Skip to main content
Glama

Delete database

databaseDelete
DestructiveIdempotent

Delete an owned app’s managed database (Database page: Delete this database). THIS DESTROYS DATA, keeping no copy: the database, everything in it and its Supabase project go permanently. Requires the human’s agreement to this deletion for this exact app; confirmName is its exact name, letter case included. An operator-run export is separate, never a condition of this deletion. Deleting a running database leaves a copy Tofu already holds (the archive it came from, an operator’s export); with none, the data cannot be restored. A database Tofu is setting up, pausing, resuming or archiving is refused until settled (an archive within hours). An archived database IS its stored archive. Deleting it, or one whose archive stopped with a copy recorded (archive_attention or running again), deletes every copy Tofu holds for this app. A refusal changes nothing; an error can leave the data gone, Tofu’s record kept. archive.message and environment.message say what went and what stays.

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>",
      "confirmName": "<confirmName>"
    },
    "name": "databaseDelete"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectIdYes
confirmNameYes

Output Schema

NameRequiredDescriptionDefault
stateNo
archiveNo
deletedAtYes
projectIdYes
environmentYes
providerProjectYes
providerProjectRemovedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, yet the description adds substantial context beyond them: no copy is kept, archive-linked copies are also destroyed, refusals are no-ops while errors can still lose data, and archive.message/environment.message report what was removed. That is exactly the kind of consequence disclosure a destructive tool needs.

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?

The critical warning ('THIS DESTROYS DATA') is front-loaded, and nearly every sentence adds a distinct fact about archives, refusals, or errors. It is dense and clause-heavy with parenthetical asides, which slows reading, but little is genuinely redundant.

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, irreversible operation the description covers prerequisites (human agreement, exact name), blocking states, archive interactions, failure semantics, and where to read outcomes; an output schema exists so return values need not be restated. Nothing an agent needs before calling is missing.

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 0%, so the description must carry the load. It explains confirmName well — the exact database name, case-sensitive — but projectId is never described beyond the UUID format in the schema, leaving half the parameters unelaborated.

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?

Opens with a specific verb and resource — 'Delete an owned app's managed database' — plus the UI location ('Database page: Delete this database'). This clearly separates it from siblings like databaseArchiveDownload, databaseRestore, and databaseKeep without needing their schemas.

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 conditions: requires the human's agreement for this exact app, and is refused while the database is setting up, pausing, resuming or archiving. It also clarifies that an operator export is never a precondition. It does not name an alternative sibling (e.g. archive or restore) for agents who want to preserve data, so it stops short of explicit routing.

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