Skip to main content
Glama

service_control

Start, stop, restart, or manage boot status for VPS services, with confirmation safeguards for protected services and verified status reporting.

Instructions

Control runtime state of a managed service on the VPS.

Actions:

  • 'start': Start a stopped service and report verified status.

  • 'stop': Stop a service (protected services require confirm=true).

  • 'restart': Restart a service and report verified state (logs included on failure).

  • 'enable_boot': Enable service to start automatically at system boot.

  • 'disable_boot': Disable service from starting at boot (protected requires confirm=true).

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": {
      "service": "<service>",
      "action": "<action>"
    },
    "name": "service_control"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoService kind disambiguator
actionYes
confirmNoOperator approval flag (required for protected services)
serviceYesTarget service name

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.3

TDQS

A3.5/5.0
Behavior3/5

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

The description adds real context beyond the annotations: a confirm=true gate for protected services and that restart reports verified state with logs on failure. However, 'protected services' is never defined and there is no way for the caller to know in advance whether a gate will apply, which is a meaningful gap for a mutation tool. There is also mild tension with idempotentHint=false, since 'start' and 'enable_boot' are naturally idempotent, and the description does not reconcile this.

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?

One orienting sentence followed by a scannable per-action bullet list, with the destructive/gated cases called out inline. Slight redundancy between 'report verified status' and 'report verified state', but nothing that wastes real space.

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?

An output schema exists, so return values are covered, and the description usefully adds failure-log behavior. Still missing for a four-parameter mutation tool: what 'kind' means and when to set it, what counts as a protected service, and what happens when an action fails or is rejected for lack of confirmation.

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 enum values are listed there, but the description supplies the meaning of each action and ties 'confirm' to the protected-service condition, which the schema only gestures at. The one unexplained parameter is 'kind' (os vs container), which the description never mentions.

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 opens with a specific verb and resource ('Control runtime state of a managed service on the VPS') and enumerates the five discrete actions, so an agent can immediately tell what the tool does. It does not differentiate itself from the sibling 'service_manage', which by name sounds like a close neighbor, leaving the boundary between the two unstated.

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 conveyed implicitly through per-action semantics (e.g. 'start' is for a stopped service), which is more than nothing. But there is no explicit statement of when to choose this over service_manage or service_inspect, and no guidance on when a service would be considered 'protected' or how an agent should discover that before calling.

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