Skip to main content
Glama
Sign In
carmaker-mcp

carmaker-mcp

by dimitr-io
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Control a standalone run

cm_standalone_control
Destructive

Manage a standalone IPG CarMaker simulation instance by starting, pausing, resuming, or stopping it, or opening IPGMovie for a movie-enabled study.

Instructions

Start, pause, resume or stop the simulation of a standalone instance, or open its IPGMovie. A study with movie=true runs on one instance: cm_standalone_status shows it.

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": {
      "action": "<action>"
    },
    "name": "cm_standalone_control"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesmovie: (re)open IPGMovie for the program
instanceNoStandalone instance id such as 'sa1' (may be omitted while there is only one)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.3.0
    • changedInput schema / properties / action / description
      Previous value: -"What to do"New value: +"movie: (re)open IPGMovie for the program"
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "start",
-  "pause",
-  "resume",
-  "stop"
-]New value: +[
+  "start",
+  "pause",
+  "resume",
+  "stop",
+  "movie"
+]
  2. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is known; the description adds that a movie=true study runs on one instance. However, it never says that 'stop' terminates a running simulation abruptly or what state is lost, which is exactly the consequence an agent needs before invoking a destructive action. No mention of auth, prerequisites, or idempotency.

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?

Two short sentences, action list front-loaded, no filler. The trailing clause about cm_standalone_status is slightly cryptic ('shows it' – shows what, the run?) but earns its place as a companion pointer.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and annotations covering safety, the description doesn't need to explain return values. But for a destructive multi-action control tool with overlapping siblings (cm_start_sim, cm_stop_sim, cm_movie_open, cm_standalone_close), the missing guidance on action consequences and sibling precedence leaves a real gap.

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%, with the action enum fully documented including the movie case, so the baseline is 3. The description contributes one extra fact not in the schema: that a study with movie=true is tied to a single instance, which hints at why 'instance' may be omitted. It adds nothing about the 'sa1'-style id format beyond the schema text.

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 names specific verbs (start, pause, resume, stop, open IPGMovie) against a specific resource (a standalone instance's simulation), matching the action enum exactly. It points to cm_standalone_status as the companion for observing state, which helps separate it from the many other start/stop siblings. It stops short of distinguishing itself from cm_start_sim / cm_stop_sim / cm_movie_open, which overlap on individual actions.

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?

Usage is implied by the enumerated actions rather than stated: an agent can infer 'use this to control a standalone run'. The only routing guidance given is that cm_standalone_status shows the running state. Nothing says when to prefer cm_start_sim or cm_movie_open over the corresponding actions here, despite those siblings covering the same ground.

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

Deploy Server

Other Tools