Skip to main content
Glama
Sign In
carmaker-mcp

carmaker-mcp

by dimitr-io
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Driver adaption

cm_driver_adaption
Destructive

Trains IPGDriver to learn a vehicle (basic) or circuit-specific race behavior, saves the learned knowledge, and lets you start, wait for, check, or cancel the adaptation run.

Instructions

Let IPGDriver learn the car (basic) or the car on this circuit (race), and save the knowledge. It takes minutes (basic about 2 standalone, 5 to 20 with MATLAB; race as long as the test run allows): run it only when the car changed noticeably, the race driver lacks knowledge, or the user asks, and tell the user the duration first. Start returns at once; then 'wait' until state is done/failed.

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_driver_adaption"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNobasic: learn the car (needed first); race: laps of a closed circuitbasic
modeNoauto: the MATLAB session if connectedauto
saveNoSave the knowledge (template file or test run; backed up)
actionYeswait: until it ends or timeout_s. close: end the CarMaker GUI the server opened for standalone adaptions (it stays open for the next one; it ends with the server)
testrunNoLoad this test run first (needed standalone)
knowledgeNoKnowledge set to learn into (default: the active one, else DefaultDriverKnowledge)
timeout_sNoLongest time to wait in s, at most 50 (larger values are cut to 50); call again if not finished
learning_rateNorace: 0 sensitive .. 1 aggressive

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.3.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already flag this as destructive and non-read-only; the description adds material operational context beyond them: expected durations per kind and mode (minutes, up to 5–20 with MATLAB), that start is non-blocking and must be followed by wait, and the GUI lifecycle implied for the close action. This is exactly the added value the annotations don't supply.

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 core verb and resource, then usage conditions, then the async pattern. Three sentences with little waste, though the parenthetical duration clause is dense and slightly interrupts the flow.

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?

An output schema exists and all 8 parameters are documented, so the description needn't restate them. It covers the key async workflow and safety-relevant duration/side-effect context. The cancel/status/close lifecycle is left to the schema rather than explained, which is a minor 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 100%, so the baseline is 3. The description adds meaning beyond the schema by tying kind and mode to duration expectations (basic ~2 standalone, 5–20 with MATLAB; race as long as the test run allows), which helps the agent reason about which mode to pick.

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?

States a specific verb and resource: lets IPGDriver learn the car (basic) or the car on a circuit (race) and save the knowledge. The two kinds are distinguished clearly. It doesn't differentiate itself from adaptation-adjacent siblings like cm_dva_write or cm_standalone_dva_write, so it stops short of 5.

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

Usage Guidelines5/5

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

Explicit when-to-use conditions are given: only when the car changed noticeably, the race driver lacks knowledge, or the user asks, plus the instruction to tell the user the duration first. The async contract is spelled out — start returns immediately, then call 'wait' until done or failed.

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