Skip to main content
Glama

get-task

Read-onlyIdempotent

Retrieve complete details for a specific Dooray task by task ID or URL, including body, workflow status, assignees, attachments, and metadata; optionally omit body content.

Instructions

Get detailed information about a specific task.

This tool retrieves complete details of a task including its full body content, attachments, workflow status, assignees, and all metadata.

URL Pattern Recognition - Two formats supported:

  1. Project-scoped URL: "https://nhnent.dooray.com/task/PROJECT_ID/TASK_ID"

  2. Task-only URL: "https://nhnent.dooray.com/project/tasks/TASK_ID"

IMPORTANT:

  • taskId is REQUIRED, projectId is OPTIONAL

  • The taskId is the unique identifier (ID) from the URL, NOT the sequential task number shown in the UI

  • You can fetch task details with just the taskId without knowing the projectId

  • When a specific task URL is provided, use this tool directly instead of calling get-project-list first

  • To find taskId from task descriptions, use get-task-list to search and get task IDs

  • Bodies can exceed 50,000 characters. When you only need status, assignees, number or dates, set includeBody to false

Examples:

  • From URL pattern 1: {"taskId": "4206132384174602537", "projectId": "1769381697328002548"}

  • From URL pattern 2: {"taskId": "4206132384174602537"}

  • Just taskId: {"taskId": "789012345"}

  • With both IDs: {"taskId": "789012345", "projectId": "123456"}

  • Without body: {"taskId": "789012345", "includeBody": false}

Returns complete task information including:

  • Basic info: id, number, subject, taskNumber (PROJECT-CODE/NUMBER format)

  • Project: project object with id and code

  • Status: workflowClass (registered/working/closed), workflow (id and name), closed flag, priority

  • Dates: createdAt, updatedAt, dueDate, dueDateFlag

  • Content: body with mimeType (text/x-markdown or text/html) and content. With includeBody false: mimeType and contentLength

  • Hierarchy: parent task information (id, number, subject) if this is a subtask

  • People: users object with from (creator), to (assignees), cc (watchers)

  • Organization: milestone (id, name), tags array (id only, use get-tag for names)

  • Files: fileIdList (attachment IDs, use get-attachment-list for names and sizes)

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "taskId": "<taskId>"
    },
    "name": "get-task"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskIdYesTask ID (unique identifier, REQUIRED)
projectIdNoProject ID (optional, can be omitted)
includeBodyNoDefault true. Set to false to get body mimeType and contentLength instead of the full content

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.3
    • addedInput schema / properties / includeBody
      Added value: +{
      +  "description": "Default true. Set to false to get body mimeType and contentLength instead of the full content",
      +  "type": "boolean"
      +}
  2. First observedv1.0.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered; the description adds genuinely new behavior: draft URLs fail with 404, bodies can exceed 50,000 characters, and includeBody=false substitutes mimeType plus contentLength for content. It does not discuss permissions or rate limits, keeping it short of a 5.

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 critical guidance is front-loaded and the URL patterns are useful, but the text is bloated: the required/optional facts are stated twice (once in IMPORTANT, again in the schema and again in the param list), and five near-identical example payloads follow a section that already gave worked URL conversions. It could lose roughly a third of its length without losing information.

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?

With no output schema, the description carries the burden of describing returns, and it does so field by field (basic info, project, status, dates, content, hierarchy, people, organization, files), including cross-references to get-tag and get-attachment-list for name resolution. Nothing needed to call it correctly is missing.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema: taskId is the unique identifier from the URL and NOT the sequential task number shown in the UI, projectId is optional and can be omitted entirely, and includeBody=false changes the returned body fields. The redundant restatement of 'taskId is REQUIRED' is the only wasted portion.

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?

States a specific verb and resource ('Get detailed information about a specific task') and immediately scopes it by listing what is returned (body, attachments, workflow status, assignees, metadata). It is clearly distinguishable from get-task-list, which the description names as the search-oriented sibling.

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?

Gives explicit routing rules: when a task URL is supplied, call this tool directly instead of get-project-list; when only a description is known, use get-task-list to find the taskId; and set includeBody to false when only status/assignees/dates are needed. It also rules out draft URLs, which return 404.

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