Skip to main content
Glama

Restore into a new database

restore_database
Idempotent

Creates a NEW database, billed like any other, holding the data as it was at a given minute of the source's restore window (list_database_backups; Valkey: the last snapshot before that minute), with the same users and passwords. The source is not touched and may have been deleted in the last 7 days. Retrying the same call is safe. Scope: vms.create.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "database": "<database>",
      "at": "<at>",
      "name": "<name>"
    },
    "name": "restore_database"
  }
}

Input Schema

NameRequiredDescriptionDefault
atYesISO 8601 timestamp, UTC unless an offset is given, e.g. 2026-10-14T09:30:00Z.
vpcNoDefault: the source's private network.
nameYesName of the new database.
size_gbNoMemory in GB, one of the sizes of get_database_options for the region. Default: 1, or the source's size.
databaseYesThe source database.
idempotency_keyNoYour own unique value per order. By default one is derived from the call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / idempotency_key / description
      Added value: +"Your own unique value per order. By default one is derived from the call."
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: the new database is billed like any other, the source is left untouched, users and passwords are carried over, Valkey sources resolve to the last snapshot before the requested minute, and the required scope is vms.create. The retry-safety sentence reinforces idempotentHint=true rather than contradicting it, and destructiveHint=false is consistent with 'the source is not touched.'

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?

Information-dense and front-loaded with the core action, with short follow-on sentences for source safety, idempotency, and scope. The nested parenthetical about list_database_backups and the Valkey snapshot rule is compact but requires careful reading.

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 six-parameter, non-destructive create tool with full annotation coverage and no output schema, this covers billing, data identity, source safety, retry behavior, and authorization scope. The only real gap is that it never says what the call returns (e.g., the new database's id) or how to look it up afterward.

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, but the description earns more by giving `at` real semantics — minute granularity, restore-window bound, and snapshot resolution rules for Valkey — plus pointing at list_database_backups as the way to discover valid values. It adds no extra meaning for name, size_gb, or idempotency_key beyond the schema.

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?

States a specific verb and resource ('Creates a NEW database') and qualifies it precisely as a point-in-time restore holding data 'as it was at a given minute of the source's restore window.' The capitalization of NEW signals the create-into-new-resource semantics, which separates it from in-place operations, and the mention of list_database_backups anchors the restore-window concept.

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?

Gives concrete usage context: the restore point must fall inside the source's restore window (via list_database_backups), and the source may have been deleted within the last 7 days. It does not explicitly contrast with fork_database or plain create_database, so the agent must infer that this is the choice when historical data is wanted rather than a live copy.

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.