Skip to main content
Glama

mnemon_wal_rewind

Recover PostgreSQL to a historical timestamp or WAL LSN by forking an isolated zero-copy copy-on-write branch, enabling point-in-time recovery without altering the source database.

Instructions

31ms Point-in-Time Recovery & WAL rewind: forks an isolated zero-copy CoW PostgreSQL branch from an arbitrary historical timestamp or LSN.

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": "mnemon_wal_rewind"
  }
}

Input Schema

NameRequiredDescriptionDefault
project_idNoOptional project ID
sandbox_idNoOptional sandbox ID to rewind
target_lsnNoTarget PostgreSQL WAL LSN position
target_timeNoTarget ISO-8601 UTC timestamp to rewind to

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.6

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description must carry the full behavioral burden, and it does add real value: 'isolated' and 'zero-copy CoW' signal that the source data is not mutated, which is the key safety fact for an agent. However, it leaves the tension between the name ('rewind') and the description ('forks a branch') unresolved — whether the original is altered or a new branch is returned — and says nothing about required permissions, what happens with no target argument (0 required params), or whether the two target parameters are mutually exclusive.

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?

A single front-loaded sentence that pairs the latency claim with the core mechanism; nothing is redundant. The '31ms' figure is mildly promotional rather than operational, which keeps it from a 5.

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

Completeness3/5

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

For a four-parameter, all-optional, no-output-schema tool with zero annotation coverage, the description covers mechanism and isolation but omits the default/fallback behavior and the identity of the resulting branch, which an agent needs to chain a follow-up call. Adequate but not complete.

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%, so the schema already documents all four parameters, and the baseline is 3. The description reinforces that target_lsn and target_time accept 'arbitrary historical' values but adds no detail on precedence, mutual exclusivity, or default behavior when neither project_id/sandbox_id nor a target is supplied.

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 verb and resource ('forks an isolated zero-copy CoW PostgreSQL branch') plus the input domain ('arbitrary historical timestamp or LSN'), so an agent knows exactly what the tool produces. It stops short of differentiating itself from likely-adjacent siblings such as mnemon_pitr_restore, mnemon_time_travel, or mnemon_create_branch, which the name overlap makes necessary.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance and no named alternative, despite the sibling list containing several plausible substitutes (pitr_restore, time_travel, create_branch). Usage is only inferable from the phrase 'Point-in-Time Recovery & WAL rewind'.

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