Skip to main content
Glama
cq27-dev

rag-rat

by cq27-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

commit_search

Search historical commit messages by keyword to identify when and why a change was made.

Instructions

Full-text search over historical commit subjects and bodies — find when/why something changed by keyword.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
queryYes
worktreeNoAbsolute 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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.23.2
    • removedInput schema / $defs
      Removed value: -{
-  "McpGraphMode": {
-    "enum": [
-      "none",
-      "compact",
-      "full"
-    ],
-    "type": "string"
-  },
-  "SearchInclude": {
-    "description": "`semantic_search` `include` flags. `git`/`papertrail` are on by default (omit `include` to keep\nthem); `generated`/`fallback` are off by default.",
-    "enum": [
-      "generated",
-      "git",
-      "papertrail",
-      "fallback"
-    ],
-    "type": "string"
-  }
-}
    • removedInput schema / properties / explain
      Removed value: -{
-  "default": false,
-  "type": "boolean"
-}
    • removedInput schema / properties / graph_limit
      Removed value: -{
-  "default": 3,
-  "format": "uint32",
-  "minimum": 0,
-  "type": "integer"
-}
    • removedInput schema / properties / include
      Removed value: -{
-  "default": null,
-  "description": "What to include: `git`, `papertrail` (both on by default), `generated`, `fallback` (off by\ndefault). Omit to keep defaults; an explicit list is the exact on-set.",
-  "items": {
-    "$ref": "#/$defs/SearchInclude"
-  },
-  "type": [
-    "array",
-    "null"
-  ]
-}
    • removedInput schema / properties / include_graph
      Removed value: -{
-  "$ref": "#/$defs/McpGraphMode",
-  "default": "compact"
-}
  2. Changed3 schema fields changedv0.23.0
    • removedInput schema / properties / worktree / default
      Removed value: -null
    • changedInput schema / properties / worktree / description
      Previous value: -"Absolute path to a linked git worktree you're working in. When set, results are served from\nthat worktree's branch overlay (its committed + uncommitted changes) on top of the indexed\ncheckout; omit to query the indexed checkout. An unrelated/invalid path falls back to it."New value: +"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."
    • changedInput schema / properties / worktree / type
      Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
  3. First observedv0.9.0-3b4b4b7

TDQS

B3.3/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the search operation but does not mention read-only behavior, result ordering, pagination, error cases, or the worktree fallback behavior that appears only inside the schema. For a tool with no annotation safety signals, this is a meaningful transparency gap.

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?

The description is a single, front-loaded sentence with no filler. It communicates the resource, the search mode, and the intended answer in one compact phrase, making it easy for an agent to parse quickly.

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?

Given there is no output schema full-text search tool, the description should explain what results look like or how they are ordered, but it does not. It also lacks usage routing relative to many related siblings. The worktree behavior is hidden in the schema description, and no guidance about limits or edge cases is present, leaving the definition incomplete for reliable invocation.

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 only 33% (worktree has a description; query and limit do not). The tool description itself adds no parameter-level meaning and does not compensate for the undocumented required query parameter or the limit semantics. The parameter names are somewhat self-explanatory, but the description provides no additional clarification beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource ('historical commit subjects and bodies') and a specific mode ('full-text search'), making the core function unmistakable. It also sets expectations for what results answer ('when/why something changed'), which distinguishes it from sibling tools like semantic_search or git_history_for_path.

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?

The description implies its use case—keyword-based searching of commit history—but never explicitly states when to choose it over alternatives such as semantic_search, rationale_search, or commits_touching_query. There is no exclusion guidance or comparison, so the agent must infer selection from sibling names and the description alone.

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

Deploy Server

Other Tools