Skip to main content
Glama

Create database

databaseCreate

Create a managed database for one owned app — Create database on the dashboard’s Database page. A managed database is part of the Pro plan, and of the account’s plan where it includes one, and it keeps running until it is deleted: confirmed: true represents the human’s agreement to create a database for this exact projectId; an earlier deploy or scan is not that agreement. At most one per app, from the number the account’s plan includes across its apps. An app or account that cannot have one yet is refused before a database is created, with a sentence that says why. It returns non-secret status, never a password, key or connection string. Creation is asynchronous. The result reports the recorded creation state; an interrupted provider attempt remains eligible for reconciliation. It cannot run SQL or migrations, and local-only rows are not copied.

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": "databaseCreate"
  }
}

Input Schema

NameRequiredDescriptionDefault
regionNoamericas
confirmedYes
projectIdYes

Output Schema

NameRequiredDescriptionDefault
refYes
exitYes
stateYes
regionYes
schemaYes
archiveYes
enabledYes
messageYes
restoreNo
providerYes
nextStepsYes
inactivityNo
agentPromptYes
lifecycleModeNo
storedArchiveNo
environmentKeysYes
lifecycleFailureYes
requiresDeploymentYes
manualRetentionSinceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations only declare the generic write profile; the description adds what actually matters: creation is asynchronous, the result reports recorded creation state, an interrupted provider attempt stays eligible for reconciliation, and the response never contains a password, key, or connection string. It also discloses persistence and cost implications ('keeps running until it is deleted') and the limits ('cannot run SQL or migrations', local-only rows not copied), all consistent with readOnlyHint=false and idempotentHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, but the second clause ('Create database on the dashboard's Database page') restates the title and adds nothing. Several sentences are dense semicolon-and-dash constructions that take a second pass to parse, so the information is there but the structure costs readability.

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 mutation tool with an output schema present, the description covers what the schema cannot: plan eligibility, the one-per-app cap, async behavior, refusal semantics, and secret-free responses. The remaining gap is the unmentioned `region` parameter and any sense of how long an asynchronous creation takes to settle.

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?

With 0% schema description coverage, the description has to carry parameter meaning itself. It does this well for `confirmed` (human agreement for this exact projectId, not inferred from a prior deploy or scan) and reasonably for `projectId` (must be an owned app), but `region` and its enum/default are never mentioned. Half the parameter surface is therefore still undocumented.

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?

The first clause names a specific verb and resource ('Create a managed database for one owned app') and immediately bounds scope to a single app, which separates it from databaseDelete, databaseRestore, and databaseReconcile. An agent can identify the operation and its subject without consulting the 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?

It gives real preconditions and refusal conditions: Pro plan (or an account plan that includes one), at most one per app, and a refusal with a stated reason when the app or account is not eligible. It also clarifies that `confirmed: true` means the human agreed to this exact projectId and that an earlier deploy or scan does not count. It stops short of naming a sibling alternative, so 4 rather than 5.

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