Skip to main content
Glama

mirror_history

Read-only

Lists live mirror files and history backup copies matching a Studio path so you can find a previous version to restore.

Instructions

What the on-disk mirror can bring back. The plugin saves every direct child of StarterGui, ReplicatedStorage, ServerStorage, StarterPack and Lighting as a .rbxm next to the script files (seconds after a change), and keeps a frozen copy in .history whenever one is removed, loses descendants (a delete or Ctrl+Z) or is overwritten after a quiet spell; scripts get the same. Lists the live mirror files and the history copies whose path matches path (a unit or anything inside it). Read-only. Restore one with restore_from_mirror; for snapshots taken inside the place use list_snapshots, and for committed script history use git_log.

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": "mirror_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoStudio dot path, or the start of one, to filter by, e.g. "StarterGui.MineGui". Omit to list everything.
limitNoMaximum history rows to return, up to 500. Default 40.
placeNoTarget place (PlaceId or project name). Defaults to the bound/sole connected place.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.1
    • changedInput schema / properties / limit / description
      Previous value: -"max history rows (default 40)"New value: +"Maximum history rows to return, up to 500. Default 40."
    • changedInput schema / properties / path / description
      Previous value: -"Studio path or part of one, e.g. StarterGui.MineGui (omit for everything)"New value: +"Studio dot path, or the start of one, to filter by, e.g. \"StarterGui.MineGui\". Omit to list everything."
  2. First observedv0.1.0

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, yet the description adds substantial behavior beyond them: what gets mirrored (direct children of StarterGui, ReplicatedStorage, ServerStorage, StarterPack, Lighting as .rbxm), the timing (seconds after a change), and precisely when frozen copies are created (removal, loss of descendants via delete or Ctrl+Z, or overwrite after a quiet spell). This tells an agent what data is recoverable and why a history copy may or may not exist, which is real value on top of the safety hints.

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?

It is one dense paragraph where the actual operation appears only after two sentences of mirroring background, so the key action is not front-loaded. The mechanism detail is useful but could have been compressed or moved after the statement of what the tool returns.

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?

With no output schema, the description does say what is returned (live mirror files plus matching history copies) and what the filter applies to. Missing is any mention of the shape of a returned row or how the `limit` interacts with ordering, but the essentials for calling it correctly are present.

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 baseline is 3; the description earns an extra point by clarifying that `path` matches a unit or anything inside it, i.e. subtree/prefix semantics, which the schema's "Studio dot path, or the start of one" only hints at. `limit` and `place` are left entirely to the schema, which is acceptable given their descriptions.

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 action is stated specifically: "Lists the live mirror files and the history copies whose path matches `path` (a unit or anything inside it)." That is a clear verb plus resource and it is differentiated from restore_from_mirror, list_snapshots and git_log. It loses a point because the operative sentence is buried after two sentences of mirroring mechanics, so the purpose is not front-loaded.

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?

The description names three alternatives and the condition that selects each: restore_from_mirror for restoring, list_snapshots for in-place snapshots, git_log for committed script history. It implies the use case ("What the on-disk mirror can bring back") without an explicit "use this when you need to inspect recoverable files" sentence, so it falls just short of full routing guidance.

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