AdCopilot

Google Ads: list audiences

list_audiences

Read-onlyIdempotent

Lists the account's audiences and where its campaigns use them.

Returns the audience lists (open or closed, size range, whether each is
eligible for Search and Display, match rate for customer lists), custom
and combined audiences, and for each enabled or paused campaign its
audience setting (OBSERVATION, TARGETING or NOT_SET) and the audiences
attached at campaign or ad group level, with clicks, conversions and
cost. An ad group audience also carries its ad group's own setting,
which Google allows only when the campaign has none. In-market and
affinity segments are listed only for a name search. It reads only.

Args:
    customer_id: The Google Ads customer ID (numbers only, no hyphens).
    campaign_id: Only this campaign's audiences. Optional; the account's
        lists are returned either way.
    start_date: First day of the clicks and cost (YYYY-MM-DD). Optional;
        with end_date. Default: the last 30 days.
    end_date: Last day of the clicks and cost (YYYY-MM-DD). Optional.
    segments: IN_MARKET or AFFINITY, to search Google's segment
        catalogue by name (with name_contains). Optional.
    name_contains: Text the segment names contain, e.g. "travel"
        (2 to 60 letters, digits, spaces or & , -); at most 50 segments
        come back. Required with segments.

Returns:
    Dictionary with user_lists, custom_audiences, combined_audiences,
    campaigns (audience_mode, level, audiences with metrics and, at ad
    group level, the ad group's audience_mode), segments when searched,
    date_range and notes.

Tools revision: 5c9bea8f.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`end_date`	No
`segments`	No
`start_date`	No
`campaign_id`	No
`customer_id`	Yes
`name_contains`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses real behavioral traits: the 30-day default window, the 50-segment result cap, the 2–60 character and character-set constraint on name_contains, and the conditional rule that ad group audiences carry their own setting only when the campaign has none. It also flags which data is conditional on a name search. This is behavioral context annotations cannot express.

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?

The summary is front-loaded and the Args/Returns structure is easy to scan, with nearly every clause carrying a constraint or default. Minor waste: 'It reads only' restates readOnlyHint, and the Returns block partly duplicates the existing output schema. Length is justified by the six undocumented parameters, but it could trim slightly.

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?

With six parameters at 0% schema coverage, a complex nested return, and an output schema in place, this description supplies exactly what's missing: parameter formats, defaults, preconditions, caps, and conditional-result rules. Nothing an agent needs to call it correctly and interpret the response is absent.

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 the load, and it does for all six parameters: customer_id format ('numbers only, no hyphens'), start/end date format and pairing/default, campaign_id's non-restrictive effect on account lists, and the segments/name_contains pairing including the valid values IN_MARKET/AFFINITY. It adds syntax and constraints the schema does not encode.

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 opening sentence states a specific verb and resource ('Lists the account's audiences') plus scope ('where its campaigns use them'), and the body enumerates exactly which audience types come back. No sibling tool in the list covers audience inventory, and the description makes that boundary unambiguous. An agent can tell what it returns 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?

It gives concrete operating guidance: campaign_id narrows to one campaign but account lists still return, dates default to the last 30 days, and 'In-market and affinity segments are listed only for a name search' establishes a precondition for the segments path. What's missing is an explicit statement of when to reach for this versus alternatives (e.g. search or list_asset_links), so usage is clear but not fully disambiguated.

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?