Skip to main content
Glama

Metadata MCP Connector

Create Retargeting Audience

create_retargeting_audience

Create a new retargeting audience on the Metadata platform from native channel audiences.

            This tool creates a retargeting audience by importing an existing audience from a native advertising
            channel (Google Ads, LinkedIn, or Facebook). The audience can be selected from the list of available
            retargeting audiences returned by the get_retargeting_audiences tool.

            **REQUIRED TWO-STEP WORKFLOW:**

            STEP 1: Get available audiences for your channel
            - Call get_retargeting_audiences with your channel (GOOGLE_ADS, LINKEDIN, or FACEBOOK)
            - Review the returned list of available audiences with their details (name, matchCount, etc.)
            - Select the audience you want to import by its ID or by matching its properties

            STEP 2: Create the retargeting audience
            - Use this tool (create_retargeting_audience) with the audience data from Step 1
            - Provide the audience details from the get_retargeting_audiences response
            - The audience will be created and imported into the Metadata platform

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

            WHEN TO USE:
            - "Create a retargeting audience from [audience name] in [channel]"
            - "Import [native channel] audience into Metadata"
            - "Add [audience name] from [channel] as a retargeting audience"
            - "Create a new retargeting audience based on [channel] native audience"

            WORKFLOW EXAMPLE:
            User: "Create a retargeting audience from my Google Ads campaign audience"
            1. Call get_retargeting_audiences(channel="GOOGLE_ADS") to list available audiences
            2. Select the desired audience from the results
            3. Call create_retargeting_audience with the audience object from the results

            PARAMETERS:
            - audience_data: Complete audience object from get_retargeting_audiences response (required)
              Should include: id, name, type, subtype, channel, matchCount, externalAccountId
              Note: This is typically the entire audience object returned by get_retargeting_audiences

            AUDIENCE DATA STRUCTURE:
            The audience_data parameter should be a dictionary containing:
            - id: Unique audience ID (required)
            - name: Audience name (required)
            - type: Audience type (e.g., GoogleAdsAudience, LinkedInAudience, FacebookAudience) (required)
            - subtype: Audience subtype (e.g., GOOGLE_ADS_RETARGETING, LINKEDIN_RETARGETING) (required)
            - channel: Channel type identifier (required)
            - matchCount: Number of matches/members in the audience
            - externalAccountId: Associated account ID on the advertising platform (required)
            - mdId: Metadata ID (optional, typically null for new imports)
            - externalName: External name (optional)
            - externalSubType: External subtype (optional)
            - seedSourcePlatform: Source platform for the audience seed (optional)

            RETURNS:
            Success confirmation with details about the created retargeting audience including:
            - Audience ID
            - Audience name
            - Type and subtype
            - Channel
            - Match count
            - Creation status

            COMMON USE CASES:
            - Create retargeting audiences from Google Ads native audiences
            - Import LinkedIn retargeting audiences into Metadata
            - Setup Facebook retargeting audiences for multi-channel campaigns
            - Consolidate native channel audiences into Metadata platform

            IMPORTANT NOTES:
            - Audience must be selected from get_retargeting_audiences results
            - The audience object must contain all required fields
            - Channel must be GOOGLE_ADS, LINKEDIN, or FACEBOOK
            - Audience creation is immediate and the audience becomes available for targeting
            - Once created, the audience can be used in campaigns across channels

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
audience_dataYesComplete audience object from get_retargeting_audiences response. Should contain: id, name, type, subtype, channel, matchCount, externalAccountId, and other relevant fields.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true. The description adds behavioral context beyond these: creation is immediate, the audience becomes available for targeting, and it can be used in campaigns across channels. It also discloses the return confirmation details. This enriches the agent's understanding of side effects and lifecycle without contradicting the 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 well-structured with clear headers and front-loaded purpose, but it is very verbose. Multiple sections repeat similar information: 'WHEN TO USE' and 'COMMON USE CASES' overlap, and the 'WORKFLOW EXAMPLE' partially reiterates the two-step workflow. Not every sentence earns its place, making it less concise than it could be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with one nested parameter and no output schema, the description provides a full workflow, parameter structure, return details, and important notes. It explains how to obtain the input object and what fields are required. Minor gap: matchCountType appears in the schema but is not listed in the description's AUDIENCE DATA STRUCTURE, though the schema already covers it. Overall it is complete enough for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 100%, the description adds significant meaning: it specifies that audience_data should be the complete object from get_retargeting_audiences, lists the required fields and optional fields, and notes it is 'typically the entire audience object returned'. This goes beyond the schema's per-field descriptions by conveying the source and packaging of the value, which is crucial for correct 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 states exactly what the tool does: 'Create a new retargeting audience on the Metadata platform from native channel audiences' and explains it imports an existing audience from Google Ads, LinkedIn, or Facebook. It distinguishes this import-based tool from siblings like create_linkedin_engagement_retargeting_audience or create_facebook_native_criteria_audience by making the 'import existing native audience' angle explicit, so an agent can tell them apart without opening schemas.

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 a detailed two-step workflow, a 'WHEN TO USE' section with natural-language triggers, and a concrete workflow example. It explicitly names get_retargeting_audiences as the required prerequisite. However, it does not explicitly state when NOT to use this tool or contrast it with alternative audience-creation tools (e.g., create_linkedin_engagement_retargeting_audience), so it misses clear exclusion guidance for a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources