Skip to main content
Glama

gitlab_deploy

Destructive

Deploy GitLab refs to declared VPS targets with preview/apply plans and rollback to prior releases while restarting associated services.

Instructions

Deploy git code versions from GitLab to declared VPS targets with zero-downtime rollback.

Actions:

  • 'targets': List declared deploy targets, active release version, and retention history.

  • 'deploy': Deploy a git ref to a VPS target (confirm=false returns plan; confirm=true applies).

  • 'rollback': Revert a target to its previous release and restart associated services.

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": "gitlab_deploy"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNoe.g. 'v1.5', 'branch:main', or commit SHA
actionYes
targetNoDeploy target name from policy
confirmNofalse = preview only; true = apply change
plan_idNoPlan ID from confirm=false preview
releaseNoNamed historical release for rollback

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.3

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and openWorldHint=true, so the risk bar is partly covered. The description adds real behavioral context beyond that: deploy is a two-phase plan/apply flow, and rollback explicitly 'restart[s] associated services', which is a side effect an agent must know about. It omits permission/authorization requirements and what happens to in-flight traffic during rollback.

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 single front-loaded summary sentence followed by a tight, bulleted action list. Every line carries distinct information and nothing is repeated from the schema or annotations.

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?

With an output schema present and annotations carrying the risk profile, the description covers the essentials for a destructive, multi-action tool. The gaps are minor: prerequisites for target declaration and rollback defaults (previous release vs. named release) are left implicit.

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 83%, so the baseline is 3, but the description earns more by tying parameters together: confirm=false returns a plan, confirm=true applies, and the plan feeds plan_id. That relationship is meaningful semantics the schema alone only implies. It does not clarify whether 'release' is optional for rollback or how 'target' resolves against policy.

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?

The opening sentence names a specific verb and resource ('Deploy git code versions from GitLab to declared VPS targets') plus a distinguishing trait ('zero-downtime rollback'). The three enumerated actions make the tool's scope fully legible and separable from siblings like gitlab_ci or service_control.

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 is scoped with a use case: 'targets' for discovery, 'deploy' for applying a ref, 'rollback' for reverting. The confirm=false/confirm=true split gives clear operational guidance. It stops short of explicit when-not-to-use guidance or prerequisites (e.g., target must already be declared in policy), so it is not a 5.

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