Skip to main content
Glama
Google Ads MCP Server

Google Ads MCP Server

create_ad_group

Create an ad group in a Google Ads campaign with optional CPC bid or target CPA; enabled ad groups and bids return a cost preview requiring confirmation.

Instructions

Create a new ad group in a campaign.

Safety: creating an ENABLED ad group or setting a bid returns a preview
first; call again with confirm=True. A PAUSED ad group with no bid is
created immediately. Refused if cpc_bid is above GOOGLE_ADS_MAX_CPC_BID.

Args:
    customer_id: Google Ads customer ID.
    campaign_id: Campaign ID to create the ad group in.
    name: Ad group name.
    cpc_bid: Max CPC bid in currency (e.g., 2.50 for $2.50).
    target_cpa: Target CPA in currency (overrides campaign-level if set).
    ad_group_type: Ad group type -- 'SEARCH_STANDARD', 'DISPLAY_STANDARD',
        'VIDEO_TRUE_VIEW_IN_STREAM', 'VIDEO_BUMPER', etc.
    status: Initial status -- 'ENABLED' (default) or 'PAUSED'.
    confirm: Must be True to create an ENABLED ad group or one with bids.

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": {
      "customer_id": "<customer_id>",
      "campaign_id": "<campaign_id>",
      "name": "<name>"
    },
    "name": "create_ad_group"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
statusNoENABLED
confirmNo
cpc_bidNo
target_cpaNo
campaign_idYes
customer_idYes
ad_group_typeNoSEARCH_STANDARD

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations, the description discloses the two-phase preview/confirm gate, the exact conditions that bypass it, the default status of ENABLED, and a hard refusal when cpc_bid exceeds GOOGLE_ADS_MAX_CPC_BID. These are exactly the mutation-side effects an agent cannot infer from readOnlyHint=false and destructiveHint=false.

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?

The destructive/safety constraint is front-loaded in its own paragraph, followed by a compact Args list. Every line earns its place given the zero schema coverage, though the Args block is a plain enumeration rather than integrated prose.

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 an eight-parameter creation tool with no output schema, the description covers the confirmation protocol, bid ceilings, and defaults, which is enough to call it safely. It does not state what the successful create response contains (e.g., the new ad group resource name or ID), a minor gap.

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 carries the full burden and does: it documents all eight parameters, including the currency format for cpc_bid, that target_cpa overrides campaign-level settings, the allowed status values, and concrete ad_group_type values that the schema leaves as an unconstrained string. This adds substantial meaning beyond the bare JSON types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a specific verb and resource ('Create a new ad group in a campaign') and ties it to campaign_id, which cleanly separates it from the campaign- and ad-level creation siblings. It does not explicitly name a sibling it is not, but the resource distinction is unambiguous.

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?

The Safety paragraph gives concrete when-to-use guidance: ENABLED ad groups or bids trigger a preview and require a follow-up call with confirm=True, while a PAUSED ad group with no bid goes immediately. It lacks guidance on alternatives such as update_ad_group or set_ad_group_status, but the decision rule for the confirm flow is explicit.

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