get_schema
Retrieve schema and structure information for span recordings to understand available fields, view example payloads, and identify filtering options before querying spans.
Instructions
Get schema and structure information for span recordings on Tusk Drift.
Use this tool to:
Understand what fields are available for a specific instrumentation type
See example payloads for HTTP requests, database queries, etc.
Learn what to filter on before querying spans
Common package names:
http: Incoming HTTP requests (has statusCode, method, url, headers)
fetch: Outgoing HTTP calls
pg: PostgreSQL queries (has db.statement, db.name)
grpc: gRPC calls
express: Express.js middleware spans
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| observableServiceId | No | Service ID to query (required if multiple services available) | |
| packageName | No | Package name (e.g., 'http', 'pg', 'fetch') | |
| instrumentationName | No | Instrumentation name | |
| name | No | Span name to filter by | |
| showExample | No | Include an example span | |
| maxPayloadLength | No | Truncate example payload strings |
Implementation Reference
- src/tools/getSchema.ts:53-94 (handler)The core handler function for the 'get_schema' tool. It validates the input using Zod schema, calls the API client's getSchema method, and formats the result into markdown sections for display.export async function handleGetSchema( client: TuskDriftApiClient, args: Record<string, unknown> ): Promise<{ content: Array<{ type: "text"; text: string }> }> { const input = getSchemaInputSchema.parse(args) as GetSchemaInput; const result = await client.getSchema(input); const sections: string[] = []; if (result.description) { sections.push(`## Description\n${result.description}`); } if (result.commonJsonbFields) { sections.push(`## Common Queryable Fields **inputValue fields:** ${result.commonJsonbFields.inputValue.join(", ") || "(none)"} **outputValue fields:** ${result.commonJsonbFields.outputValue.join(", ") || "(none)"}`); } if (result.inputSchema) { sections.push(`## Input Schema\n\`\`\`json\n${JSON.stringify(result.inputSchema, null, 2)}\n\`\`\``); } if (result.outputSchema) { sections.push(`## Output Schema\n\`\`\`json\n${JSON.stringify(result.outputSchema, null, 2)}\n\`\`\``); } if (result.exampleSpanRecording) { sections.push(`## Example Span\n\`\`\`json\n${JSON.stringify(result.exampleSpanRecording, null, 2)}\n\`\`\``); } return { content: [ { type: "text", text: sections.join("\n\n") || "No schema information available.", }, ], }; }
- src/tools/getSchema.ts:5-51 (registration)Tool registration object defining the 'get_schema' tool, including its name, description, and JSON input schema for MCP.export const getSchemaTool: Tool = { name: "get_schema", description: `Get schema and structure information for span recordings on Tusk Drift. Use this tool to: - Understand what fields are available for a specific instrumentation type - See example payloads for HTTP requests, database queries, etc. - Learn what to filter on before querying spans Common package names: - http: Incoming HTTP requests (has statusCode, method, url, headers) - fetch: Outgoing HTTP calls - pg: PostgreSQL queries (has db.statement, db.name) - grpc: gRPC calls - express: Express.js middleware spans`, inputSchema: { type: "object", properties: { observableServiceId: { type: "string", description: "Service ID to query. Required if multiple services are available.", }, packageName: { type: "string", description: "Package name to get schema for (e.g., 'http', 'pg', 'fetch')", }, instrumentationName: { type: "string", description: "Specific instrumentation name", }, name: { type: "string", description: "Span name to get schema for (e.g., '/api/users')", }, showExample: { type: "boolean", description: "Include an example span with real data", default: true, }, maxPayloadLength: { type: "number", description: "Truncate example payload strings to this length", default: 500, }, }, }, };
- src/types.ts:186-193 (schema)Zod schema for validating inputs to the 'get_schema' tool, used in the handler for parsing arguments.export const getSchemaInputSchema = z.object({ observableServiceId: z.string().optional().describe("Service ID to query (required if multiple services available)"), packageName: z.string().optional().describe("Package name (e.g., 'http', 'pg', 'fetch')"), instrumentationName: z.string().optional().describe("Instrumentation name"), name: z.string().optional().describe("Span name to filter by"), showExample: z.boolean().default(true).describe("Include an example span"), maxPayloadLength: z.number().min(0).default(500).describe("Truncate example payload strings"), });
- src/tools/index.ts:10-17 (registration)Registration of all tools including 'get_schema' (via getSchemaTool) in the tools array exported for use in the main MCP server.export const tools: Tool[] = [ querySpansTool, getSchemaTool, listDistinctValuesTool, aggregateSpansTool, getTraceTool, getSpansByIdsTool, ];
- src/tools/index.ts:24-31 (registration)Mapping of tool names to their handler functions, including 'get_schema' to handleGetSchema, used by the MCP server.export const toolHandlers: Record<string, ToolHandler> = { query_spans: handleQuerySpans, get_schema: handleGetSchema, list_distinct_values: handleListDistinctValues, aggregate_spans: handleAggregateSpans, get_trace: handleGetTrace, get_spans_by_ids: handleGetSpansByIds, };