Google Ads MCP Server

remove_keyword

DestructiveIdempotent

Removes a keyword from a Google Ads ad group, showing a preview first and requiring confirmation before deletion.

Instructions

Remove a keyword from an ad group.

Safety: returns a preview first; call again with confirm=True to remove.

Args:
    customer_id: Google Ads customer ID.
    ad_group_id: Ad group ID containing the keyword.
    criterion_id: Keyword criterion ID to remove.
    confirm_removal: Older name for confirm; either one set to True proceeds.
    confirm: Must be True to proceed (after reviewing the preview).

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>",
      "criterion_id": "<criterion_id>"
    },
    "name": "remove_keyword"
  }
}

Input Schema

Name	Required	Description	Default
`confirm`	No
`ad_group_id`	Yes
`customer_id`	Yes
`criterion_id`	Yes
`confirm_removal`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 11, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true and idempotentHint=true, so the description is not obligated to restate that. It adds real value beyond them by documenting the two-step preview/confirm gate and clarifying that either confirm or the legacy confirm_removal flag satisfies the gate, which an agent could not infer from the schema.

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?

One sentence of purpose, one sentence of safety, then a parameter list — front-loaded with the destructive confirmation flow before the details. No filler, and the Args block is justified rather than redundant given 0% schema coverage.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, open-world mutation with no output schema, the definition tells the agent to "review the preview" but never says what the preview contains or whether removal is permanent/reversible. Parameter and confirmation semantics are covered, but the return behavior an agent must act on is left entirely unspecified.

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 description coverage is 0%, so the Args block carries the full burden and does document all five parameters, including resolving the ambiguous confirm vs confirm_removal overlap. The per-parameter text is terse (e.g. "Google Ads customer ID") and adds little about ID format or lookup, so it compensates for the coverage gap without fully closing it.

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?

"Remove a keyword from an ad group" names a specific verb and a precise resource plus its container, which cleanly separates it from remove_campaign and remove_asset_from_group. It stops short of explicitly naming an alternative tool, so it lands at clear-but-not-differentiating.

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 line gives explicit procedural guidance: call once for a preview, call again with confirm=True to actually remove. That is a clear when/how-to-invoke rule, but there is no guidance on when not to use this versus siblings such as update_keyword_bid for pausing a keyword.

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

Deploy Server