gsc_traffic_drop
Compare two date periods to detect pages or queries with significant click drops. Identify traffic losses from algorithm updates, technical issues, or content decay.
Instructions
Compare two date periods and identify pages or queries with significant traffic drops. Useful for diagnosing algorithm updates, technical issues, or content decay.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| site_url | No | Site URL in GSC format, e.g. 'sc-domain:example.com'. Uses config default if omitted. | |
| current_start | Yes | Current period start date (YYYY-MM-DD). | |
| current_end | Yes | Current period end date (YYYY-MM-DD). | |
| previous_start | Yes | Previous period start date (YYYY-MM-DD). | |
| previous_end | Yes | Previous period end date (YYYY-MM-DD). | |
| dimension | No | Group by page or query. Default: 'page'. | |
| min_drop_percent | No | Minimum click drop percentage to flag (e.g. 20 = 20% drop). Default: 20. | |
| min_clicks_previous | No | Minimum clicks in previous period to include (filters out low-traffic noise). Default: 5. | |
| row_limit | No | Max dropped items to show. Default: 25. |
Implementation Reference
- src/types/tool.ts:12-17 (helper)ToolDefinition interface that defines the structure (name, description, schema, handler) used by gscTrafficDrop.
export interface ToolDefinition<T extends AnyZodObject = AnyZodObject> { name: string; description: string; schema: T; handler: (args: z.infer<T>, config: Config) => Promise<ToolResult>; }