Skip to main content
Glama

Create wiki page

gitlab_create_wiki_page

Create a new wiki page in a GitLab project by specifying the project ID, title, and content. Use it to add or publish project documentation directly through the GitLab API.

Instructions

Create a new wiki page for a project.

Args: **kwargs: Additional parameters for the request (e.g., project_id).

Returns: Response: A wrapper containing the original response and a WikiPage model.

Raises: MissingParameterError: If the project_id is missing. ParameterError: If invalid parameters are provided.

Input Schema

NameRequiredDescriptionDefault
dataNo
fileNo
slugNo
titleNo
branchNo
contentNo
versionNo
project_idNo
format_typeNo
render_htmlNo
with_contentNo
api_parametersNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv27.3.13

TDQS

B3/5.0
Behavior3/5

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true), so that ground is covered. The description usefully adds the return shape (a wrapper plus a WikiPage model) and named error modes, which matters given there is no output schema. It omits real behavioral questions for a create tool: what happens if a page with the same slug/title already exists, whether it overwrites, and whether project_id is actually required (the schema marks it optional with a null default, while the docstring says it raises MissingParameterError).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The single informative sentence is front-loaded, which is good, but the rest is Python docstring boilerplate ('Args: **kwargs: Additional parameters for the request') that conveys no information and actively misleads about the schema. The Returns/Raises blocks earn their place; the Args block does not.

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?

Placeholder — see recalibrated value below.

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

Parameters2/5

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

Schema description coverage is 0% across 12 parameters, so the description carries the full burden and largely fails: "**kwargs: Additional parameters for the request (e.g., project_id)" is generic boilerplate. It barely names project_id and says nothing about title, content, slug, branch, format_type, render_html, with_content, version, file, data, or api_parameters. An agent cannot infer which fields are needed to actually create a page.

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?

The first line states a specific verb and resource: "Create a new wiki page for a project." That clearly separates it from the update/delete/get wiki siblings in the same namespace. It stops short of explicitly naming those siblings or the scope of what a wiki page is, so it is clear but not maximally differentiating.

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?

There is no statement of when to use this versus gitlab_update_wiki_page, gitlab_upload_wiki_page_attachment, or gitlab_api_request, and no preconditions such as authentication or project resolution. The only conditional signal is a raised error, which is error handling rather than usage guidance.

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