Skip to main content
Glama

service_manage

Destructive

Deploy, update, configure, roll back, or remove OS package and container services with preview-only or confirmed changes to control the full lifecycle.

Instructions

Manage service lifecycle, deployment, declarative configuration, and rollbacks.

Actions:

  • 'deploy': Deploy a new service from an approved OS package or declarative container spec.

  • 'update': Upgrade/downgrade OS package version or container image (auto-rolls back if unhealthy).

  • 'configure': Replace declared config files or patch container spec (masked diff preview).

  • 'rollback': Restore the previous revision of configuration/version.

  • 'remove': Stop, uninstall, and unmanage a service (data retained unless delete_data=true).

Safety: confirm=false returns a preview/diff without modifying state; confirm=true applies.

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>",
      "confirm": "<confirm>"
    },
    "name": "service_manage"
  }
}

Input Schema

NameRequiredDescriptionDefault
osNoOS package specification for deploy
kindNoService kind disambiguator
filesNoNew config files for configure
imageNoTarget container image for update
startNoStart service after deploy (default true)
actionYes
confirmYesfalse = preview only; true = apply change
serviceYesTarget service name
versionNoTarget OS package version for update
containerNoContainer specification for deploy
spec_patchNoContainer spec patch for configure
delete_dataNoDelete persistent data during remove (default false)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.3

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds real context on top: update auto-rolls back if unhealthy, configure shows a masked diff preview, remove retains data unless delete_data=true, and confirm=false returns a preview without mutating state. It does not cover auth/permission requirements or whether a rollback is itself undoable, which keeps it below a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A one-line purpose, a bulleted action table, and a single safety line — front-loaded and scannable, with no filler. The opening phrase mildly overlaps the 'deploy' bullet, but it establishes the whole domain before the enumeration and earns its place.

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?

For a 12-parameter, 5-action lifecycle tool with an output schema present, the description supplies what the schema cannot: per-action parameter intent, the preview/apply gate, and data-retention behavior on removal. Error behavior and cross-action parameter validation (e.g. passing image with configure) are the only soft spots, and those are minor given the output schema and rich field descriptions.

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 92%, so the baseline is 3, but the description goes further by binding parameters to actions: os for deploy, image/version for update, files/spec_patch for configure, delete_data for remove, confirm for apply-versus-preview. That mapping is genuinely useful because the schema alone lists the parameters flatly without saying which action consumes which.

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 opening sentence names the resource (service) and the scope (lifecycle, deployment, declarative configuration, rollbacks), and the action bullets give a specific verb per operation. An agent can tell what the tool does, but nothing in the text distinguishes it from siblings like service_control or service_inspect, which share the 'service' domain.

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

Usage Guidelines4/5

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

Each action carries an inline condition that implies when to pick it (deploy = new service from OS package or container spec; update = version/image change; configure = config replacement or spec patch; rollback = restore previous revision; remove = stop/uninstall). The confirm=false/confirm=true sentence gives concrete usage guidance for preview-versus-apply. Missing is any explicit exclusion, e.g. telling the agent to use service_control for start/stop rather than this tool.

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