gitlab-api

Gitlab Graphql Ops Retry Pipeline

gitlab_graphql_ops_retry_pipeline

Retry failed jobs in a GitLab pipeline using GraphQL by specifying the project ID and pipeline ID.

Instructions

Retry the failed jobs of a pipeline through GraphQL.

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": {
      "project_id": "<project_id>",
      "pipeline_id": "<pipeline_id>"
    },
    "name": "gitlab_graphql_ops_retry_pipeline"
  }
}

Input Schema

Name	Required	Description	Default
`project_id`	Yes	Project id or full path.
`pipeline_id`	Yes	Pipeline id.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv27.3.20Nov 7, 2026

removedInput schema / properties / params_json

Removed value: -{
-  "default": "{}",
-  "description": "JSON string of parameters to pass to the action.",
-  "type": "string"
-}

addedInput schema / properties / pipeline_id

Added value: +{
+  "description": "Pipeline id.",
+  "type": "integer"
+}

addedInput schema / properties / project_id

Added value: +{
+  "description": "Project id or full path.",
+  "type": "string"
+}

addedInput schema / required

Added value: +[
+  "project_id",
+  "pipeline_id"
+]

First observedv27.3.13Oct 25, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already establish that this is a non-read-only but non-destructive mutation, so the safety profile is covered. The description adds real value by scoping the effect to failed jobs only, implying successful jobs are untouched. It still omits what a retry produces (a new pipeline vs. re-run jobs), whether all failed jobs are retried unconditionally, and any permission requirements.

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?

A single front-loaded sentence with no filler; the resource scope follows immediately after the verb. It is efficient, though the brevity leaves no room for the operational context an agent would benefit from.

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?

With full schema coverage, annotations, and no output schema, the description covers the essential purpose. It is still thin for a mutation tool: it does not clarify the outcome of a retry (new pipeline or new job records), whether all failed jobs are affected at once, or the preconditions on pipeline state.

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

Parameters3/5

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

Schema coverage is 100% with two fully documented parameters (project_id as id or full path, pipeline_id as integer), so the schema carries the burden. The description adds no format or interpretation detail beyond it, which makes baseline 3 appropriate.

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 (retry) and a precise resource scope (the failed jobs of a pipeline), which is enough to separate it from siblings like gitlab_retry_project_job (single job) and gitlab_run_pipeline (new run). It does not explicitly name those alternatives, so the differentiation must be inferred from the scope wording.

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

Usage Guidelines2/5

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

The phrase 'of a pipeline' implies the triggering condition is a pipeline with failed jobs, but there is no explicit when-to-use statement, no when-not to prefer gitlab_retry_project_job or gitlab_run_pipeline, and no note on whether this only applies when the pipeline is in a retryable state.

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

Deploy Server