Skip to main content
Glama
ai-commit-helper-mcp

ai-commit-helper-mcp

by mahshid

create_commit_rules

Creates a .commit-helper.json file in the repository root from chosen commit-message rules to configure commit validation; fails if the file already exists.

Instructions

Create a .commit-helper.json file in the repository root using the user's chosen commit-message rules. Fails if the file already exists.

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": {
      "repositoryPath": "<repositoryPath>",
      "rules": "<rules>"
    },
    "name": "create_commit_rules"
  }
}

Input Schema

NameRequiredDescriptionDefault
rulesYes
repositoryPathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.1/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose two real behaviors: the exact file written (repository root, .commit-helper.json) and the non-overwrite failure mode, which tells an agent this is not idempotent and will error on a second call. It says nothing about required permissions, what is returned on success, or whether the repository path must already exist.

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 sentences, front-loaded with the action and target file, with the failure caveat following naturally. Nothing is padded, though it is arguably under-written rather than tightly written.

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?

The tool writes a file, takes a nested object with a two-value enum, has no annotations and no output schema, and the description omits enum semantics, success behavior, and how the created file relates to validate_commit_message. For that complexity level, the definition leaves too much for the agent to infer.

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 0% for both parameters, so the description must compensate and largely does not: 'repository root' hints at repositoryPath, and 'user's chosen commit-message rules' maps to rules, but there is no explanation of what the 'typed' vs 'ticket' enum values mean or what maxSubjectLength constrains. The nested rules object is the most error-prone part of the call and receives no guidance.

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?

States a concrete verb and artifact: creates a .commit-helper.json file at the repository root from the user's chosen commit-message rules. That is enough to distinguish it from the read/validate siblings (get_commit_context, validate_commit_message) without naming them, though it never explicitly contrasts itself with those siblings.

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?

Implied usage is clear — call it when the user has chosen commit-message rules and the config file does not yet exist — and the 'Fails if the file already exists' clause gives a useful precondition. There is no explicit when-to-use/when-not-to-use guidance or reference to the sibling validation tool as the alternative once the file is in place.

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