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: 5c9bea8f.

Input Schema

TableJSON Schema

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

Output Schema

TableJSON 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?

Annotations already give readOnly/idempotent/non-destructive, but the description adds genuinely new behavioral context: it explicitly applies and dismisses nothing, and warns that Google may replace or withdraw a recommendation within the day, which affects caching and re-listing expectations. It does not discuss rate limits or error modes, so a 4 rather than 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-loaded purpose sentence, then param and return detail in labeled blocks; every line is useful. The Returns block partially duplicates the existing output schema, which is the only real slack.

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 read-only listing tool with five parameters and an output schema, the description covers purpose, filtering semantics, volatility of the data source, and non-mutation guarantee. Nothing an agent needs in order to invoke it correctly 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 must carry all five parameters — and it does: customer_id format ('numbers only, no hyphens'), campaign_id scope, types as Google Ads API names with concrete examples (KEYWORD, CAMPAIGN_BUDGET, SEARCH_PARTNERS_OPT_IN), include_dismissed semantics, and limit bounds with default. This is meaning the schema alone does not supply.

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?

Opens with a specific verb and resource: 'Lists the account's open Google Ads Recommendations.' No sibling tool covers recommendations, and the description further specifies what each item contains, so an agent can characterize the payload without opening the schema.

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?

Scope and constraints are clear (open recommendations by default, optional dismissed inclusion, campaign and type filtering), and 'It reads only; it applies and dismisses nothing' sets expectations for what this tool cannot do. It stops short of naming a concrete alternative tool for acting on a recommendation, so not a full 5.

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?