Skip to main content
Glama

jules_bulk_create_tasks

Create multiple coding tasks simultaneously by providing descriptions and repository details for automated development workflows.

Instructions

Create multiple tasks from a list of descriptions and repositories

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tasksYesArray of task objects to create

Implementation Reference

  • Main handler implementation for jules_bulk_create_tasks. Loops through the array of tasks, calls createTask for each, collects success/failure messages, and returns a summary.
    private async bulkCreateTasks(args: any) {
      const { tasks } = args;
      const results = [];
    
      for (const taskData of tasks) {
        try {
          const result = await this.createTask(taskData);
          results.push(`✓ ${taskData.repository}: ${taskData.description.slice(0, 50)}...`);
        } catch (error) {
          results.push(`✗ ${taskData.repository}: Failed - ${error}`);
        }
      }
    
      return {
        content: [
          {
            type: 'text',
            text: `Bulk Task Creation Results (${tasks.length} tasks):\n\n${results.join('\n')}`
          }
        ]
      };
    }
  • Input schema definition for the tool, specifying an array of task objects each with description, repository (required), and optional branch.
    {
      name: 'jules_bulk_create_tasks',
      description: 'Create multiple tasks from a list of descriptions and repositories',
      inputSchema: {
        type: 'object',
        properties: {
          tasks: {
            type: 'array',
            items: {
              type: 'object',
              properties: {
                description: { type: 'string' },
                repository: { type: 'string' },
                branch: { type: 'string' },
              },
              required: ['description', 'repository'],
            },
            description: 'Array of task objects to create',
          },
        },
        required: ['tasks'],
      },
    },
  • src/index.ts:379-380 (registration)
    Registration in the CallToolRequestSchema handler switch statement that dispatches to the bulkCreateTasks method.
    case 'jules_bulk_create_tasks':
      return await this.bulkCreateTasks(args);
  • Supporting helper function createTask used by bulkCreateTasks to create individual tasks via browser automation on jules.google.com.
    private async createTask(args: any) {
      const { description, repository, branch = 'main' } = args;
      const page = await this.getPage();
    
      try {
        // Navigate to Jules task creation
        await page.goto(`${this.config.baseUrl}/task`);
        await page.waitForLoadState('networkidle');
    
        // Click new task button if needed
        const newTaskButton = page.locator('button.mat-mdc-tooltip-trigger svg');
        if (await newTaskButton.isVisible()) {
          await newTaskButton.click();
        }
    
        // Repository selection
        await page.locator("div.repo-select div.header-container").click();
        await page.locator("div.repo-select input").fill(repository);
        await page.locator("div.repo-select div.opt-list > swebot-option").first().click();
    
        // Branch selection
        await page.locator("div.branch-select div.header-container > div").click();
        
        // Try to find specific branch or select first available
        const branchOptions = page.locator("div.branch-select swebot-option");
        const branchCount = await branchOptions.count();
        if (branchCount > 0) {
          await branchOptions.first().click();
        }
    
        // Task description
        await page.locator("textarea").fill(description);
        await page.keyboard.press('Enter');
    
        // Submit
        await page.locator("div.chat-container button:nth-of-type(2)").click();
    
        // Wait for task creation and get URL
        await page.waitForURL('**/task/**');
        const url = page.url();
        const taskId = this.extractTaskId(url);
    
        // Create task object
        const task: JulesTask = {
          id: taskId,
          title: description.slice(0, 50) + (description.length > 50 ? '...' : ''),
          description,
          repository,
          branch,
          status: 'pending',
          createdAt: new Date().toISOString(),
          updatedAt: new Date().toISOString(),
          url,
          chatHistory: [],
          sourceFiles: []
        };
    
        // Save to data
        const data = await this.loadTaskData();
        data.tasks.push(task);
        await this.saveTaskData(data);
    
        return {
          content: [
            {
              type: 'text',
              text: `Task created successfully!\n\nTask ID: ${taskId}\nRepository: ${repository}\nBranch: ${branch}\nDescription: ${description}\nURL: ${url}\n\nTask is now pending Jules' analysis. You can check progress with jules_get_task.`
            }
          ]
        };
      } catch (error) {
        throw new Error(`Failed to create task: ${error}`);
      }
Behavior2/5

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

With no annotations provided, the description carries full burden but only states the action without disclosing behavioral traits such as permissions needed, rate limits, whether tasks are created synchronously/asynchronously, or error handling for partial failures. It mentions the source data but not the operational impact.

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 that front-loads the key action and resource without any wasted words. It is appropriately sized for the tool's purpose, making it easy to parse quickly.

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 of a bulk creation tool with no annotations and no output schema, the description is incomplete. It lacks details on behavioral aspects, error handling, and what the tool returns, leaving gaps that could hinder an AI agent's ability to use it effectively.

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 'tasks' parameter fully documented in the schema. The description adds minimal value by hinting at the content ('list of descriptions and repositories'), but doesn't provide additional semantics beyond what the schema already specifies, meeting the baseline for high coverage.

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 ('Create multiple tasks') and the resource ('tasks'), specifying they come from 'a list of descriptions and repositories'. It distinguishes from the sibling 'jules_create_task' by indicating bulk creation, though it doesn't explicitly name that sibling for comparison.

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?

No guidance is provided on when to use this tool versus alternatives like 'jules_create_task' for single tasks or other task-related tools. The description implies bulk operations but lacks explicit context, prerequisites, or exclusions for usage.

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