gitlab-api

Get group subgroups

gitlab_get_group_subgroups

Read-onlyIdempotent

Retrieve subgroups for a specified GitLab group ID to list nested groups and manage group hierarchies.

Instructions

Get subgroups of a specific group.

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

Returns: Response: A wrapper containing the original response and a list of Group models.

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

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "gitlab_get_group_subgroups"
  }
}

Input Schema

Name	Required	Description	Default
`data`	No
`name`	No
`page`	No
`path`	No
`avatar`	No
`argument`	No
`group_id`	No
`per_page`	No
`max_pages`	No
`visibility`	No
`description`	No
`lfs_enabled`	No
`total_pages`	No
`default_branch`	No
`emails_enabled`	No
`membership_lock`	No
`mentions_disabled`	No
`wiki_access_level`	No
`auto_devops_enabled`	No
`duo_features_enabled`	No
`ip_restriction_ranges`	No
`share_with_group_lock`	No
`project_creation_level`	No
`request_access_enabled`	No
`shared_runners_setting`	No
`subgroup_creation_level`	No
`two_factor_grace_period`	No
`file_template_project_id`	No
`default_branch_protection`	No
`lock_duo_features_enabled`	No
`allowed_email_domains_list`	No
`enabled_git_access_protocol`	No
`shared_runners_minutes_limit`	No
`math_rendering_limits_enabled`	No
`prevent_forking_outside_group`	No
`unique_project_download_limit`	No
`require_two_factor_authentication`	No
`default_branch_protection_defaults`	No
`extra_shared_runners_minutes_limit`	No
`lock_math_rendering_limits_enabled`	No
`unique_project_download_limit_alertlist`	No
`unique_project_download_limit_allowlist`	No
`prevent_sharing_groups_outside_hierarchy`	No
`auto_ban_user_on_excessive_projects_download`	No
`unique_project_download_limit_interval_in_seconds`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedv27.3.20Nov 7, 2026

removedInput schema / properties / api_parameters

Removed value: -{
-  "anyOf": [
-    {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}

changedInput schema / properties / argument / default
```
Previous value: -"state=opened"New value: +null
```

removedInput schema / properties / avatar / anyOf

Removed value: -[
-  {
-    "format": "binary",
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedInput schema / properties / avatar / title
```
Added value: +"Avatar"
```
changedInput schema / properties / page / default
```
Previous value: -1New value: +null
```
changedInput schema / properties / per_page / default
```
Previous value: -100New value: +null
```

First observedv27.3.13Oct 25, 2026

TDQS

C2.8/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuine value by naming the error conditions (MissingParameterError, ParameterError) and the wrapper-plus-Group-list return shape. It omits pagination behavior entirely, which is significant for a list endpoint exposing page, per_page, and max_pages.

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

Conciseness3/5

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

Google-docstring Args/Returns/Raises structure is front-loaded and readable, and the purpose sentence comes first. But the Args block is boilerplate that says nothing useful about the 45-parameter surface, so the space is spent on formatting rather than content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 45-parameter list tool with no output schema and no annotation coverage of pagination, the definition should explain page/per_page/max_pages semantics and which filters actually apply. It covers the return type adequately but leaves the call-correctness details an agent needs unaddressed.

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 45 parameters, so the description must carry the load and does not. It reduces the interface to '**kwargs ... (e.g., group_id)', which misrepresents a schema of explicit named properties and explains none of the pagination parameters or the many group-attribute filters present.

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 and resource: 'Get subgroups of a specific group.' An agent can tell it lists child groups of one parent. However, it offers no differentiation from close siblings such as gitlab_get_group_descendant_groups, gitlab_get_project_groups, or gitlab_get_nested_projects_by_group, leaving the subgroups-vs-all-descendants distinction to inference.

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?

No when-to-use, when-not-to-use, or alternative-selection guidance is given. The description never says whether this returns only immediate children or recursive descendants, which is precisely the decision point among the sibling group-listing tools.

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

Deploy Server