Explain LinkedIn Anomaly
User asks why their LinkedIn metrics changed, wants to understand a performance drop/spike, or says something like “My LinkedIn leads dropped 40%, why?”
Explains significant metric changes with contributing factors:
LinkedIn-Specific Factors Analyzed:
- CPM changes (auction dynamics, competition)
- CTR changes (creative effectiveness)
- Audience saturation (B2B pools are smaller)
- Seniority targeting shifts
- Industry performance shifts
- Company size targeting changes
- Campaign changes (paused, new, budget)
- B2B seasonal patterns (holidays, fiscal quarters)
- Creative fatigue (14-day threshold)
Returns:
- Metric change summary (current vs previous)
- Severity assessment (CRITICAL, HIGH, MEDIUM, LOW)
- Contributing factors ranked by impact
- Historical context (30/60/90 day averages)
- Similar periods for comparison
- Actionable recommendations
- LinkedIn B2B-specific insights
Parameters:
- metric: Metric to analyze (required). Options: roas, ctr, cpc, cpm, conversions, conversion_rate, leads, engagement_rate, lead_form_completion_rate
- period_start: Start date (YYYY-MM-DD format, required)
- period_end: End date (YYYY-MM-DD format, required)
- comparison_period_start: Optional comparison start date
- comparison_period_end: Optional comparison end date
- ad_account_id: Required for multi-account users. Get from list_connected_accounts
Example Prompts:
- “Why did my LinkedIn ROAS drop last week?”
- “Explain the LinkedIn CTR decline in December”
- “My LinkedIn leads dropped 40%, what happened?”
- “Why did LinkedIn CPC increase?”
Execution time: 4-6 seconds
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 explaining LinkedIn metric anomalies
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.

