> ## Documentation Index > Fetch the complete documentation index at: https://docs.testworld.dev/llms.txt > Use this file to discover all available pages before exploring further. # Get a run > While the run is open, trace and evaluation are null. Reading also ends a run that is due. ## OpenAPI ````yaml /openapi.json get /v1/runs/{id} openapi: 3.1.0 info: title: testworld API version: 1.0.0 description: >- Start a run on a simulated workplace, point your agent at its tools, and read back the trace and the evaluation. The hosted API opens with early access. x-fingerprint: d223e1b42e3f0279 servers: - url: https://api.testworld.dev description: Hosted, opens with early access security: - bearer: [] paths: /v1/runs/{id}: get: tags: - Runs summary: Get a run description: >- While the run is open, trace and evaluation are null. Reading also ends a run that is due. operationId: getRun parameters: - name: id in: path required: true schema: type: string description: The run id. responses: '200': description: The run, without its token. content: application/json: schema: $ref: '#/components/schemas/Run' '401': description: No key, or a wrong one. content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: No such run. content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: Run: type: object description: One agent doing one task in one environment. properties: id: type: string description: Opaque id, starts with run_. status: type: string enum: - created - running - evaluating - done - failed ended_by: type: - string - 'null' enum: - finish - idle_timeout - timeout - max_calls - null error: type: - object - 'null' properties: type: type: string message: type: string environment: type: object properties: id: type: string slug: type: string version: type: object properties: id: type: string number: type: integer task: type: object properties: id: type: - string - 'null' text: type: string agent: type: object properties: name: type: - string - 'null' revision: type: - string - 'null' tools_url: type: string description: The agent's base address for the tools. mcp_url: type: string description: One MCP address for the Gmail and Slack tools. tools: type: array items: $ref: '#/components/schemas/ToolAddress' token: type: string description: >- The run's credential for the tools, tw_run_... Only in the answers of POST /v1/runs and GET /v1/runs/{id}/tools. now: type: string format: date-time description: Simulated time after the last call. calls: type: integer max_calls: type: integer idle_timeout_seconds: type: integer timeout_seconds: type: integer created_at: type: string format: date-time started_at: type: - string - 'null' format: date-time expires_at: type: string format: date-time finished_at: type: - string - 'null' format: date-time scored_at: type: - string - 'null' format: date-time metadata: type: object trace: oneOf: - $ref: '#/components/schemas/Trace' - type: 'null' evaluation: oneOf: - $ref: '#/components/schemas/Evaluation' - type: 'null' Error: type: object required: - error properties: error: type: object required: - type - message properties: type: type: string enum: - invalid_request - unauthorized - not_found - run_ended - idempotency_conflict - rate_limited description: Stable. Use it in code. message: type: string description: For people. It can change. ToolAddress: type: object properties: provider: type: string enum: - google.gmail - slack - google.calendar surface: type: string enum: - rest - web-api - mcp url: type: string description: Absolute address. Trace: type: object description: >- Every call the tools answered during the run, reads included. Nothing from inside the agent. properties: calls: type: array items: $ref: '#/components/schemas/TraceCall' Evaluation: type: object description: The end state and the output compared with the run's checks. properties: score: type: - number - 'null' minimum: 0 maximum: 1 description: Passed checks over all checks. null when the run had no checks. passed: type: - boolean - 'null' description: true only when every check passed. checks: type: array items: $ref: '#/components/schemas/CheckResult' state_diff: type: object description: 'Per collection: created, updated and removed ids.' evaluated_at: type: string format: date-time TraceCall: type: object properties: seq: type: integer minimum: 1 at: type: string format: date-time description: Simulated time. provider: type: string surface: type: string operation: type: string description: >- For example gmail.messages.list or slack.chat.postMessage. On MCP it is the tool's name. arguments: type: object description: >- Path, query and body merged for REST and Web API calls. The tool arguments for MCP. result: description: The body the tool answered. status: type: string enum: - ok - error error: type: - object - 'null' properties: type: type: string message: type: string mutated: type: boolean description: Whether the call changed the environment. state_digest: type: string reactions: type: array items: type: object properties: id: type: string user: type: string ts: type: string text: type: string CheckResult: type: object properties: id: type: string kind: type: string description: type: string source: type: string enum: - template - custom passed: type: - boolean - 'null' description: null when undecided, which counts as not passed. explanation: type: string description: One line on what was found. judge: type: - object - 'null' properties: model: type: string securitySchemes: bearer: type: http scheme: bearer description: Your API key. Tool calls under tools_url use the run token instead. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.