Skip to main content
Glama

create-task

Create a new task in a Dooray project by specifying required fields like project ID and subject, with options for assignees, tags, priority, and content formatting.

Instructions

Create a new task (업무) in a Dooray project. Required fields: projectId and subject.

RECOMMENDED INTERACTIVE WORKFLOW (ask user questions step by step):

  1. Templates: Call get-project-template-list, ask user if they want to use a template

    • If yes: Call get-project-template to get full details, use as defaults for subject/body/tags/assignees/cc/priority

    • Extract tag IDs: template.tags.map(t => t.id)

    • Transform members: template.users.to/cc to {id, type} format

  2. Title & Body: Ask for task title (subject) and content (body)

    • If template selected: Elaborate user's content to fit template structure

    • If no template and no body provided: Ask user for body content before creating task

    • Body format: {"mimeType": "text/x-markdown", "content": "..."}

  3. Assignees & CC: Ask for "to" (담당자) and "cc" (참조)

    • Get options: get-my-member-info (current user), get-project-member-list (members), get-project-member-group-list (groups)

    • Member types: {"id": "...", "type": "member|group|email"}

    • "member": organizationMemberId, "group": group id, "email": email address

  4. Tags: Call get-tag-list, ask which tags to register

    • CRITICAL: Check tagGroup.mandatory=true - MUST select from these groups or task creation fails (500 error)

    • tagGroup.selectOne=true: Select exactly ONE tag from group

    • tagGroup.selectOne=false: Select one or MORE tags from group

Key Settings:

  • Priority: Default "none" if not specified

  • Subtasks: Set parentPostId to create 하위업무

  • URL extraction: "https://nhnent.dooray.com/task/PROJECT_ID" → extract PROJECT_ID

Examples:

  • Simple: {"projectId": "123", "subject": "Fix bug", "tagIds": ["tag1"]}

  • With template: {"projectId": "123", "subject": "[SMS] Issue", "body": {...}, "assignees": [{...}], "tagIds": ["tag1", "tag2"]}

  • Full: {"projectId": "123", "subject": "Deploy", "assignees": [{"id": "user1", "type": "member"}], "cc": [{"id": "user2", "type": "member"}], "priority": "high", "tagIds": ["tag1"]}

Returns: Created task with ID and number.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
projectIdYesProject ID where the task will be created
parentPostIdNoParent task ID to create this as a subtask (하위업무). Omit to create a regular task.
subjectYesTask subject/title (required)
bodyNoTask body with formatted content. IMPORTANT: If user has not provided body content and no template is selected, ask the user for task details/description before creating the task.
assigneesNoList of assignees (담당자). To get assignee options: (1) use get-my-member-info for current user, (2) use get-project-member-list for project members, (3) use get-project-member-group-list for member groups. Each assignee object has {id: string, type: "member"|"group"|"email"}.
ccNoList of CC recipients (참조). To get CC options: (1) use get-my-member-info for current user, (2) use get-project-member-list for project members, (3) use get-project-member-group-list for member groups. Each CC object has {id: string, type: "member"|"group"|"email"}.
dueDateNoDue date in ISO 8601 format (YYYY-MM-DDTHH:mm:ssZ)
milestoneIdNoMilestone ID to associate with this task
tagIdsNoArray of tag IDs to apply to this task. IMPORTANT: Check for mandatory tag groups using get-tag-list tool. Projects may require specific tags from mandatory tag groups.
priorityNoTask priority level (highest, high, normal, low, lowest, none). Default: "none" if not specified by user.

Implementation Reference

  • The createTaskHandler function that executes the tool logic: validates input, calls Dooray projects API to create task, returns result or formatted error.
    export async function createTaskHandler(args: CreateTaskInput) {
      try {
        const result = await projectsApi.createTask({
          projectId: args.projectId,
          parentPostId: args.parentPostId,
          subject: args.subject,
          body: args.body,
          users: {
            to: transformMembers(args.assignees),
            cc: transformMembers(args.cc),
          },
          dueDate: args.dueDate,
          milestoneId: args.milestoneId,
          tagIds: args.tagIds,
          priority: args.priority,
        });
    
        return {
          content: [
            {
              type: 'text',
              text: JSON.stringify(result, null, 2),
            },
          ],
        };
      } catch (error) {
        return {
          content: [
            {
              type: 'text',
              text: `Error: ${formatError(error)}`,
            },
          ],
          isError: true,
        };
      }
    }
  • Zod schema (createTaskSchema) used for input validation in the handler.
    export const createTaskSchema = z.object({
      projectId: z.string().describe('Project ID where the task will be created'),
      parentPostId: z.string().optional().describe('Parent task ID to create this as a subtask'),
      subject: z.string().describe('Task subject/title'),
      body: bodySchema.optional().describe('Task body content'),
      assignees: z.array(memberSchema).optional().describe('List of assignees'),
      cc: z.array(memberSchema).optional().describe('List of CC recipients'),
      dueDate: z.string().optional().describe('Due date (ISO 8601 format: YYYY-MM-DDTHH:mm:ssZ)'),
      milestoneId: z.string().optional().describe('Milestone ID'),
      tagIds: z.array(z.string()).optional().describe('Array of tag IDs'),
      priority: z.enum(['highest', 'high', 'normal', 'low', 'lowest', 'none']).optional().describe('Task priority level'),
    });
  • src/index.ts:51-52 (registration)
    Registration of the 'create-task' tool in the central toolRegistry mapping tool names to handlers and schemas.
    'get-task': { handler: getTaskHandler, schema: getTaskSchema },
    'create-task': { handler: createTaskHandler, schema: createTaskSchema },
  • The createTaskTool object defining the tool metadata including name, description, and JSON inputSchema for MCP protocol.
    export const createTaskTool = {
      name: 'create-task',
  • src/index.ts:24-24 (registration)
    Import statement bringing in the create-task tool components (tool, handler, schema) for registration.
    import { createTaskTool, createTaskHandler, createTaskSchema } from './tools/projects/create-task.js';
Behavior5/5

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

With no annotations provided, the description carries the full burden and excels by disclosing critical behavioral traits: it warns of potential errors (e.g., 500 error if mandatory tags are not selected), explains default behaviors (priority defaults to 'none'), describes the return format ('Created task with ID and number'), and details workflow constraints like body content requirements. This goes beyond what the input schema alone provides.

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

Conciseness3/5

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

The description is well-structured with sections like workflow, key settings, and examples, but it is overly verbose (over 400 words). While most content is useful, some details (e.g., step-by-step interactive workflow) might be better suited for external documentation, reducing front-loaded clarity. It earns its place but could be more streamlined.

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

Completeness5/5

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

Given the tool's complexity (10 parameters, nested objects, no output schema, and no annotations), the description is highly complete. It covers purpose, usage, behavioral details, parameter semantics, and provides examples. It compensates for the lack of annotations and output schema by explaining return values and error conditions, making it sufficient for an agent to use the tool effectively.

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

Parameters4/5

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

The input schema has 100% description coverage, so the baseline is 3. The description adds significant value by elaborating on parameter usage: it explains how to derive values (e.g., using sibling tools for assignees/cc, extracting projectId from URLs), provides examples with context, and clarifies critical constraints (e.g., tag selection rules). However, it doesn't cover all parameters equally (e.g., dueDate, milestoneId get less attention), preventing a perfect score.

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 'Create' and the resource 'new task (업무) in a Dooray project', distinguishing it from sibling tools like update-task or get-task-list. It specifies the required fields (projectId and subject), making the purpose specific and actionable.

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

Usage Guidelines5/5

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

The description provides explicit guidance on when and how to use this tool through a detailed 'RECOMMENDED INTERACTIVE WORKFLOW', including step-by-step instructions and references to sibling tools (e.g., get-project-template-list, get-tag-list). It clearly outlines prerequisites and alternatives, such as using templates or handling mandatory tags.

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/jhl8041/dooray-mcp'

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