Analyze Meta Audiences
User asks about Meta/Facebook/Instagram audience performance by demographics, age group or gender targeting optimization, audience saturation, or which demographic segments to target or exclude.
This tool provides deep analysis of audience segment performance and detects audience saturation to optimize demographic targeting for Meta Ads.
Returns:
- Age group performance breakdown (18-24, 25-34, 35-44, 45-54, 55-64, 65+)
- Gender performance breakdown (male, female, unknown)
- Age + Gender combination analysis
- Segments categorized as SCALE/MAINTAIN/REDUCE/EXCLUDE based on ROAS
- Audience saturation score (0-100) with contributing factors
- Best performing segments to scale
- Underperforming segments to reduce/exclude
- Targeting optimization recommendations
- Quick actionable items
When to use this tool:
- “Which age groups perform best for my Meta ads?”
- “Should I target men or women on Facebook?”
- “Is my Meta audience saturated?”
- “Which demographics should I exclude?”
- “Analyze my Instagram audience performance”
- “Best demographic targeting for my Facebook campaigns”
- “Age and gender breakdown for my Meta ads”
- “Are my lookalike audiences exhausted?”
- “Which audience segments are wasting money?”
Parameters:
- lookback_days: 7, 14, 30 (default), 60, or 90 days
- start_date: Optional start date (YYYY-MM-DD). Overrides lookback_days when used with end_date.
- end_date: Optional end date (YYYY-MM-DD). Overrides lookback_days when used with start_date. ⚠️ DATE CLARIFICATION: If the user’s date request is vague or ambiguous (e.g., “March to June” without a year, “last quarter”, “recently”, “a few months ago”), ask the user to specify exact dates before calling this tool. Do not assume or guess dates.
- breakdown_type: ‘age’, ‘gender’, ‘age_gender’, or ‘all’ (default)
- include_saturation: Include saturation analysis (default: True)
- target_roas: Optional override (default: from account goals or 2.0x)
- ad_account_id: Required for multi-account users. Get from list_connected_accounts
Execution time: 2-5 seconds (cached database query with analysis) Data source: meta_audience_daily_metrics table (demographic-level daily metrics)
ROAS Thresholds for Segment Recommendations:
- 🚀 SCALE (ROAS ≥ 1.5x target): Increase budget to this segment
- ➖ MAINTAIN (ROAS 0.75x-1.5x target): Keep current allocation
- ⚠️ REDUCE (ROAS 0.5x-0.75x target): Decrease budget
- 🔴 EXCLUDE (ROAS
<0.5x target): Remove from targeting
Saturation Score Factors (weighted):
- Frequency Score (35%): How often users see ads (>3 indicates fatigue)
- CTR Decline Score (30%): Week-over-week CTR changes
- CPA Increase Score (25%): Rising cost per acquisition
- Reach Saturation Score (10%): Audience reach exhaustion
Saturation Levels:
- ✅ HEALTHY (
<40): Audience is fresh, continue scaling - 🟡 AT_RISK (40-69): Monitor frequency, prepare new audiences
- 🔴 SATURATED (≥70): Expand targeting or refresh creatives
Common Insights:
- Age 25-44 typically has highest ROAS for e-commerce
- Gender targeting varies significantly by product category
- High frequency (>4) combined with declining CTR indicates saturation
- Lookalike audiences can exhaust within 4-8 weeks at high spend
Authorizations
API key from https://adspirer.ai/keys. Prefix sk_live_. Treat as a secret — never commit.
Headers
Client-generated UUID to make writes idempotent. Strongly recommended for write tools. A repeat call with the same key returns the cached result instead of re-executing. Example: 550e8400-e29b-41d4-a716-446655440000
Body
All tool arguments are wrapped in an arguments object. The fields accepted inside arguments are listed below — required fields are marked with a red asterisk.
Input schema for Meta audience performance analysis
Response
Tool executed successfully. data.text carries the human-readable result (markdown-friendly). data.quota shows your current usage against the plan limit. data.structured appears when the tool emits machine-parseable structured content. data.content appears for tools that return non-text blocks (images, resources).
Returned on HTTP 200. data.text is the primary human-readable output. data.quota is always present for billable calls. data.structured is set only when the tool emits machine-parseable structured content. data.content is set only when the tool emits non-text content blocks.

