Skip to main content
Glama

Keep database

databaseKeep
Idempotent

Keep one app’s managed database from being archived for going unused — Keep this database on the dashboard’s Database page. Where archiving for inactivity is on, Tofu may archive a database that goes unused — never a Free account’s own, which it keeps — and it warns first; Keep counts as use: the inactivity clock starts again and a warning ends. The operation represents the human’s agreement to keep this exact app’s database; inactivity.keepOffered reports whether Keep is offered. It needs a running (ready) database, and the account’s plan must include Keep; a Free account’s own has nothing to keep, and any other account is refused: the human manages the account’s plan in the Tofu dashboard. Archiving a database the account’s plan no longer includes is separate, and Keep does not stop it. It spends nothing, deletes nothing and changes nothing else. It returns a human-readable message; archiveNotBefore is a meaningful date only where message names it.

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>"
    },
    "name": "databaseKeep"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectIdYes

Output Schema

NameRequiredDescriptionDefault
keptAtYes
messageYes
archiveNotBeforeYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations, it discloses concrete effects: the inactivity clock restarts, a pending warning ends, and nothing is spent, deleted, or otherwise changed. It also states the refusal condition and prerequisite states, which the readOnlyHint=false / idempotentHint=true annotations do not convey.

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?

Purpose is front-loaded in the first clause and every sentence carries operational information, but the em-dash-chained phrasing is dense and the 'Keep this database on the dashboard's Database page' clause partially restates the opening.

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?

Covers prerequisites, refusal cases, side effects, and even return semantics (message, archiveNotBefore being meaningful only when named in message) despite an output schema already existing. Nothing an agent needs to decide whether and how to call it appears 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% for the single projectId parameter, so the description must compensate. It implies scope by repeatedly saying 'one app's managed database' and 'this exact app's database', which hints that projectId identifies the app, but it never explicitly maps the parameter or states its format expectations.

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 — keeping one app's managed database from being archived for inactivity — and explicitly contrasts it with the separate archiving-by-plan case, so an agent can distinguish it from databaseArchiveDownload/databaseReconcile without opening 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives conditions for use (inactivity.keepOffered reports whether Keep is offered, database must be ready, plan must include Keep) and conditions where it does not apply (a Free account's own database has nothing to keep; other accounts are refused). It also names the adjacent-but-separate operation (archiving due to plan changes) that Keep does not affect.

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