Skip to main content
Glama

Request database restore

databaseRestoreRequest
Destructive

Ask a person at Tofu by email to put one owned app’s running managed database back to one of its daily backups — Ask for a restore on the Database page. A restore puts the WHOLE database back to that moment, losing everything saved since — new rows, changes, anyone who signed up — and the app cannot reach its database while it runs. Requires confirmed: true, representing the human’s agreement to this exact projectId and backup with that data loss and downtime; without the literal nothing is sent. The human gets a confirmation email (replying to it cancels); nothing in the database changes until the person at Tofu restores it and emails the human. The backup is backupId or date (UTC: that day’s newest complete backup); note goes to that person. The answer is a report with a human-readable message; outcome is requested, refused (nothing was sent) or not_sent (nobody got it, so nothing will happen; asking again later is safe). It returns no credential.

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": {
      "projectId": "<projectId>",
      "confirmed": "<confirmed>"
    },
    "name": "databaseRestoreRequest"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNo
noteNo
backupIdNo
confirmedYes
projectIdYes

Output Schema

NameRequiredDescriptionDefault
atYes
codeYes
backupYes
messageYes
outcomeYes
receiptYes
projectIdYes
requestIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior3/5

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

The annotations already flag destructiveHint=true and openWorldHint=true, and the description goes beyond them with concrete stakes: the whole database resets to that moment, all rows and changes and signups since are lost, and the app cannot reach its database while the restore runs. It also discloses the outcome vocabulary and the confirmation flow. It does not state how long the restore takes or whether the request can be withdrawn after it is sent.

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?

One dense paragraph that front-loads the action, then the data-loss and downtime risk, then the confirmed guardrail, then the return shape. Nothing is redundant, though the single-paragraph layout makes the high-stakes warning compete with mechanical detail an agent may skim.

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

Completeness5/5

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

For a destructive, human-in-the-loop request tool this covers what matters: irreversible data loss, downtime, the confirmed gate, the email round trip, and the outcome values (requested, refused, not_sent) with the note that nobody receiving it means retrying later is safe. The output schema exists, so leaving return-field detail to it is appropriate.

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 0%, so the description must supply meaning and it largely does: backupId versus date (UTC, taking that day's newest complete backup), note passing through to the Tofu contact, and confirmed needing to be the literal true or nothing is sent. projectId is only gestured at as 'this exact projectId' and is never explained, and the input format of the other fields is left to the schema's patterns.

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: 'Ask a person at Tofu by email to put one owned app's running managed database back to one of its daily backups.' That phrasing separates the human-mediated request path from the direct sibling databaseRestore, so an agent can choose without opening either schema.

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?

Conveys the context clearly: it is an email request routed to a person, with a confirmation email that can be replied to in order to cancel, and no change until that person acts. It never explicitly contrasts with the sibling databaseRestore or states when the direct path is preferable, so the when-not guidance is only implied.

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.

Resources