AdCopilot

Google Ads: add keywords

add_keywords

Destructive

Adds keywords to an ad group.

Keywords are created enabled: in an ad group and campaign that are
already running they can trigger ads to the public at once and spend
from the campaign's budget.

Args:
    customer_id: The Google Ads customer ID (numbers only, no hyphens).
    ad_group_id: The ID of the ad group to add keywords to.
    keywords: List of keyword objects, each with:
        - text: The keyword text (e.g., "buy shoes online").
        - match_type: One of: EXACT, PHRASE, BROAD. Default: BROAD.
        - cpc_bid_micros: Optional CPC bid in micros of the account's currency for this keyword.

Returns:
    Dictionary with created keyword resource names and count.

Tools revision: d80f65c0.

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>",
      "ad_group_id": "<ad_group_id>",
      "keywords": "<keywords>"
    },
    "name": "add_keywords"
  }
}

Input Schema

Name	Required	Description	Default
`keywords`	Yes
`ad_group_id`	Yes
`customer_id`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4/5.0

Behavior4/5

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

The annotations already declare this as a non-idempotent, destructive, open-world mutation. The description adds material behavioral context beyond that: keywords are created enabled and can immediately trigger public ads and spend campaign budget. It does not cover duplicate handling, partial failures, or required permissions, so it falls short of a 5.

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 description is front-loaded with purpose and risk, then structured into Args and Returns. The warning sentence is slightly awkward and the revision trailer is noise, but the substantive content earns its place given the zero schema coverage.

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 destructive mutation tool with an output schema and safety annotations, this is fairly complete: it covers effect, spend risk, parameters, and return summary. It still leaves gaps around permissions, duplicate keyword behavior, and failure modes, which keeps it from being fully complete.

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 description coverage is 0%, so the description must carry the parameter burden, and it does. It explains customer_id formatting, ad_group_id purpose, and the nested keyword fields including text, allowed match types with a BROAD default, and cpc_bid_micros units.

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 description states a specific verb and resource: it adds keywords to an ad group. It is clear enough to distinguish from negative-keyword tools and update_keyword by name, but it does not explicitly name or differentiate against those siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied by the purpose, but there is no explicit when-to-use guidance, no alternatives such as add_negative_keywords or update_keyword, and no stated prerequisites beyond the ad group context. An agent can infer the use case, but must still infer exclusions.

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

All AdCopilot tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?