Skip to main content
Glama

fetch_tool

Clones a GitHub repository into ./tools-cache for inspection: accepts an owner/repo string, a github.com URL, or a catalog name, and can report clone status. It only clones, nothing is built or run.

Instructions

Shallow-clone a GitHub repository (from the catalog, 'owner/repo' or a github.com URL) into ./tools-cache. Clone only: nothing is built or executed.

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": {
      "repo_or_query": "<repo_or_query>"
    },
    "name": "fetch_tool"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoclone
repo_or_queryYes'owner/repo', a https://github.com/... URL, or a catalog name

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries full burden and does disclose meaningful traits: shallow-clone depth, a fixed local destination, catalog/URL/repo-slug source resolution, and the guarantee that nothing is built or executed. It omits several behaviors that matter for a network+filesystem operation: auth/network requirements, what happens if the target already exists, and what 'status' mode does.

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 the operation and destination front-loaded and the safety caveat immediately after. Every clause earns its place and nothing is padded.

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 a 2-parameter tool with no annotations and no output schema, the description covers the clone path adequately but leaves the 'status' branch completely undefined and gives no signal about the return shape. An agent invoking mode='status' would be acting blind.

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 50%. The description reinforces and slightly extends repo_or_query semantics by noting the source must come from the catalog and can be a github.com URL. The 'mode' parameter's 'status' enum value is explained nowhere — not in the schema description and not in the description — so coverage of half the parameters remains blank.

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 opens with a specific verb+resource ('Shallow-clone a GitHub repository') plus the exact destination ('./tools-cache'), which clearly separates it from catalog_search/catalog_categories siblings. The only deduction is that it never mentions the 'status' mode the schema exposes, so the tool's full purpose is not fully stated.

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?

'Clone only: nothing is built or executed' usefully bounds the operation and implicitly tells the agent not to expect build/run behavior. However, there is no guidance on when to pick mode='status' over the default clone, nor on prerequisites (private repos, existing cache contents), leaving alternatives to inference.

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