Skip to main content
Glama

start_workflow

Initiate workflow execution in Conductor by specifying workflow name, version, input parameters, and optional correlation ID for tracking.

Instructions

Start a new workflow execution. Returns the workflow execution ID of the newly started workflow.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
workflowNameYesName of the workflow to start
versionNoVersion of the workflow (optional, defaults to latest)
inputNoInput parameters for the workflow as a JSON object
correlationIdNoOptional correlation ID for tracking
priorityNoWorkflow execution priority (0-99, default: 0)

Implementation Reference

  • The handler function that implements the core logic for the 'start_workflow' tool. It destructures input arguments, validates the workflowName, prepares the request body, sends a POST request to the Conductor /workflow endpoint to start the workflow, and formats a success response with the new workflow ID.
    case "start_workflow": {
      const { workflowName, version, input = {}, correlationId, priority = 0 } = args as any;
    
      // Validate workflow name
      if (!workflowName || workflowName.trim() === "") {
        return {
          content: [
            {
              type: "text",
              text: "āŒ Validation Error: Workflow name is required",
            },
          ],
          isError: true,
        };
      }
    
      const requestBody: any = {
        name: workflowName,
        input,
        priority,
      };
    
      if (version) requestBody.version = version;
      if (correlationId) requestBody.correlationId = correlationId;
    
      const response = await conductorClient.post("/workflow", requestBody);
    
      return {
        content: [
          {
            type: "text",
            text: `āœ… Workflow started successfully!\n\nšŸ†” Workflow ID: ${response.data}\nšŸ“‹ Workflow Name: ${workflowName}\n${version ? `šŸ“Œ Version: ${version}\n` : ""}${correlationId ? `šŸ”— Correlation ID: ${correlationId}\n` : ""}\nšŸ’” Tip: Use get_workflow_status with this ID to monitor progress.`,
          },
        ],
      };
    }
  • The schema definition for the 'start_workflow' tool, including input schema with properties for workflowName (required), version, input, correlationId, and priority. This is part of the tools array returned by list_tools.
    {
      name: "start_workflow",
      description:
        "Start a new workflow execution. Returns the workflow execution ID of the newly started workflow.",
      inputSchema: {
        type: "object",
        properties: {
          workflowName: {
            type: "string",
            description: "Name of the workflow to start",
          },
          version: {
            type: "number",
            description: "Version of the workflow (optional, defaults to latest)",
          },
          input: {
            type: "object",
            description: "Input parameters for the workflow as a JSON object",
          },
          correlationId: {
            type: "string",
            description: "Optional correlation ID for tracking",
          },
          priority: {
            type: "number",
            description: "Workflow execution priority (0-99, default: 0)",
          },
        },
        required: ["workflowName"],
      },
    },
  • src/index.ts:598-602 (registration)
    The request handler for ListToolsRequestSchema that returns the tools array containing the 'start_workflow' tool registration.
    server.setRequestHandler(ListToolsRequestSchema, async () => {
      return {
        tools,
      };
    });
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool starts a workflow and returns an execution ID, but lacks critical details: whether this is a mutating operation (implied but not confirmed), required permissions, rate limits, error conditions, or what happens if the workflow fails to start. For a tool that likely triggers backend processes, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences that front-load the core action and outcome. There's no fluff or redundancy. However, it could be slightly more structured by explicitly stating it's a mutating operation or listing key parameters, though this isn't required for full marks.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (starting workflows with 5 parameters, no output schema, and no annotations), the description is incomplete. It doesn't explain the return value format beyond 'execution ID', error handling, or side effects. For a tool that initiates potentially long-running processes, more context on behavior and outcomes is needed to be fully helpful to an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all parameters are documented in the schema itself. The description adds no additional parameter semantics beyond implying 'workflowName' is required (matching the schema) and mentioning the return value. With high schema coverage, the baseline is 3, as the description doesn't compensate but doesn't detract either.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Start a new workflow execution') and resource ('workflow'), making the purpose immediately understandable. It distinguishes from siblings like 'create_workflow_definition' (which defines workflows) and 'list_workflows' (which lists existing ones). However, it doesn't explicitly contrast with 'restart_workflow' or 'resume_workflow', which are also initiation-related operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing workflow definition), contrast with similar tools like 'restart_workflow' (for failed executions) or 'resume_workflow' (for paused ones), or specify typical use cases. The agent must infer usage from the name and context alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/opensensor/conductor-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server