Skip to main content
Glama

gitlab_items

Search, read, and create GitLab issues and merge requests; filter by state, labels, author, or keyword, post comments, and preview changes before confirming.

Instructions

Search, read, and create GitLab issues and merge requests.

Actions:

  • 'list': Search or list issues or MRs (filter by state, labels, author, keyword).

  • 'read': Read an issue or MR description and discussion comments.

  • 'create_issue': Open a new issue with title, description, and labels (confirm=false previews).

  • 'comment': Post a comment to an issue or MR (confirm=false previews).

  • 'create_mr': Open a merge request between branches (confirm=false previews).

  • 'close_issue': Close an issue created by vps-mcp (confirm=false previews).

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>",
      "project": "<project>"
    },
    "name": "gitlab_items"
  }
}

Input Schema

NameRequiredDescriptionDefault
iidNoIssue or MR number
bodyNoComment body
kindNo'issue' or 'mr'
limitNoItems limit
stateNoState filteropened
titleNoIssue or MR title
actionYes
authorNoAuthor filter
labelsNoLabels
searchNoSearch term
confirmNofalse = preview only; true = apply
projectYesProject alias from gitlab_projects
descriptionNoIssue or MR description
notes_limitNoDiscussion notes limit
source_branchNoMR source branch
target_branchNoMR target branch

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 declare readOnlyHint=false and openWorldHint=true but say nothing about the two-phase confirm workflow; the description supplies that ('confirm=false previews' repeated per mutating action), which is genuinely useful behavior beyond the annotations. It also discloses a non-obvious constraint that 'close_issue' only closes issues created by vps-mcp. No annotation contradiction — the mixed read/write action set is consistent with readOnlyHint=false and destructiveHint=false.

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?

Front-loaded summary sentence followed by a compact bulleted action index; every line corresponds to an enum value and adds a distinguishing detail. There is no filler and no repetition across bullets.

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 16 parameters, two required, an output schema present, and annotations covering safety, the description covers all six actions and the confirm workflow. The remaining gap is the lack of a per-action parameter matrix, forcing the agent to infer which of the 14 optional parameters are required or meaningful for the chosen action.

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 description coverage is 94%, so the schema already documents every parameter, and the description largely restates it ('filter by state, labels, author, keyword' mirrors those four schema fields). It adds no per-action parameter mapping — nothing tells the agent that iid is needed for 'read'/'comment'/'close_issue' or that source_branch/target_branch apply only to 'create_mr', which is the one thing the 16-param schema cannot express on its own.

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 set and resource ('Search, read, and create GitLab issues and merge requests'), and each action is enumerated with its own verb+object pair ('list': Search or list issues or MRs; 'create_mr': Open a merge request between branches). An agent can map a user intent to an exact action value 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.

Usage Guidelines4/5

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

The action list effectively doubles as when-to-use guidance: use 'list' to search/filter, 'read' for descriptions and discussion comments, 'create_issue'/'create_mr' to open new items. It also flags the preview-vs-apply pattern for every mutation. The gap is the absence of explicit exclusions or routing to siblings (e.g., when to use gitlab_repo instead), so an agent must infer boundaries.

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