AdCopilot

Google Ads: list Google Ads Recommendations

list_recommendations

Read-onlyIdempotent

Lists the account's open Google Ads Recommendations.

Each comes with Google's description of its type, the settings it would
change (current and proposed values), Google's own estimate of its
effect when Google gives one, and how the change is made: a tool of this
server with its arguments filled in, or the Recommendations page in
Google Ads. It reads only; it applies and dismisses nothing. Google can
replace or withdraw a recommendation within the day.

Args:
    customer_id: The Google Ads customer ID (numbers only, no hyphens).
    campaign_id: Only the recommendations for this campaign. Optional.
    types: Only these recommendation types, as Google Ads API names
        (e.g. KEYWORD, CAMPAIGN_BUDGET, SEARCH_PARTNERS_OPT_IN). Optional.
    include_dismissed: Also list recommendations dismissed in Google Ads.
        Default false.
    limit: The most recommendations to return, 1 to 200. Default 50.

Returns:
    Dictionary with recommendations (id, type, google_label, campaign,
    ad_group, changes, google_estimate, action), total, counts_by_type,
    optimization_score and note.

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>"
    },
    "name": "list_recommendations"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No
`types`	No
`campaign_id`	No
`customer_id`	Yes
`include_dismissed`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Beyond the readOnly/idempotent annotations, the description discloses genuinely useful behavior: estimates appear only "when Google gives one," each item carries an executable action payload (a tool name plus arguments) or a deep link to the Google Ads page, and recommendations can be replaced or withdrawn within the day. That staleness caveat materially affects how an agent should consume results.

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-loaded with purpose, then behavior, then Args and Returns. Slightly long: the Returns block restates a field list the output schema already provides, and the read-only guarantee overlaps the readOnlyHint annotation, though the added "applies and dismisses nothing" phrasing is sharper than the hint alone.

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 five-parameter read tool with an output schema and full annotation coverage, the description supplies exactly the missing layer: parameter formats, filterable type vocabulary, result contents, and the freshness caveat. An agent can call this correctly and interpret the response without further lookup.

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 0% schema description coverage, the description carries the full burden and does so: customer_id format (numbers only, no hyphens), types as Google Ads API enum names with three concrete examples, limit bounds (1-200) and default (50), campaign_id scoping, and include_dismissed default false. Nothing in the schema is left ambiguous.

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?

The first line names a specific verb and resource plus a scope qualifier: "Lists the account's open Google Ads Recommendations." It immediately distinguishes this read-only lister from the many mutation siblings (create_*, set_*, update_*) by stating nothing is applied or dismissed.

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?

Usage context is clear: this is the discovery tool for open recommendations, with include_dismissed as the escape hatch for previously dismissed items, and an explicit note that applying or dismissing happens outside this tool. No sibling alternative is named, but none exists on this server that competes with this listing.

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?