AI agents call remove_experiment_arm to permanently remove resources in Google Ads — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing an experiment arm is a destructive action that cannot be undone—it permanently deletes a configured experiment variant and its associated data/results from the Google Ads system. While the blast radius is limited to experiment configuration rather than financial transactions, the irreversibility and inability to recover deleted experiment arms justifies the Destructive category over Execute.
From the tool's definition Tool name is 'remove_experiment_arm' with description 'Remove an experiment arm.' The verb 'remove' indicates deletion of an experiment arm resource, which is irreversible within the Google Ads API context.
Documented attack patterns abuse exactly the kind of access remove_experiment_arm gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Google Ads, and nothing reaches the server without passing your rules. This is the rule we recommend for remove_experiment_arm:
{
"version": "1",
"default": "deny",
"hide": [
"remove_experiment_arm"
]
} remove_experiment_arm disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Remove an experiment arm. It is categorised as a Destructive tool in the Google Ads MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Google Ads MCP server in PolicyLayer and add a rule for remove_experiment_arm: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Google Ads. Nothing to install.
remove_experiment_arm is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_experiment_arm rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for remove_experiment_arm. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
remove_experiment_arm is provided by the Google Ads MCP server (promobase/google-ads-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Google Ads, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
59 Google Ads tools catalogued and risk-classified — across an index of 43,000+ MCP servers.