Proofpack

Overview Schema Source Related Servers Discussions Admin

Proofpack acceptance report

proofpack_check

Read-onlyIdempotent

Inspect a Git repository read-only and generate a Markdown or JSON acceptance report covering change facts, review prompts, unrun checks, and limitations for AI-assisted changes.

Instructions

Inspect the current Git repository read-only and return a Markdown or JSON acceptance report with change facts, review prompts, unrun checks, and limitations.

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": "proofpack_check"
  }
}

Input Schema

Name	Required	Description
`cwd`	No	Optional starting directory for Git discovery. Defaults to the MCP server process working directory.
`base`	No	Optional Git ref to compare committed, staged, and working-tree changes against. Untracked files are excluded in this view.
`format`	No	Report format. Defaults to markdown.
`language`	No	Display language for Markdown and JSON text fields. Defaults to en or PROOFPACK_LANG.
`shareSafe`	No	Omit branch, HEAD, paths, base commit, and other identifying evidence on a best-effort basis.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 14, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered without prose. The description still adds real value by disclosing the report's composition — notably 'unrun checks' and 'limitations', which signal that the tool surfaces but does not execute checks, a non-obvious behavioral trait.

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?

A single dense sentence that leads with the action and scope, then the output contract. No filler, no restated title, nothing that could be cut without losing information.

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?

There is no output schema, so the description must describe the return, and it does so by naming the report's four sections and the two supported formats. What is slightly under-specified is the notion of an 'acceptance report' and what an 'unrun check' means in practice, though annotations cover the read-only and closed-world behavior.

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 100% with all five parameters documented, including enum values and defaults, so the schema does the heavy lifting. The description contributes no parameter-level meaning beyond that; the baseline 3 applies.

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 gives a specific verb ('Inspect'), a specific resource ('the current Git repository'), and enumerates what the returned acceptance report contains (change facts, review prompts, unrun checks, limitations). This is far more than a restatement of the name, though with no sibling tools listed there is no alternative to distinguish it from.

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?

Usage is implied by 'the current Git repository' — an agent can infer it applies to repo-scoped review/acceptance work. However, the description never states when to prefer this tool over other checks, what prerequisites exist (e.g., must be inside a Git work tree), or what happens outside a repository.

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

This server cannot be deployed

Other Tools

proofpack_checkA