Explain Meta Anomaly
User asks why Meta/Facebook/Instagram performance dropped or changed, what happened to their ROAS/CTR/CPM, or wants to understand why a metric changed during a specific period.
This tool analyzes why a specific metric changed during a specified period by comparing it to historical baselines and identifying contributing factors. It detects Meta-specific causes including creative fatigue, audience saturation, placement mix shifts, and auction competition.
Returns:
- Current metric value vs historical averages (30/60/90-day)
- Deviation percentages from baselines
- Contributing factors ranked by estimated impact
- Factor explanations with details
- Similar historical periods with comparable changes
- Assessment of anomaly severity (CRITICAL/WARNING/MINOR/NORMAL)
- Specific recommendations based on detected factors
- Quick actionable items
When to use this tool:
- “Why did my Meta ROAS drop?”
- “What happened to my Facebook CTR this week?”
- “Why is my Instagram CPM so high?”
- “Explain my Meta performance change”
- “My conversions dropped last week - why?”
- “Why did my frequency spike?”
- “What caused my ROAS to decline 40%?”
- “Diagnose my Meta performance problem”
Parameters:
- metric: Required - ‘roas’, ‘ctr’, ‘cpc’, ‘cpm’, ‘conversions’, ‘conversion_rate’, ‘frequency’, or ‘reach’
- period_start: Required - Start date (YYYY-MM-DD format)
- period_end: Required - End date (YYYY-MM-DD format, must be ≤30 days from start)
- ad_account_id: Required for multi-account users. Get from list_connected_accounts
Execution time: 3-8 seconds (statistical analysis across multiple periods) Data source: campaign_daily_metrics + meta_placement_daily_metrics + meta_ad_creative_metrics tables
Contributing Factors Detected:
- CPM Change: Auction competition fluctuations (holidays, competitor activity)
- CTR Change: Creative performance (fatigue, messaging, targeting)
- Conversion Rate Change: Landing page or offer issues
- Frequency Change: Audience saturation (Meta-specific)
- Creative Fatigue: High frequency + declining CTR (Meta-specific)
- Placement Mix Change: Shift in placement distribution (Meta-specific)
- Campaign Changes: Paused/new campaigns affecting overall performance
Severity Levels:
- 🔴 CRITICAL (≥40% deviation): Immediate action required
- 🟡 WARNING (25-40% deviation): Review recommended
- 🟢 MINOR (15-25% deviation): Monitor situation
- ✅ NORMAL (
<15% deviation): Within normal variation
Similar Historical Periods: Finds past periods with comparable deviations to provide context (e.g., “similar drop occurred during Black Friday 2024”)
Best for:
- Diagnosing sudden performance drops
- Understanding seasonal patterns
- Identifying actionable causes vs. external factors
- Prioritizing optimization efforts
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 anomaly explanation 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.

