AdCopilot

Google Ads: pause an auto-apply recommendation type

pause_auto_apply_subscription

DestructiveIdempotent

Pauses one auto-apply recommendation subscription.

Stops Google applying that type of recommendation to the account
unattended. It only pauses: it cannot enable, create or remove a
subscription. Pausing an already-paused subscription changes nothing. A
type the account has no subscription for is reported, not created. Only
the types in list_auto_apply_subscriptions' api_subscribable_types can be
paused here; the ui_only_types can only be changed in the Google Ads UI.

Args:
    customer_id: The Google Ads customer ID (numbers only, no hyphens).
    recommendation_type: The subscription's type, as listed by
        list_auto_apply_subscriptions, e.g. SEARCH_PARTNERS_OPT_IN or
        USE_BROAD_MATCH_KEYWORD.

Returns:
    Dictionary with recommendation_type, previous_status, status,
    changed, message and the subscription's resource_name when one
    exists.

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>",
      "recommendation_type": "<recommendation_type>"
    },
    "name": "pause_auto_apply_subscription"
  }
}

Input Schema

Name	Required	Description	Default
`customer_id`	Yes
`recommendation_type`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=true and openWorldHint=false; the description corroborates the idempotent behavior ('Pausing an already-paused subscription changes nothing') and adds the no-create/no-delete boundary plus the api_subscribable_types vs ui_only_types restriction, which annotations cannot express. It does not discuss permission/auth requirements or rate limits, and does not reconcile the 'destructive' flag with the claim that it 'only pauses', so it stops 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?

Front-loads the action and the hard constraints before the Args section, and every sentence in the prose body adds a rule rather than restating the name. The trailing Returns block is redundant since an output schema exists, which is the only real waste.

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?

For a two-parameter mutation on Google Ads subscriptions, the definition covers scope, idempotency, no-op behavior, allowed value domain, and the UI-only escape hatch — everything an agent needs to call it without trial-and-error. The Returns block is duplicated by the output schema but nothing essential is missing.

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 carries the full burden and does: customer_id is documented as numbers only with no hyphens, and recommendation_type is constrained to values from list_auto_apply_subscriptions with two concrete examples and the api_subscribable_types limitation. This adds meaning well beyond the bare string-typed properties in the schema.

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?

States a specific verb and resource ('Pauses one auto-apply recommendation subscription') and immediately narrows the scope: it toggles one subscription of one recommendation type. That is unambiguously distinct from the sibling list_auto_apply_subscriptions, which is even named as the source of the type value.

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

Usage Guidelines5/5

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

Gives explicit when-not semantics: it cannot enable, create or remove a subscription; pausing an already-paused subscription is a no-op; a type with no subscription is reported rather than created; and ui_only_types must be handled in the Google Ads UI instead. The alternative path (UI vs this tool) is spelled out, so an agent can route correctly without guessing.

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?