Metadata MCP Connector

Get Retargeting Audiences

get_retargeting_audiences

Read-only

Get all available retargeting audiences for a specific advertising channel.

            This tool retrieves all retargeting audiences and native audiences available for the specified
            advertising channel (GOOGLE_ADS, LINKEDIN, or FACEBOOK) that can be used to create new retargeting
            audiences. This is useful when you need to discover existing audiences before creating or targeting them.

            SUPPORTED CHANNELS:
            - GOOGLE_ADS: Google Ads retargeting audiences
            - LINKEDIN: LinkedIn retargeting audiences
            - FACEBOOK: Facebook retargeting audiences

            WHEN TO USE:
            - Discover all available retargeting audiences for a specific channel
            - View native audiences that can be used for targeting on a channel
            - Find audience IDs and details for audience creation or targeting
            - Review audience names, sizes (matchCount), and other metadata
            - Understand what audiences are available before building campaigns
            - Compare audiences across different advertising channels

            PARAMETERS:
            - channel: The advertising channel to fetch retargeting audiences for (required)
              Options: GOOGLE_ADS, LINKEDIN, FACEBOOK
              Note: Channel names are case-insensitive and will be converted to uppercase

            RETURNS:
            List of available retargeting and native audiences with details including:
            - id: Unique audience ID
            - name: Audience name
            - type: Audience type (e.g., GoogleAdsAudience, LinkedInAudience, FacebookAudience)
            - subtype: Audience subtype (e.g., GOOGLE_ADS_RETARGETING, LINKEDIN_RETARGETING)
            - channel: Channel type identifier
            - matchCount: Number of matches/members in the audience
            - externalAccountId: Associated account ID on the advertising platform
            - seedSourcePlatform: Source platform for the audience seed

            AUDIENCE DETAILS:
            Each audience record provides comprehensive information about:
            - Audience identification and naming
            - Type and subtype classification
            - Match count to understand audience size
            - External platform integration details
            - Account associations

            COMMON USE CASES:
            - Get all LinkedIn retargeting audiences (including Marketing Automation, Bulk, Retargeting, and Business Objective Based Audience)
            - Find Google Ads audiences suitable for retargeting campaigns
            - Identify Facebook retargeting audiences

Input Schema

TableJSON Schema

Name	Required	Description	Default
`channel`	Yes	The advertising channel to fetch retargeting audiences for

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 16, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description doesn't need to restate that. It adds valuable behavioral context by detailing the return fields (id, name, type, subtype, channel, matchCount, etc.) and clarifying that it retrieves both retargeting and native audiences. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very verbose, with multiple sections (SUPPORTED CHANNELS, WHEN TO USE, PARAMETERS, RETURNS, AUDIENCE DETAILS, COMMON USE CASES). Some redundancy exists: 'AUDIENCE DETAILS' largely restates the RETURNS list, and 'COMMON USE CASES' overlaps with 'WHEN TO USE'. While well-structured, it could be trimmed significantly without losing information.

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?

Given that there is no output schema, the description fully compensates by detailing the exact return fields and their meanings. It covers every aspect an agent needs: how to call (channel parameter), what it returns, and common use cases. No missing information that would hinder correct usage.

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?

The single 'channel' parameter is fully described in the schema (enum + description), but the tool description adds critical extra semantics: it explains that channel names are case-insensitive and will be converted to uppercase. This goes beyond the schema and provides practical guidance for invocation.

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 description clearly states the action: 'Get all available retargeting audiences for a specific advertising channel.' It specifies the resource (retargeting audiences) and the scope (per channel), distinguishing it from creation tools like create_retargeting_audience or other retrieval tools like get_audience_details.

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?

Provides an explicit 'WHEN TO USE' section listing concrete scenarios (discover audiences, view native audiences, find IDs, etc.), which gives strong contextual guidance. However, it does not explicitly mention when not to use it or name alternatives, though the use cases imply this is for read-only discovery.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Metadata MCP Connector 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?