Skip to main content
Glama

jules_screenshot

Capture screenshots of Jules AI coding assistant pages for debugging and verification purposes during development workflows.

Instructions

Take a screenshot of current Jules page for debugging and verification

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filenameNoOptional filename for screenshot
taskIdNoOptional task ID to navigate to first

Implementation Reference

  • The handler function that implements the jules_screenshot tool. It optionally navigates to a task page, takes a full-page screenshot using Playwright, saves it to a file, and returns the file path.
    private async takeScreenshot(args: any) {
      const { taskId, filename } = args;
      const page = await this.getPage();
    
      try {
        if (taskId) {
          const actualTaskId = this.extractTaskId(taskId);
          const url = taskId.includes('jules.google.com') ? taskId : `${this.config.baseUrl}/task/${actualTaskId}`;
          await page.goto(url);
          await page.waitForLoadState('networkidle');
        }
    
        const screenshotPath = filename || `jules-screenshot-${Date.now()}.png`;
        await page.screenshot({ path: screenshotPath, fullPage: true });
    
        return {
          content: [
            {
              type: 'text',
              text: `Screenshot saved to: ${screenshotPath}`
            }
          ]
        };
      } catch (error) {
        throw new Error(`Failed to take screenshot: ${error}`);
      }
    }
  • The input schema definition for the jules_screenshot tool, registered in the listTools handler.
      name: 'jules_screenshot',
      description: 'Take a screenshot of current Jules page for debugging and verification',
      inputSchema: {
        type: 'object',
        properties: {
          taskId: {
            type: 'string',
            description: 'Optional task ID to navigate to first',
          },
          filename: {
            type: 'string',
            description: 'Optional filename for screenshot',
          },
        },
      },
    },
  • src/index.ts:382-382 (registration)
    The dispatch case in the CallToolRequestSchema handler that routes calls to the takeScreenshot method.
    return await this.takeScreenshot(args);
  • Helper method used by takeScreenshot to extract task ID from URL if provided.
    private extractTaskId(taskIdOrUrl: string): string {
      if (taskIdOrUrl.includes('jules.google.com/task/')) {
        const match = taskIdOrUrl.match(/\/task\/([^/]+)/);
        return match ? match[1] : taskIdOrUrl;
      }
      return taskIdOrUrl;
    }
  • src/index.ts:118-358 (registration)
    The ListToolsRequestSchema handler that registers and advertises the jules_screenshot tool schema.
    this.server.setRequestHandler(ListToolsRequestSchema, async () => {
      return {
        tools: [
          // === CORE TASK MANAGEMENT ===
          {
            name: 'jules_create_task',
            description: 'Create a new task in Google Jules with repository and description',
            inputSchema: {
              type: 'object',
              properties: {
                description: {
                  type: 'string',
                  description: 'Task description - what you want Jules to do',
                },
                repository: {
                  type: 'string',
                  description: 'GitHub repository in format owner/repo-name',
                },
                branch: {
                  type: 'string',
                  description: 'Git branch to work on (optional, defaults to main)',
                },
              },
              required: ['description', 'repository'],
            },
          },
          {
            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'],
            },
          },
          {
            name: 'jules_list_tasks',
            description: 'List all Jules tasks with their status',
            inputSchema: {
              type: 'object',
              properties: {
                status: {
                  type: 'string',
                  enum: ['all', 'active', 'pending', 'completed', 'paused'],
                  description: 'Filter tasks by status',
                },
                limit: {
                  type: 'number',
                  description: 'Maximum number of tasks to return (default 10)',
                },
              },
            },
          },
          {
            name: 'jules_send_message',
            description: 'Send a message/instruction to Jules in an active task',
            inputSchema: {
              type: 'object',
              properties: {
                taskId: {
                  type: 'string',
                  description: 'Task ID or URL',
                },
                message: {
                  type: 'string',
                  description: 'Message to send to Jules',
                },
              },
              required: ['taskId', 'message'],
            },
          },
          {
            name: 'jules_approve_plan',
            description: 'Approve Jules execution plan for a task',
            inputSchema: {
              type: 'object',
              properties: {
                taskId: {
                  type: 'string',
                  description: 'Task ID or URL',
                },
              },
              required: ['taskId'],
            },
          },
          {
            name: 'jules_resume_task',
            description: 'Resume a paused Jules task',
            inputSchema: {
              type: 'object',
              properties: {
                taskId: {
                  type: 'string',
                  description: 'Task ID or URL',
                },
              },
              required: ['taskId'],
            },
          },
          // === ADVANCED TASK OPERATIONS ===
          {
            name: 'jules_analyze_code',
            description: 'Analyze code changes and diff in a Jules task',
            inputSchema: {
              type: 'object',
              properties: {
                taskId: {
                  type: 'string',
                  description: 'Task ID or URL',
                },
                includeSourceCode: {
                  type: 'boolean',
                  description: 'Whether to include full source code content',
                },
              },
              required: ['taskId'],
            },
          },
          {
            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'],
            },
          },
          // === SESSION & AUTHENTICATION MANAGEMENT ===
          {
            name: 'jules_session_info',
            description: 'Get current session configuration and authentication status',
            inputSchema: {
              type: 'object',
              properties: {},
            },
          },
          {
            name: 'jules_setup_wizard',
            description: 'Interactive session setup wizard for automated Google authentication configuration',
            inputSchema: {
              type: 'object',
              properties: {
                environment: {
                  type: 'string',
                  enum: ['local', 'cloud', 'smithery', 'auto-detect'],
                  description: 'Deployment environment (auto-detect will analyze current setup)',
                },
                preferences: {
                  type: 'object',
                  properties: {
                    priority: {
                      type: 'string',
                      enum: ['ease-of-use', 'reliability', 'portability', 'performance'],
                      description: 'User priority for session management'
                    },
                    hasChrome: {
                      type: 'boolean',
                      description: 'Whether user has local Chrome browser access'
                    },
                    cloudDeployment: {
                      type: 'boolean', 
                      description: 'Whether deploying to cloud platforms'
                    }
                  }
                }
              },
            },
          },
          {
            name: 'jules_get_cookies',
            description: 'Extract current browser cookies for session persistence and backup',
            inputSchema: {
              type: 'object',
              properties: {
                format: {
                  type: 'string',
                  enum: ['json', 'string'],
                  description: 'Output format for cookies (default: json)',
                },
              },
            },
          },
          {
            name: 'jules_set_cookies',
            description: 'Set browser cookies from string or JSON for authentication',
            inputSchema: {
              type: 'object',
              properties: {
                cookies: {
                  type: 'string',
                  description: 'Cookies as JSON string or cookie string format',
                },
                format: {
                  type: 'string',
                  enum: ['json', 'string'],
                  description: 'Format of input cookies (default: json)',
                },
              },
              required: ['cookies'],
            },
          },
          // === DEBUGGING & UTILITIES ===
          {
            name: 'jules_screenshot',
            description: 'Take a screenshot of current Jules page for debugging and verification',
            inputSchema: {
              type: 'object',
              properties: {
                taskId: {
                  type: 'string',
                  description: 'Optional task ID to navigate to first',
                },
                filename: {
                  type: 'string',
                  description: 'Optional filename for screenshot',
                },
              },
            },
          },
        ],
      };
    });

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

C2.9/5.0
Behavior1/5

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

No annotations exist, so the description must fully disclose behavior. It fails to do so: it doesn't describe where the screenshot is saved, whether it's temporary, what happens if the page isn't ready, or if it has side effects. Only the purpose is given, not behavioral traits.

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 a single sentence, no verbosity. However, it sacrifices necessary detail for brevity. Still, it is well-structured and front-loaded.

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?

The description lacks key information for a complete understanding, especially since there is no output schema. It doesn't explain what the tool returns (e.g., a file path, a data URL) or error conditions. For a simple screenshot tool, it should at least mention the outcome.

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 the schema already explains both parameters (taskId and filename). The tool description adds no additional context or constraints beyond that. Baseline 3 is appropriate.

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

Purpose5/5

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

The description clearly states the verb 'take' and the resource 'screenshot of current Jules page', with a specific purpose 'for debugging and verification'. This distinguishes it from sibling tools like jules_analyze_code or jules_send_message, which have different actions.

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 usage guidance is provided. The description does not indicate when to use this tool over siblings (e.g., when visual verification is needed vs code analysis). There is no mention of when-not-to-use or alternative tools.

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