Skip to main content
Glama
Google Workspace MCP connector

Google Workspace MCP connector

by animesh-ex

google_setup

Set up and check your Google connection: import OAuth credentials, sign in or out, view configuration status, and save Google Ads tokens so Workspace tools can access your account.

Instructions

Set up or check the Google connection. Actions: 'status' (what's configured), 'import_credentials' (copy a downloaded Desktop-app OAuth client JSON into place; omit path to use the newest client_secret_*.json in Downloads), 'sign_in' (opens the browser for Google consent and waits up to 5 minutes), 'sign_out' (deletes the saved token), 'configure_ads' (save a Google Ads developer token and optional manager account ID).

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": {
      "action": "<action>"
    },
    "name": "google_setup"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
developerTokenNoFor configure_ads: Google Ads API developer token
credentialsPathNoFor import_credentials: path to the downloaded client_secret_*.json
loginCustomerIdNoFor configure_ads: manager (MCC) account ID, if accounts are accessed through one

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false and openWorldHint=true, and the description adds real behavioral context beyond that: sign_in opens a browser and blocks up to 5 minutes, sign_out deletes the saved token (a destructive side effect on stored state), and import_credentials writes a JSON file into place. The remaining gap is that it never says what happens on failure, timeout, or when no credentials exist yet.

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 the per-action details follow in a compact, quoted, self-contained list with no filler sentences. The single dense sentence is slightly harder to scan than a bulleted list would be, but no wording is wasted.

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 four-parameter tool with no output schema, the description covers all modes and the one non-obvious default, which is close to what an agent needs. It stops short of describing prerequisite state (whether a valid token already exists, what 'status' reports, what happens after a 5-minute consent timeout).

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 coverage is 75%, so the baseline sits at 3, and the description's added value is mostly the credentialsPath default behavior (fall back to the newest client_secret_*.json in Downloads), which is not in the schema. It restates configure_ads' purpose but adds no format hints for developerToken or loginCustomerId beyond what the schema already documents.

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 specific verb and resource ('Set up or check the Google connection') and then enumerates all five modes with quoted action names, so an agent can map 'status', 'import_credentials', 'sign_in', 'sign_out' and 'configure_ads' to concrete outcomes without opening the schema. Nothing about sibling tools (drive_/docs_/ads_) overlaps, so the tool is clearly distinguished.

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?

Each action carries an inline condition for when it applies ('omit path to use the newest client_secret_*.json in Downloads', 'configure_ads' saves a developer token and optional MCC ID), which is genuine when-to-use guidance. What is absent is ordering or exclusion guidance — e.g., that credentials must be imported before sign_in, or which action to pick when the connection state is unknown.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.