Skip to main content
Glama

git_sync

Synchronize Git history with the architecture whiteboard by running pre-commit verification gates, stamping commits, healing renames, refreshing AST anchors, and detecting drift.

Instructions

Step 4 (Verify & Sync): Run Git <-> Whiteboard sync: mode='pre' (50ms pre-commit gate checking STALE edit guard, AST signatures, call-graph % LAW reachability, > FLOW schemas, dangling imports, Bend 2 proofs, and unregistered_public_symbols; pass mark_verified=true to auto-transition STALE components to VERIFIED when allowed=true), mode='post' (stamp commit_sha, heal git mv renames, refresh #Lstart-Lend AST anchors, cascade STALE), mode='baseline', or mode='drift'.

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": "git_sync"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoSync mode: pre, post, baseline, or drift
boardNoTarget board name (default: lattice_core)
manifestNoOptional JSON manifest path or inline JSON string
project_rootNoOptional repository root path (auto-discovered by board name or file paths if omitted)
mark_verifiedNoAuto-transition STALE components to VERIFIED when mode='pre' gate passes (default: false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full burden and does disclose substantial behavior: a 50ms pre-commit gate with a named checklist, that post mode mutates state (stamps commit_sha, heals git mv renames, refreshes anchors, cascades STALE), and that mark_verified only fires when allowed=true. What it does not disclose is what happens when the gate fails (does it block, throw, or return a report), or whether the mutations in post mode are reversible. For a mutating tool with zero annotation coverage, that failure-path gap is significant.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is densely packed into a single run-on sentence with deeply nested parentheticals, so the four modes are not visually scannable. The purpose is not front-loaded — the reader hits 'Step 4 (Verify & Sync)' and then immediately a 50ms gate spec before learning the overall shape. Little of the content is wasted, but the structure makes extraction of the mode differences harder than necessary.

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 tool with five optional parameters, no annotations, and no output schema, the description covers the modes, the mutation semantics of post mode, and the mark_verified condition well. The main missing piece is return-value and failure behavior — an agent cannot tell what a failed pre-commit gate yields or how to detect it. Defaults for board and project_root are already in the schema, so their absence from the description is not a gap.

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 coverage is 100%, so the schema already documents all five parameters, but the description still adds real meaning beyond it: it explains what each mode does operationally, and it clarifies that mark_verified is conditional on both mode='pre' passing the gate and allowed=true. That conditional coupling between two parameters is not expressible in the schema and is genuinely useful. The board, manifest, and project_root parameters receive no added meaning in the description, relying entirely on 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 names a specific action (run a Git <-> Whiteboard sync) and enumerates the four modes it supports, so the agent knows which operation it is invoking. It also frames itself as 'Step 4 (Verify & Sync)', placing it in a workflow. It does not distinguish itself from siblings such as status or atlas, and the heavy jargon (LAW reachability, Bend 2 proofs) makes the subject matter opaque to an agent without domain context.

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 mode breakdown effectively functions as intra-tool routing: pre for a pre-commit gate, post for stamping commit_sha and cascading STALE, plus baseline and drift. The 'Step 4' framing implies it is the verification stage of a pipeline. However, there is no guidance on when to call this versus the sibling tools, no stated prerequisites (e.g. must a board be initialized first), and no when-not-to-use condition.

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