Skip to main content
Glama
blizzy78

Task Manager MCP Server

by blizzy78

Create task

create_task

Create new tasks with detailed specifications, complexity assessments, and completion criteria to manage and track work within the Task Manager system.

Instructions

Creates a new task that must be executed. If decomposing a complex task is required, must use 'decompose_task' first before executing it. All tasks start in the todo status. Must use 'update_task' before executing this task, and when executing this task has finished.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesA concise title for this task. Must be understandable out of context
descriptionYesA detailed description of this task. Must be understandable out of context
goalYesThe overall goal of this task. Must be understandable out of context
criticalPathYesWhether this task is on the critical path and required for completion
definitionsOfDoneYesA detailed list of criteria that must be met for this task to be considered 'complete'. Must be understandable out of context.
uncertaintyAreasYesA detailed list of areas where there is uncertainty about this task's requirements or execution. Must be understandable out of context. May be empty.
estimatedComplexityYesAn estimate of the complexity of this task. All tasks with complexity higher than low must be decomposed into smaller, more manageable subtasks before execution. Caution: Don't underestimate complexity.

Implementation Reference

  • The handler function that creates a new task object, stores it in the task database, optionally sets it as the current task for single-agent mode, computes incomplete tasks in the tree, and returns a CallToolResult with content (text warning if decomposition needed, resource link) and structured content with task info.
    export async function handleCreateTask(
      { title, description, goal, definitionsOfDone, criticalPath, uncertaintyAreas, estimatedComplexity }: CreateTaskArgs,
      taskDB: TaskDB,
      singleAgent: boolean
    ) {
      const task = {
        taskID: newTaskID(),
        status: TodoStatus,
        dependsOnTaskIDs: [],
    
        title,
        description,
        goal,
        definitionsOfDone,
        criticalPath: !!criticalPath,
        uncertaintyAreas,
        estimatedComplexity,
        lessonsLearned: [],
        verificationEvidence: [],
      } satisfies Task
    
      taskDB.set(task.taskID, task)
    
      if (singleAgent) {
        taskDB.setCurrentTask(task.taskID)
      }
    
      const incompleteTaskIDs = taskDB.incompleteTasksInTree(task.taskID).map((t) => t.taskID)
    
      const res = {
        taskCreated: toBasicTaskInfo(task, false, false, true),
        incompleteTasksIdealOrder: singleAgent ? incompleteTaskIDs : undefined,
      }
    
      return {
        content: [
          mustDecompose(task) &&
            ({
              type: 'text',
              text: "Task must be decomposed before execution, use 'decompose_task' tool",
              audience: ['assistant'],
            } satisfies TextContent),
    
          {
            type: 'resource_link',
            uri: `task://${task.taskID}`,
            name: task.taskID,
            title: task.title,
            annotations: {
              audience: ['assistant'],
              priority: 1,
            },
          } satisfies ResourceLink,
        ].filter(Boolean),
    
        structuredContent: res,
      } satisfies CallToolResult
    }
  • Zod schema defining the input arguments for the create_task tool, extending SimpleTaskSchema with estimatedComplexity field.
    export const CreateTaskArgsSchema = SimpleTaskSchema.extend({
      estimatedComplexity: TaskComplexitySchema,
    })
  • Tool definition object createTaskTool used for listing tools (via tools() in index.ts), including name, title, description, and inputSchema derived from CreateTaskArgsSchema.
    export const createTaskTool = {
      name: CREATE_TASK,
      title: 'Create task',
      description: `Creates a new task that must be executed.
    If decomposing a complex task is required, must use 'decompose_task' first before executing it.
    All tasks start in the todo status.
    Must use 'update_task' before executing this task, and when executing this task has finished.`,
      inputSchema: zodToJsonSchema(CreateTaskArgsSchema, { $refStrategy: 'none' }),
    }
  • tools/index.ts:24-27 (registration)
    Registration of the create_task tool handler and schema in the toolHandlers() map, used by task_manager.ts to dispatch tool calls.
    [CREATE_TASK]: {
      handler: handleCreateTask,
      schema: CreateTaskArgsSchema,
    } satisfies ToolHandlerInfo,
  • tools/index.ts:14-19 (registration)
    The tools() function returns an array of tool objects including createTaskTool, used for the listTools MCP request.
    export function tools(singleAgent: boolean) {
      if (!singleAgent) {
        return [createTaskTool, decomposeTaskTool, updateTaskTool, taskInfoTool] as const
      }
    
      return [createTaskTool, decomposeTaskTool, updateTaskTool, taskInfoTool, currentTaskTool] as const
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses that tasks start in 'todo status' and mentions prerequisites (decompose_task for complexity, update_task before/after execution), which adds useful context. However, it doesn't cover behavioral aspects like error handling, permissions, or what happens on creation (e.g., does it return an ID?). The description adds some value but leaves gaps for a mutation tool.

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 4 sentences but could be more front-loaded. The first sentence states the purpose, but the subsequent sentences about decomposition and update_task usage, while important, might be better structured. It's not overly verbose, but the flow could be improved for clarity.

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

Completeness3/5

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

Given no annotations and no output schema, the description provides good usage guidelines and some behavioral context (starting status, prerequisites). However, for a mutation tool with 7 required parameters and complex nested objects, it lacks details on what happens after creation (e.g., success response, error cases). The description is adequate but has clear gaps in completeness.

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 documents all 7 parameters thoroughly. The description adds no parameter-specific information beyond what's in the schema. According to the rules, with high schema coverage (>80%), the baseline is 3 even with no param info in the description.

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 tool's purpose: 'Creates a new task that must be executed.' It specifies the verb ('creates') and resource ('task'), but doesn't explicitly differentiate from siblings like 'update_task' or 'decompose_task' beyond mentioning them. The purpose is clear but lacks direct sibling comparison.

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 usage guidelines: 'If decomposing a complex task is required, must use 'decompose_task' first before executing it' and 'Must use 'update_task' before executing this task, and when executing this task has finished.' It clearly states when to use alternatives (decompose_task for complex tasks) and prerequisites (update_task before and after execution).

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/blizzy78/mcp-task-manager'

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