List files and subdirectories at any path in a GitHub repository, including the root, to explore repository structure and locate code before browsing or searching further.
List files and subdirectories at a given path in a GitHub repository.
| Name | Required | Description | Default |
|---|---|---|---|
| ref | No | ||
| path | Yes | Directory path. Empty string for repo root. | |
| repo | No | ||
| owner | No |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden and largely drops it: nothing about token/auth requirements for private repos, rate limits, result truncation (GitHub caps large directories), or how entries are ordered. Only 'List' hints at a read-only operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with no filler, mapping directly to verb and scope. It is efficient, though its brevity edges into under-specification rather than pure concision.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With four parameters at 25% coverage, no annotations, and no output schema, the description should explain what is returned (entry names only vs. type/size/SHA) and how owner/repo/ref combine. None of that is present, so an agent knows the purpose but not the contract.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 25% — just 'path' is documented. 'owner', 'repo', and especially 'ref' (branch/tag/commit selector) are unexplained in both schema and description, and the description does not compensate; it only vaguely gestures at 'a GitHub repository' and 'a given path'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('List') and resource ('files and subdirectories at a given path in a GitHub repository'), which is enough to separate it from github_get_file (single file) and github_list_repos (repos, not contents). It stops short of naming those siblings explicitly, so it is clear but not maximally differentiated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description never says when to use this versus github_get_file, github_search_code, or a recursive listing, and offers no prerequisites (auth, private repo access). Usage is only inferable from the verb 'List', which is the same bar as the MID calibration example.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.