Skip to main content
Glama
Sign In
gitlab mcp

gitlab mcp

by zereight
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

update_issue_description_patch

Patch a GitLab issue description using search/replace or unified diff without resending the full body. Preview changes with dry_run and add a summarizing note.

Instructions

Patch an issue description (search/replace or unified diff) without resending the full body. dry_run previews; create_note summarizes.

Input Schema

NameRequiredDescriptionDefault
patchYesThe patch content to apply to the issue description
dry_runNoIf true, preview changes without updating the issue
jmespathNoOptional JMESPath expression filtering the JSON result before return.
issue_iidYesThe internal ID of the project issue
patch_typeYesType of patch format to apply
project_idYesProject ID or URL-encoded path
create_noteNoIf true, add a note summarizing the change after update
allow_multipleNoFor search_replace: allow multiple matches to all be replaced (default: false — fail on duplicate)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.1.66
    • addedInput schema / properties / jmespath
      Added value: +{
+  "description": "Optional JMESPath expression filtering the JSON result before return.",
+  "type": "string"
+}
  2. Changed1 schema field changedv2.1.62
    • changedInput schema / required
      Previous value: -[
-  "patch_type",
-  "patch",
-  "project_id",
-  "issue_iid"
-]New value: +[
+  "project_id",
+  "issue_iid",
+  "patch_type",
+  "patch"
+]
  3. Addedv2.1.18
  4. Removedv2.1.14
  5. Addedv2.1.12

TDQS

A3.5/5.0
Behavior3/5

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

Annotations only supply openWorldHint, so the description carries most of the burden. It usefully discloses two behavioral flags (dry_run previews, create_note summarizes after the update) but says nothing about permissions, match-failure behavior, or what happens to unmentioned description content.

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?

Two short sentences with zero filler, front-loading the core action and formats before the optional behaviors. Every clause carries information an agent needs.

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?

For an eight-parameter mutation tool with only openWorldHint for annotations and no output schema, the definition covers the happy path but leaves out error semantics (patch mismatch, duplicate matches) and permission requirements. Adequate but with clear gaps given the tool's complexity.

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%, so all eight parameters are already documented in the schema. The description's notes on dry_run and create_note largely restate the schema text and it adds nothing for allow_multiple, jmespath, or patch_type beyond naming the formats. Baseline 3 applies.

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 (patch) plus resource (issue description) and names the two supported formats (search/replace, unified diff). The clause 'without resending the full body' implicitly separates it from the sibling update_issue, though it never names that tool outright.

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

Usage Guidelines3/5

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

The description implies usage by contrasting with a full-body update, and it explains what dry_run and create_note do. But it gives no explicit when-to-use/when-not guidance and no prerequisite or failure conditions (e.g., what happens when a search pattern doesn't match).

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

Deploy Server

Other Tools