Skip to main content
Glama

Delete app

projectDelete
DestructiveIdempotent

Delete one app this account owns, with its managed database if it has one — Danger zone on the dashboard’s Settings page. This is permanent: its hosting is removed, its address goes offline and its database goes with everything in it (databaseDeleted: true). Requires confirmed: true, representing the human’s agreement to delete this exact projectId and its database — an earlier upload, scan or deploy is not that agreement; without the literal nothing is sent. Keeping the data takes an export or a transfer to the user’s own Supabase organization, which Tofu makes on request before the deletion. It deletes exactly one app per call — there is no bulk form — and a projectId the caller does not own is refused without saying anything about it. A repeat for an app this account already deleted answers with that deletion’s result (alreadyDeleted: true) instead of deleting anything twice. It cannot delete a domain or a hosting account, and 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": "projectDelete"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmedYes
projectIdYes

Output Schema

NameRequiredDescriptionDefault
projectIdYes
alreadyDeletedYes
databaseDeletedNo
providerProjectYes
providerProjectRemovedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Goes well past destructiveHint/idempotentHint: it spells out what is destroyed (hosting, the offline address, the database and everything in it), the `databaseDeleted: true` signal, the refusal-without-disclosure behavior for unowned projectIds, and how repeats return `alreadyDeleted: true` rather than deleting twice. The idempotency and permission behavior are stated concretely and are consistent with the annotations.

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?

Front-loaded with the destructive action and its scope, and every clause carries information an agent needs. It is dense with em-dash asides, though, and the export/transfer clause ('which Tofu makes on request before the deletion') is the one place the phrasing costs more attention than it returns.

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 tool with an output schema present, the definition covers destruction scope, prerequisites, idempotent replay, and authorization failures. Nothing an agent needs in order to call this safely is missing, and return fields are referenced only where they carry behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must carry both params, and it does: `confirmed` is defined as the human's agreement to this exact projectId and its database, with a warning that an earlier upload, scan, or deploy is not that agreement and nothing is sent without the literal. `projectId` gains ownership semantics (unowned ids are silently refused) beyond the uuid format in 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?

Opens with a specific verb and resource plus scope: 'Delete one app this account owns, with its managed database if it has one.' It also fences off adjacent resources ('cannot delete a domain or a hosting account'), so an agent can separate this from domain/hosting siblings without opening a 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?

Gives clear conditions: single app per call with no bulk form, an explicit prerequisite that a human must have agreed to this exact projectId, and a prerequisite step (export or transfer) when the data must be kept. It does not name a specific alternative tool to use for the data-preserving path, so the routing is implied rather than explicit.

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