rag-rat

Overview Schema Source Related Servers Discussions Admin

repo_clusters

Map a repository into ownership clusters using path proximity, graph edges, and git co-touch to identify subsystems and representative files.

Instructions

Map the repo into ownership clusters from path proximity, graph edges, and git co-touch — a cheap overview of subsystems and their representative files.

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": "repo_clusters"
  }
}

Input Schema

Name	Required	Description
`limit`	No
`include`	No	What to include: `memories` (on by default), `generated` (off). Omit to keep defaults.
`worktree`	No	Absolute path of the checkout to scope reads to — pass a linked worktree to read its branch overlay. Defaults to the server's working directory. A path that is not a linked worktree of this repo is silently ignored: results then come from the indexed checkout, with no error.
`min_cluster_size`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.23.0Aug 19, 2026

addedInput schema / properties / worktree

Added value: +{
+  "description": "Absolute path of the checkout to scope reads to — pass a linked worktree to read its branch overlay. Defaults to the server's working directory. A path that is not a linked worktree of this repo is silently ignored: results then come from the indexed checkout, with no error.",
+  "type": "string"
+}

First observedv0.9.0-3b4b4b7Jun 25, 2026

TDQS

C2.9/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full disclosure burden. It discloses the clustering methodology and implies a read-only, low-cost operation via 'cheap', but it does not disclose default behaviors (limit=10, min_cluster_size=2), how the memories/generated include flags alter results, or any failure modes.

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?

A single, front-loaded sentence that stays on-topic. Every phrase contributes (methodology, cost profile, output shape), with no wasted words. It is appropriately compact for a mapper-style tool, though it could arguably have folded in a usage pointer.

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?

No output schema and no annotations exist, making the description the agent's sole source of behavioral truth. Given the 4 parameters and no return-shape information, the description is incomplete — it omits result format, default limits, and the important memories-on-by-default include behavior.

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?

The description adds no parameter-level meaning at all — it never mentions limit, min_cluster_size, include, or worktree. With schema description coverage at only 50%, the description fails to compensate for the two parameters (limit, min_cluster_size) left undocumented in the schema.

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 uses a specific verb ('Map') with a clear resource (the repo) and names both the methodology (path proximity, graph edges, git co-touch) and the expected output (subsystems and their representative files). It clearly differentiates from the search/view/memory siblings, but it does not distinguish itself from the closely-related repo_brief tool, which the schema explicitly references.

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 explicit when-to-use or when-not-to-use guidance is provided. The phrase 'a cheap overview' weakly implies a fast-orientation use case, but no alternatives are named and no exclusions are given — particularly problematic given the near-identical repo_brief sibling exists on the same enum.

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