Skip to main content
Glama

commit_hygiene

Read-onlyIdempotent

Deterministic commit-message hygiene checker: conventional-commit format, vague-subject detection, subject-length limit, a same-message secret-pattern scan (AWS keys, private key headers, Slack/GitHub tokens, inline password=/secret= style credentials - checked against the message text only, never a diff), and an oversized-commit warning from caller-supplied insertions/deletions. POST one commit or a batch (max 200). Deterministic, no LLM, no network.

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": "commit_hygiene"
  }
}

Input Schema

NameRequiredDescriptionDefault
commitNoOne commit.
commitsNoAlternative: batch of up to 200 commits.
max_lines_changedNoDefault 500. Total insertions+deletions above this triggers a large_commit finding.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • changedInput schema / properties / commit / description
      Previous value: -"One commit: {sha?, message, insertions?, deletions?}. message is required."New value: +"One commit."
    • addedInput schema / properties / commit / properties
      Added value: +{
      +  "deletions": {
      +    "description": "Lines removed.",
      +    "minimum": 0,
      +    "type": "number"
      +  },
      +  "insertions": {
      +    "description": "Lines added; with deletions, drives the large_commit check.",
      +    "minimum": 0,
      +    "type": "number"
      +  },
      +  "message": {
      +    "description": "Full commit message: subject, blank line, body.",
      +    "maxLength": 20000,
      +    "type": "string"
      +  },
      +  "sha": {
      +    "description": "Optional sha, echoed back.",
      +    "type": "string"
      +  }
      +}
    • addedInput schema / properties / commit / required
      Added value: +[
      +  "message"
      +]
    • addedInput schema / properties / commits / items / description
      Added value: +"One commit."
    • addedInput schema / properties / commits / items / properties
      Added value: +{
      +  "deletions": {
      +    "description": "Lines removed.",
      +    "minimum": 0,
      +    "type": "number"
      +  },
      +  "insertions": {
      +    "description": "Lines added; with deletions, drives the large_commit check.",
      +    "minimum": 0,
      +    "type": "number"
      +  },
      +  "message": {
      +    "description": "Full commit message: subject, blank line, body.",
      +    "maxLength": 20000,
      +    "type": "string"
      +  },
      +  "sha": {
      +    "description": "Optional sha, echoed back.",
      +    "type": "string"
      +  }
      +}
    • addedInput schema / properties / commits / items / required
      Added value: +[
      +  "message"
      +]
    • addedInput schema / properties / commits / maxItems
      Added value: +200
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, closed-world, and non-destructive, and the description adds materially: determinism, no network, the message-only scope of the secret scan, the 200-commit batch ceiling, the caller-supplied nature of insertions/deletions, and the large_commit finding threshold. The explicit limitation that secrets are checked in the message rather than the diff is exactly the kind of caveat that prevents a caller from over-trusting the result.

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?

Purpose and behavior are front-loaded in a single dense paragraph with no filler sentences. The enumerated check list is long and slightly run-on, but every item corresponds to a real behavior, so little is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only, deterministic checker with no output schema, the description covers inputs, checks performed, limits, and determinism well. It does not describe the shape of the returned findings beyond naming finding types like large_commit, which would help an agent interpret results, but nothing needed to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3, but the description adds meaning by stating that insertions/deletions are caller-supplied and that their sum drives the large_commit check, clarifying that the tool performs no repository inspection. The 200-item batch cap is also restated as an operational constraint rather than only a schema maximum.

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 verb and resource ('commit-message hygiene checker') and enumerates the concrete checks performed: conventional-commit format, vague-subject, subject length, secret patterns, and oversized-commit. It is clearly distinguishable from nearby siblings such as pr_description_lint, ticket_lint, and story_lint, which target different artifacts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is well conveyed: POST a single commit or a batch of up to 200, and the tool is deterministic with no LLM or network, which implicitly routes agents here instead of a model-based alternative. It also scopes the secret scan to the message text only, never a diff, which prevents misuse. It stops short of explicitly naming an alternative tool or a when-not-to-use case.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.