Skip to main content
Glama

list_project_files

Read-onlyIdempotent

List files and directories in a CERN GitLab project repository by path or recursively to inspect source code and documentation.

Instructions

List files and directories in a CERN GitLab project's repository. Supports recursive listing and path specific lookups.

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": {
      "project": "<project>"
    },
    "name": "list_project_files"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNoBranch name, tag, or commit SHA (default: project's default branch)
pathNoDirectory path within the repository (default: root '/')
projectYesProject identifier — either a numeric ID (e.g. '12345') or a namespace/project path (e.g. 'atlas/athena')
per_pageNoNumber of entries to return
recursiveNoIf true, list files recursively

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.4.0
    • changedInput schema / properties / project / description
      Previous value: -"Project identifier — either a numeric ID (e.g. '12345') or a URL-encoded path (e.g. 'atlas/athena')"New value: +"Project identifier — either a numeric ID (e.g. '12345') or a namespace/project path (e.g. 'atlas/athena')"
  2. Changed13 schema fields changedv0.3.0
    • addedInput schema / properties / path / default
      Added value: +""
    • addedInput schema / properties / path / title
      Added value: +"Path"
    • addedInput schema / properties / per_page / default
      Added value: +100
    • changedInput schema / properties / per_page / description
      Previous value: -"Number of entries to return (default: 100, max: 100)"New value: +"Number of entries to return"
    • addedInput schema / properties / per_page / title
      Added value: +"Per Page"
    • addedInput schema / properties / project / title
      Added value: +"Project"
    • addedInput schema / properties / recursive / default
      Added value: +false
    • changedInput schema / properties / recursive / description
      Previous value: -"If true, list files recursively (default: false)"New value: +"If true, list files recursively"
    • addedInput schema / properties / recursive / title
      Added value: +"Recursive"
    • addedInput schema / properties / ref / default
      Added value: +""
    • addedInput schema / properties / ref / title
      Added value: +"Ref"
    • addedInput schema / title
      Added value: +"list_project_files_fnArguments"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "title": "list_project_files_fnDictOutput",
      +  "type": "object"
      +}
  3. First observedv0.1.6

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered. The description adds only capability context (recursive, path-scoped) and says nothing about truncation or pagination, despite per_page being capped at 100, nor about behavior on a nonexistent path or ref.

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

Conciseness4/5

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

Two short, front-loaded sentences with no filler; the core purpose leads. The second sentence largely duplicates information already present in the input schema, which keeps it from a 5.

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?

With an output schema, full schema coverage, and complete safety annotations, the description needn't explain return values or safe reads. It is, however, silent on pagination limits (per_page max 100) and how to page through large directories, which matters for a listing tool that can be truncated.

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 100%, so every parameter (ref, path, project, per_page, recursive) is already documented in the schema. The description restates recursive and path without adding format, default, or edge-case semantics, so the baseline of 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?

The description states a specific verb and resource ('List files and directories in a CERN GitLab project's repository') and scopes it to a repository, so an agent knows exactly what the tool returns. It does not differentiate against siblings such as get_file_content or get_project_readme, which an agent could otherwise confuse with a listing call.

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?

Usage is only implied: 'recursive listing and path specific lookups' sketches capabilities, but there is no explicit statement of when to pick this over get_file_content, inspect_project, or get_project_readme. No prerequisites or exclusions are given.

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