gitlab-mcp

gitlab_mr_changes

Read-only

Read a merge request's per-file diff summary with status, line counts, and capped patches to find paths and lines before commenting, or fetch one file's patch.

Instructions

The merge request diff, summarised per file: status, added/removed line counts and a capped patch. Read this before commenting on a line, and to learn which paths and lines exist. Use path to pull one file's patch at a larger cap.

Input Schema

TableJSON Schema

Name	Required	Description
`iid`	Yes	project-scoped internal id - the number in !123 for a merge request or #123 for an issue, not the global id
`path`	No	return only this file
`project`	Yes	project id ('42') or full path ('group/subgroup/app'); a path is URL-encoded for you
`maxFiles`	No	files to include; the rest are counted in stats.omittedFiles
`maxPatchChars`	No	patch characters per file; a cut patch sets patchTruncated

Output Schema

TableJSON Schema

Name	Required	Description
`iid`	No
`sha`	No	source-branch HEAD; pass this to gitlab_mr_merge to pin the merge
`files`	Yes	one entry per returned file; capped by maxPatchChars each
`stats`	Yes
`web_url`	No
`merge_status`	No
`source_branch`	No
`target_branch`	No
`work_in_progress`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Oct 5, 2026

TDQS

A4.5/5.0

Behavior4/5

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

readOnlyHint=true already covers the safety profile, so the bar is lower. The description adds real context beyond annotations: output is per-file summarised and patches are 'capped', and it hints at a larger cap when path is supplied. It does not restate truncation flags, which the schema already carries.

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?

Three sentences, front-loaded with what the tool returns, then the usage trigger, then the parameter hint. No filler; every sentence 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?

With an output schema present and readOnlyHint covering safety, the description need only convey scope, usage trigger and the path shortcut — all of which it does. Nothing an agent needs to invoke this correctly is missing.

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 100%, so baseline is 3. The description goes beyond the schema by explaining the meaningful effect of 'path': it pulls one file's patch 'at a larger cap', which is behavioural guidance the schema's terse 'return only this file' does not convey.

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?

States a specific verb+resource ('the merge request diff') and enumerates what it returns per file (status, added/removed counts, capped patch). This clearly distinguishes it from siblings like gitlab_mr_get and gitlab_mr_versions without needing to name them.

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?

Explicitly states when to use it: 'Read this before commenting on a line, and to learn which paths and lines exist', which routes the agent away from blind commenting. It does not explicitly name gitlab_mr_comment_on_line or gitlab_mr_versions as alternatives, so it stops short of a 5.

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