google-ads-mcp

Official

by googleads

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

Labels Manage Label Associations

labels_manage_label_associations

Destructive

Create or remove label associations for Google Ads campaigns, customers, ad groups, and ad group criteria, with a validate-then-confirm workflow to review changes before committing.

Instructions

Manages associations between labels and Campaign, Customer, Ad Group, or Ad Group Criterion.

Supports CREATE and REMOVE operations.

Propose & Confirm Workflow (validate_only and checksum):

Call manage_label_associations with validate_only=True (the default). After validation passes, the tool returns structured change_items and a checksum without committing changes.
Present the change_items to the user and wait for explicit user approval.
Only after user confirmation, call manage_label_associations with validate_only=False along with the exact same parameters and the checksum returned by the previous validate_only=True call.

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>",
      "operation": "<operation>",
      "association_type": "<association_type>"
    },
    "name": "labels_manage_label_associations"
  }
}

Input Schema

Name	Required	Description
`checksum`	No	Checksum of the validated operation returned by a prior `validate_only=True` call. Required when `validate_only=False`.
`label_id`	No	The ID of the Label (e.g., '789'). Required for CREATE.
`operation`	Yes	The operation to perform. Must be 'CREATE' or 'REMOVE'.
`customer_id`	Yes	Google Ads Customer ID (digits or hyphenated, e.g. '1234567890').
`resource_id`	No	The ID of the entity to associate (e.g., '456' for CAMPAIGN or AD_GROUP, or composite '{ad_group_id}~{criterion_id}' such as '456~789' for AD_GROUP_CRITERION). Optional for CUSTOMER (defaults to `customer_id`); required for CREATE on other types.
`validate_only`	No	If True (default), validates the request and returns proposed `change_items` and a `checksum` without mutating the association. If False, requires `checksum` from a prior `validate_only=True` call to commit the mutation.
`association_type`	Yes	The type of resource being associated. Must be 'CAMPAIGN', 'CUSTOMER', 'AD_GROUP', or 'AD_GROUP_CRITERION'.
`login_customer_id`	No	Optional manager customer ID to use as the login-customer-id header.
`association_resource_name`	No	The full resource name of the association itself (e.g., 'customers/123/campaignLabels/456~789'). Optional alternative for REMOVE when `resource_id` and `label_id` are not provided.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.0.6Nov 5, 2026

TDQS

A4.3/5.0

Behavior4/5

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

The annotations already mark this as non-read-only and destructive, and the description adds important behavioral context: validation is the default, changes are returned as structured change_items plus checksum without committing, and the commit requires the same parameters plus the prior checksum. It does not explicitly discuss irreversibility of REMOVE, but the core mutation-safety behavior is well disclosed.

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

Conciseness5/5

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

The definition is front-loaded with the core purpose, then presents the propose-and-confirm workflow as a numbered sequence. It is appropriately sized for a destructive mutation tool and contains no obvious filler.

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?

Given the complex 9-parameter schema, full schema description coverage, existing output schema, and destructive annotations, the description supplies the missing operational context: the two-step validation and confirmation workflow. Nothing essential for correct invocation appears to be omitted.

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 100%, so the input schema already documents the nine parameters in detail. The description reinforces the validate_only and checksum relationship and the requirement to reuse the exact same parameters, but adds little parameter meaning beyond what the schema provides.

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 states a specific verb and resource: manages associations between labels and Campaign, Customer, Ad Group, or Ad Group Criterion. It also names the supported operations CREATE and REMOVE, making the tool distinguishable from label-management siblings such as labels_manage_labels.

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 description gives explicit usage guidance for the validate_only and checksum workflow, including when to validate, when to present changes for approval, and when to commit. It does not name alternative tools or exclusion scenarios, but the usage context for this tool is clear.

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

Deploy Server