AdCopilot

Google Ads: create responsive search ad

create_responsive_search_ad

Destructive

Creates a responsive search ad in an ad group.

Responsive search ads allow you to provide multiple headlines and descriptions,
and Google Ads will automatically test different combinations.

Args:
    customer_id: The Google Ads customer ID (numbers only, no hyphens).
    ad_group_id: The ID of the ad group to add the ad to.
    headlines: List of headline texts (min 3, max 15). Each headline max 30 characters.
    descriptions: List of description texts (min 2, max 4). Each description max 90 characters.
    final_url: The landing page URL for the ad.
    path1: First URL path text (max 15 characters). Optional.
    path2: Second URL path text (max 15 characters). Optional.
    status: Ad status. One of: ENABLED, PAUSED. Default: ENABLED. In a
        campaign that is already running, an ENABLED ad serves, from
        that campaign's budget, as soon as Google approves it; pass
        PAUSED to hold it.

Returns:
    Dictionary with the created ad resource name.

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>",
      "headlines": "<headlines>",
      "descriptions": "<descriptions>",
      "final_url": "<final_url>"
    },
    "name": "create_responsive_search_ad"
  }
}

Input Schema

Name	Required	Default
`path1`	No
`path2`	No
`status`	No	ENABLED
`final_url`	Yes
`headlines`	Yes
`ad_group_id`	Yes
`customer_id`	Yes
`descriptions`	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

Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavior the annotations cannot convey: an ENABLED ad starts serving from the campaign budget immediately after approval, and PAUSED holds it. It does not warn that repeated calls create duplicate ads or mention failure modes (policy review, character-limit rejection), which would be valuable for a non-idempotent write.

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?

Purpose is front-loaded in one sentence, followed by a brief conceptual note and a tightly organized Args/Returns block. Every line maps to a real decision the caller must make; nothing is padding.

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 an 8-parameter mutation tool this is complete: all parameters documented with limits, the ENABLED-vs-PAUSED spend implication explained, and return shape noted (though an output schema exists, making the Returns note harmless redundancy). An agent could call this correctly without opening the schema.

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?

With zero schema description coverage, the description carries the entire burden and does so thoroughly: constraints (headlines min 3 / max 15, 30 chars each; descriptions min 2 / max 4, 90 chars; paths max 15), the customer_id format restriction (numbers only, no hyphens), which fields are optional, and the status enum with its default. This adds meaning well beyond the bare schema.

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 opening sentence gives a specific verb and resource ("Creates a responsive search ad in an ad group"), which is clearly distinct from sibling creation tools like create_text_asset or create_ad_group. It stops short of naming an alternative when an RSA is not the right ad type, so sibling differentiation is inferred rather than stated.

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 context is implied by the RSA explanation and the status note, but there is no explicit guidance on when to choose an RSA over text assets or Performance Max, nor any stated prerequisites such as the ad group existing or account permissions. The status paragraph is the closest thing to a when-to-use rule.

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?