS-3D, including numbered executions like '01' and selecting the current configuration.

Instructions

Embodiments (исполнения, ГОСТ 2.113) of a part/assembly. action=list: all with marking, number, mass. create: new embodiment with number like '01' (marking = base marking + '-01'); it becomes CURRENT. activate: make embodiment index current. Variables (variables_set) and properties set afterwards apply to the CURRENT embodiment only — create the part variables BEFORE the first embodiment (KOMPAS refuses new variables in a dependent embodiment). Creating is one Ctrl+Z; switching is not undoable (as in KOMPAS).

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>"
    },
    "name": "embodiment"
  }
}

Input Schema

NameRequiredDescriptionDefault
docYesDocument handle
indexNoactivate: index from action=list
actionNolist
numberNocreate: '01', '02'…

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.0

TDQS

A4.2/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnly=false, destructive=false, idempotent=false) by disclosing the mutation model: create is a single undo step, activate is NOT undoable, and create implicitly changes which embodiment is CURRENT and therefore which one later variable/property writes hit. That is exactly the side-effect context an agent needs before mutating document state.

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 with the resource and per-action semantics, then the ordering and undo caveats. Dense parentheticals and Cyrillic/GOST asides add domain precision rather than filler, though the run-on final sentence could be split for readability.

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?

For a stateful mutation tool with no output schema and incomplete annotation coverage, it covers the essentials: what list yields, what create produces, what activate changes, and undo behavior. It does not state what create/activate return on success or what happens on an invalid index, which is a minor residual 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 coverage is 75%, and the description still adds meaning: 'number' is a zero-padded string like '01' from which marking is derived as base marking + '-01', and 'index' is tied to the values returned by action=list. The only gap is that the 'doc' handle parameter gets no elaboration, which the schema already covers adequately.

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?

Names the resource precisely in domain terms ('Embodiments (исполнения, ГОСТ 2.113) of a part/assembly') and defines all three verbs inline: list returns marking/number/mass, create makes a new numbered embodiment, activate flips the current one. No sibling in the catalog overlaps this domain, so cross-tool differentiation is unnecessary rather than missing.

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?

Gives concrete workflow sequencing ('create the part variables BEFORE the first embodiment') and a hard constraint ('KOMPAS refuses new variables in a dependent embodiment') that steers when each action may be called. It stops short of explicit when-not guidance or pointing to another tool for property/variable operations, so a 4 rather than a 5.

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