Skip to main content
Glama

Turn on Google sign-in

appAuthConfigure
Idempotent

Write Tofu’s Google client into one owned app’s own auth service (Sign-in page), where the account’s plan includes sign-in. Requires confirmed: true, representing the human’s agreement to enable sign-in for this exact projectId: an earlier deploy, scan or database create is not that agreement, and without the literal nothing is sent. It answers as appAuthStatus does: its message ends by saying whether Tofu’s broker would start a Google sign-in for the app now. An interrupted write may have been applied with its answer lost; a failure result alone does not establish the app’s current configuration, which appAuthStatus reads live. It never returns the OAuth client secret and changes only the named app. Tofu’s broker needs no per-app Google Cloud step and consoleStep is always null, so neither says whether sign-in works: a person in appUsersList whose methods include google, with a lastSignInAt later than their attempt, has signed in with Google.

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": "appAuthConfigure"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmedYes
projectIdYes

Output Schema

NameRequiredDescriptionDefault
stateYes
enabledYes
messageYes
siteUrlYes
nextStepsYes
providersYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Beyond the annotations it discloses real behavior: the OAuth client secret is never returned, only the named app is changed, consoleStep is always null and does not indicate whether sign-in works, and an interrupted write may have applied with its answer lost, so a failure result does not establish current state. The only gap is that it does not describe what the successful `message` field contains beyond its closing clause, though an output schema exists to carry that.

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 action and its precondition are front-loaded, and every sentence carries operational content, but the prose is very dense — nested clauses like 'an earlier deploy, scan or database create is not that agreement, and without the literal nothing is sent' slow comprehension. The final verification sentence about appUsersList is long and could be split without losing meaning.

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 two-parameter mutation with an output schema and annotations covering safety and idempotency, the description supplies what structured fields cannot: plan gating, the human-agreement precondition, non-reversibility of interrupted writes, and how to independently verify sign-in actually works. Nothing an agent needs in order to call it correctly is missing.

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 carry the parameter burden, and it largely does: it explains `confirmed` as a literal true signalling human agreement to enable sign-in for this exact projectId, and frames projectId as an owned app whose plan includes sign-in. Format and ownership resolution details are left to the schema's uuid pattern.

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 description opens with a concrete verb and resource: writes Tofu's Google client into one owned app's own auth service (Sign-in page). Scope is bounded ('one owned app', 'changes only the named app'), which separates it cleanly from the read-only appAuthStatus and from the email-auth siblings.

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?

It states the precondition for use (the account's plan must include sign-in, and `confirmed: true` must represent a human's agreement for this exact projectId) and explicitly rules out what does not count as that agreement (an earlier deploy, scan or database create). It also routes verification to appAuthStatus rather than re-calling this tool.

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