Skip to main content
Glama

jules_resume_task

Resume paused Google Jules AI coding tasks by providing the task ID or URL to continue development workflows and automation processes.

Instructions

Resume a paused Jules task

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskIdYesTask ID or URL

Implementation Reference

  • The main handler function for the 'jules_resume_task' tool. It extracts the task ID, navigates to the task page using Playwright, locates and clicks the resume button if visible, and returns an appropriate success or informational message.
    private async resumeTask(args: any) {
      const { taskId } = args;
      const actualTaskId = this.extractTaskId(taskId);
      const page = await this.getPage();
    
      try {
        const url = taskId.includes('jules.google.com') ? taskId : `${this.config.baseUrl}/task/${actualTaskId}`;
        await page.goto(url);
        await page.waitForLoadState('networkidle');
    
        // Look for resume button
        const resumeButton = page.locator("div.resume-button-container svg");
        if (await resumeButton.isVisible()) {
          await resumeButton.click();
          
          return {
            content: [
              {
                type: 'text',
                text: `Task ${actualTaskId} resumed successfully. Jules will continue working on this task.`
              }
            ]
          };
        } else {
          return {
            content: [
              {
                type: 'text',
                text: `Task ${actualTaskId} doesn't appear to be paused or may already be active.`
              }
            ]
          };
        }
      } catch (error) {
        throw new Error(`Failed to resume task: ${error}`);
      }
    }
  • The input schema definition for the 'jules_resume_task' tool, specifying that it requires a 'taskId' string parameter (which can be a task ID or full URL). This is returned by the ListTools MCP request.
    {
      name: 'jules_resume_task',
      description: 'Resume a paused Jules task',
      inputSchema: {
        type: 'object',
        properties: {
          taskId: {
            type: 'string',
            description: 'Task ID or URL',
          },
        },
        required: ['taskId'],
      },
    },
  • src/index.ts:373-374 (registration)
    The registration of the 'jules_resume_task' tool handler within the CallToolRequestSchema switch statement, mapping the tool name to the resumeTask method.
    case 'jules_resume_task':
      return await this.resumeTask(args);
  • Client-side helper function that invokes the 'jules_resume_task' MCP tool, validates prerequisites, handles the response, and updates local task storage.
    def resume_task(manager: Dict[str, Any], task_id: str) -> bool:
        """Resume a paused task via MCP and update local storage."""
    
        validated_id = _validate_task_identifier(task_id)
        mcp_client = manager.get("mcp_client")
        if mcp_client is None:
            raise ValueError("MCP client is missing")
        storage_manager = manager.get("storage")
        if storage_manager is None:
            raise ValueError("Storage manager is missing")
        existing_task = storage.get_task(storage_manager, validated_id)
        normalized_task = models.jules_task_from_dict(existing_task)
        current_status = normalized_task.get("status")
        if current_status != "paused":
            raise ValueError("Task must be paused to resume")
        payload = {"taskId": validated_id}
        LOGGER.info("Resuming task via MCP", extra=payload)
        try:
            response = _invoke_mcp_tool(mcp_client, "jules_resume_task", payload)
        except Exception as error:  # noqa: BLE001
            LOGGER.error("MCP invocation failed", extra={"task_id": validated_id})
            raise RuntimeError("Failed to resume task via MCP") from error
        text_payload = _extract_response_text(response)
        try:
            raw_data = json.loads(text_payload)
        except json.JSONDecodeError as error:
            raise ValueError("Unable to parse resume payload") from error
        if not isinstance(raw_data, dict):
            raise ValueError("Resume payload must be a dictionary")
        success_value = raw_data.get("success")
        if success_value is False:
            return False
        if raw_data.get("error"):
            message_text = str(raw_data.get("error"))
            raise RuntimeError(f"MCP task resume failed: {message_text}")
        if success_value is None:
            raise ValueError("Resume payload missing success indicator")
        if success_value is not True:
            raise ValueError("Unexpected success value in resume payload")
        normalized_task["status"] = "in_progress"
        normalized_task["updated_at"] = datetime.now().astimezone()
        serialized_task = models.jules_task_to_dict(normalized_task)
        storage.save_task(storage_manager, serialized_task)
        return True
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. While 'Resume' implies a state change (from paused to active), the description doesn't specify what happens upon resumption (e.g., does execution continue immediately?), potential side effects, authentication needs, or error conditions. This leaves significant gaps for a mutation tool.

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

Conciseness5/5

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

The description is a single, efficient sentence with zero wasted words. It's front-loaded with the core action and resource, making it easy to parse. Every word earns its place by conveying essential information without redundancy.

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?

For a mutation tool with no annotations and no output schema, the description is incomplete. It lacks details on behavioral outcomes (e.g., what the tool returns, error handling), prerequisites (e.g., task state), and how it fits within the broader task lifecycle. Given the complexity implied by sibling tools, more context is needed.

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?

The schema description coverage is 100%, with the single parameter 'taskId' documented as 'Task ID or URL'. The description adds no additional semantic context beyond what's in the schema (e.g., it doesn't clarify format examples or where to find the ID). With high schema coverage, the baseline score of 3 is appropriate.

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 ('Resume') and the resource ('a paused Jules task'), making the purpose immediately understandable. It doesn't explicitly differentiate from siblings like 'jules_get_task' or 'jules_list_tasks', but the verb 'Resume' implies a specific state transition that distinguishes it from those read-only 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., that the task must be paused), exclusions, or comparisons to siblings like 'jules_create_task' or 'jules_bulk_create_tasks'. 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/mberjans/google-jules-mcp'

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