Skip to main content
Glama

jules_get_task

Retrieve detailed information about a specific Google Jules AI coding task using its unique ID or URL to access task specifications and progress status.

Instructions

Get details of a specific Jules task by ID or URL

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskIdYesTask ID or full Jules task URL

Implementation Reference

  • Main handler implementation for 'jules_get_task'. Navigates to the Jules task page in a browser (Playwright), extracts status, chat history, source files using DOM selectors, updates local JSON data persistence, and returns formatted task summary.
    private async getTask(args: any) {
      const { taskId } = args;
      const actualTaskId = this.extractTaskId(taskId);
      const page = await this.getPage();
    
      try {
        // Navigate to task
        const url = taskId.includes('jules.google.com') ? taskId : `${this.config.baseUrl}/task/${actualTaskId}`;
        await page.goto(url);
        await page.waitForLoadState('networkidle');
    
        // Extract task information
        const taskData = await page.evaluate(() => {
          // Extract chat messages
          const chatMessages = Array.from(document.querySelectorAll('div.chat-content')).map(el => ({
            content: el.textContent?.trim() || '',
            timestamp: new Date().toISOString(),
            type: 'system' as const
          }));
    
          // Extract source files
          const sourceFiles = Array.from(document.querySelectorAll('div.source-content a')).map(link => ({
            filename: link.textContent?.trim() || '',
            url: link.getAttribute('href') || '',
            status: 'modified' as const
          }));
    
          // Extract task status
          const statusEl = document.querySelector('.task-status, [data-status], .status');
          const status = statusEl?.textContent?.toLowerCase() || 'unknown';
    
          return {
            chatMessages,
            sourceFiles,
            status
          };
        });
    
        // Update local data
        const data = await this.loadTaskData();
        let task = data.tasks.find(t => t.id === actualTaskId);
        
        if (task) {
          task.chatHistory = taskData.chatMessages;
          task.sourceFiles = taskData.sourceFiles;
          task.updatedAt = new Date().toISOString();
          await this.saveTaskData(data);
        }
    
        return {
          content: [
            {
              type: 'text',
              text: `Task Details (${actualTaskId}):\n\n` +
                    `Status: ${taskData.status}\n` +
                    `URL: ${url}\n` +
                    `Source Files (${taskData.sourceFiles.length}):\n` +
                    taskData.sourceFiles.map(f => `  - ${f.filename}`).join('\n') +
                    `\n\nRecent Chat Messages (${taskData.chatMessages.length}):\n` +
                    taskData.chatMessages.slice(-3).map(m => `  - ${m.content.slice(0, 100)}...`).join('\n')
            }
          ]
        };
      } catch (error) {
        throw new Error(`Failed to get task: ${error}`);
      }
    }
  • Input schema/JSON Schema definition for the jules_get_task tool, specifying required 'taskId' parameter.
      name: 'jules_get_task',
      description: 'Get details of a specific Jules task by ID or URL',
      inputSchema: {
        type: 'object',
        properties: {
          taskId: {
            type: 'string',
            description: 'Task ID or full Jules task URL',
          },
        },
        required: ['taskId'],
      },
    },
  • src/index.ts:367-369 (registration)
    Tool registration/dispatch in MCP CallToolRequestSchema handler switch statement, mapping 'jules_get_task' name to getTask implementation.
    case 'jules_get_task':
      return await this.getTask(args);
    case 'jules_send_message':
  • TypeScript interface defining the JulesTask data structure used in tool responses and local persistence.
    interface JulesTask {
      id: string;
      title: string;
      description: string;
      repository: string;
      branch: string;
      status: 'pending' | 'in_progress' | 'completed' | 'paused';
      createdAt: string;
      updatedAt: string;
      url: string;
      chatHistory: ChatMessage[];
      sourceFiles: SourceFile[];
    }
  • Helper function to extract task ID from full URL or raw ID, used in getTask.
    private extractTaskId(taskIdOrUrl: string): string {
      if (taskIdOrUrl.includes('jules.google.com/task/')) {
        const match = taskIdOrUrl.match(/\/task\/([^/]+)/);
        return match ? match[1] : taskIdOrUrl;
      }
      return taskIdOrUrl;
    }
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool retrieves details but doesn't describe what those details include, whether it's a read-only operation, error handling for invalid IDs, or any performance considerations. This leaves significant gaps in understanding the tool's behavior.

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 directly states the tool's function without any unnecessary words. It is front-loaded with the core action and resource, 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 lack of annotations and output schema, the description is incomplete. It doesn't explain what details are returned, how errors are handled, or any dependencies on other tools. For a tool that likely returns structured task data, this omission reduces its usefulness for an AI 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?

The schema description coverage is 100%, with the parameter 'taskId' fully documented in the schema as 'Task ID or full Jules task URL'. The description adds no additional semantic context beyond what the schema provides, such as examples or format specifics, so it meets the baseline for high schema 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 ('Get details') and resource ('a specific Jules task'), making the purpose immediately understandable. It distinguishes from siblings like 'jules_list_tasks' by focusing on a single task rather than listing multiple. However, it doesn't specify what details are retrieved, which prevents a perfect score.

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 like 'jules_list_tasks' for browsing or 'jules_create_task' for new tasks. It mentions the parameter ('by ID or URL') but doesn't explain scenarios where this tool is preferred over others in the sibling set.

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