mcp-programmatic-tool-ca-when-tasks-require-chaining-multiple-tool-calls-wh-39960676

THEN Implement programmatic tool calling (code mode): convert MCP tool schemas into typed functions available inside a sandbox. The model writes a script that calls tools, and only the final result returns to the model. This avoids passing every intermediate result through the model's context.

// Auto-generated from the Logging MCP server's tool schema
interface LogEntry {
  timestamp: string;
  message: string;
  level: string;
}

function logging_getLogs(input: {
  level: "error" | "warn" | "info";
  since: number;
}): Promise<{ entries: LogEntry[] }> {
  return mcp.callTool<{ entries: LogEntry[] }>("logging_getLogs", input);
}