Skip to main content
Glama
kompas-mcp

kompas-mcp

by biryak

Batch

batch

Applies multiple modeling operations as one atomic, undoable step; restores the model and returns VERIFY_FAILED if verification fails.

Instructions

Several operations as ONE atomic step (one Ctrl+Z): all succeed or the model is restored. 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>",
      "ops": "<ops>"
    },
    "name": "batch"
  }
}

Input Schema

NameRequiredDescriptionDefault
docYesDocument handle from doc_list/doc_open, e.g. 'doc:12001:0a1b2c3d'
opsYes[{op:'sketch'|'extrude'|'revolve'|'fillet_chamfer'|'shell'|'pattern'|'aux_plane'|'hole'|'sweep'|'loft'|'thread'|'rib'|'draft', ...same arguments as the single tools...}]; boss/cut of extrude/revolve/sweep/loft goes as operation:'cut'. Refer to the result of op N as '$N', e.g. extrude {sketch:'$0'}.
dry_runNobuild, verify, then undo; report what would happen

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.6.0
    • changedInput schema / properties / ops / description
      Previous value: -"[{op:'sketch'|'extrude'|'revolve'|'fillet_chamfer'|'shell'|'pattern'|'aux_plane'|'hole', ...same arguments as the single tools...}]. Refer to the result of op N as '$N', e.g. extrude {sketch:'$0'}."New value: +"[{op:'sketch'|'extrude'|'revolve'|'fillet_chamfer'|'shell'|'pattern'|'aux_plane'|'hole'|'sweep'|'loft'|'thread'|'rib'|'draft', ...same arguments as the single tools...}]; boss/cut of extrude/revolve/sweep/loft goes as operation:'cut'. Refer to the result of op N as '$N', e.g. extrude {sketch:'$0'}."
  2. First observedv0.4.2

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly=false, destructive=false, and idempotent=false; the description adds real context beyond that by explaining the rollback semantics, the receipt contents (handles, volume/mass before/after, backup path), and the VERIFY_FAILED failure mode. The non-destructive claim in annotations is reconciled by the explicit restore-on-failure behavior, though it is not spelled out that the restore is guaranteed even on partial side effects.

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 key guarantee in the first sentence, and every sentence carries information. The 'one Ctrl+Z' idea is repeated twice ('ONE atomic step (one Ctrl+Z)' and 'The whole call is ONE Ctrl+Z for the user'), which is mild redundancy.

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 appropriately covers return values and the failure path, which is what an agent needs for a complex mutation tool. It stops short of covering op ordering constraints or the full set of failure codes, but the core contract is complete.

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 100%, so the schema already documents doc, ops (including the $N result-reference convention), and dry_run. The description adds only the return-value shape (receipt fields), not additional meaning for the input parameters themselves; baseline 3 applies.

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?

States a specific verb and scope: combining several operations into ONE atomic step, with an explicit all-or-nothing guarantee. This clearly distinguishes it from the single-operation siblings like part_extrude or part_fillet_chamfer without needing to name them.

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?

The atomicity framing and the dry_run mention imply when the tool is appropriate (multi-step builds that must not half-apply), but the description never says explicitly 'use the single tools for one op' or states prerequisites such as needing a doc handle from doc_open. Usage is inferable rather than stated.

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