Skip to main content
Glama
Sign In

Runcrate

by io.github.aeonmindai
OverviewDiscussionsAdmin

Change an instance auto stop

set_instance_auto_stop
Destructive

Change when a running or starting instance stops on its own. Extend max_runtime_minutes before starting a job that will outlast the current auto_stop_at (get_instance shows it), and set max_runtime_minutes and idle_shutdown_minutes on any instance you leave working unattended. Max runtime counts from when the instance started running, so pass the total minutes, not extra minutes; a change never stops it sooner than 2 minutes from now. Pass null to turn a limit off; leave a field out to keep it. Either limit terminates the instance (not paused). Returns the instance with its new auto_stop_at.

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": {
      "id": "<id>"
    },
    "name": "set_instance_auto_stop"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesInstance ID, or its name if unique in the environment
workspaceNoWorkspace ID (optional: defaults to the authenticated workspace)
environmentNoEnvironment name (optional: defaults to the environment this session acts in)
max_runtime_minutesNoTotal minutes the instance may run, counted from when it started (5 to 10080). null turns max runtime off.
idle_shutdown_minutesNoTerminate after GPU utilisation stays under 5% with nobody connected (SSH, web terminal or editor) for this many minutes (5 to 1440). GPU instances launched with idle stop support only. null turns it off.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedInput schema / properties / env
      Removed value: -{
-  "description": "Environment name (optional — defaults to main)",
-  "type": "string"
-}
    • addedInput schema / properties / environment
      Added value: +{
+  "description": "Environment name (optional: defaults to the environment this session acts in)",
+  "type": "string"
+}
    • changedInput schema / properties / workspace / description
      Previous value: -"Workspace ID (optional — defaults to authenticated workspace)"New value: +"Workspace ID (optional: defaults to the authenticated workspace)"
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true, so the safety profile is known; the description goes further by disclosing the actual consequence ('Either limit terminates the instance (not paused)'), the 2-minute floor on how soon a change can stop it, and the null-vs-omit semantics. These are non-obvious behaviors an agent could otherwise get badly wrong.

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?

The purpose leads, followed by usage, semantics, and the return value, with no filler sentences. It is dense but slightly overloaded in a single paragraph; a small structural break between usage guidance and parameter semantics would scan faster.

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

Completeness5/5

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

Covers what the tool does, when to call it, the destructive terminal consequence, the timing floor, null/omit behavior, and the return shape ('Returns the instance with its new auto_stop_at'). With no output schema, that return note is exactly the missing piece an agent needs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so ranges and types are already documented, yet the description still adds real meaning: max_runtime_minutes is counted from start so the caller must pass total minutes rather than an increment, and omitting a field preserves it while null disables it. That increment-vs-total distinction is a classic misuse the schema alone does not prevent.

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 resource ('Change when a running or starting instance stops on its own') and immediately distinguishes itself from get_instance, which only reads the current auto_stop_at. An agent can tell this is the mutation counterpart to the read tool without inspecting either schema.

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?

Gives two concrete when-to-use scenarios: extend max_runtime_minutes before launching a job that outlasts auto_stop_at, and set both limits on instances left working unattended. It also names the alternative for inspection (get_instance) rather than leaving the agent to infer it.

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

All Runcrate toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources