Create a GitLab merge request from a source branch to a target branch with a title, description, and labels; dry-run validates that both branches exist before opening it.
Create a merge request. dry_run (default true) only checks that both branches exist.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | ||
| labels | No | ||
| dry_run | No | ||
| project | No | group/name or numeric id; default: GITLAB_PROJECT or the origin remote | |
| description | No | ||
| source_branch | Yes | ||
| target_branch | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnlyHint=false and openWorldHint=true. The description adds a genuinely important trait beyond that: the default invocation is a no-op branch check, not a creation — a real behavioral disclosure that prevents accidental calls. It omits return shape, error behavior, and auth requirements, keeping it short of 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, front-loaded with the action and immediately qualifying the default behavior. No filler, though the second sentence is packed so densely that the critical 'set dry_run=false to actually create' implication has to be inferred.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
This is a mutation tool with an unusual default that makes it a no-op, no output schema, and 14% schema coverage. The description should explicitly state that dry_run must be disabled to create and clarify branch/title expectations; instead it leaves the most consequential behavior implicit.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 14% — just 'project' has a description. The description explains dry_run's semantics well but leaves six parameters (source_branch, target_branch, title, description, labels, and their formats/constraints) undocumented in both schema and prose, so it does not compensate for the coverage gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ("Create a merge request"), clearly distinct from the sibling read tool gitlab_mr_list. It does not explicitly contrast against any sibling, but the resource is unambiguous enough that an agent can select it without opening the schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The note that dry_run defaults to true and only verifies branch existence is useful implied guidance: an agent can infer it must set dry_run=false to actually create the MR. However, the description never says this explicitly and offers no when-to-use vs alternatives guidance or prerequisites (e.g., branch must exist, permissions needed).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.