Skip to main content
Glama
dragosroua

addTaskManager MCP Server

by dragosroua

get_stalled_items_in_decide

Identify stalled tasks and projects in the Decide realm to maintain workflow momentum within the ADD framework.

Instructions

Find stalled items (tasks + projects) in Decide realm.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • src/index.ts:603-607 (registration)
    Tool registration in ListToolsRequestSchema handler, including name, description, and input schema (no parameters).
    {
      name: 'get_stalled_items_in_decide',
      description: 'Find stalled items (tasks + projects) in Decide realm.',
      inputSchema: { type: 'object', properties: {} }
    },
  • src/index.ts:763-764 (registration)
    Tool dispatch in CallToolRequestSchema switch statement.
      return await this.getStalledItemsInDecide();
    case 'get_undecided_items_in_decide':
  • Primary handler function implementing the tool logic. Uses withCloudKitOrMock to provide production CloudKit implementation (calls getTasksInDecideStalled and filters projects) or mock data. Formats response listing stalled tasks and projects with overdue days.
    private async getStalledItemsInDecide() {
      return this.withCloudKitOrMock(
        'getStalledItemsInDecide',
        async () => {
          // CloudKit production implementation
          const [stalledTasks, stalledProjects] = await Promise.all([
            this.cloudKitService.getTasksInDecideStalled(),
            this.cloudKitService.getProjectsByRealm(2).then((projects: any[]) => 
              projects.filter((project: any) => {
                const endDate = project.fields?.endDate?.value;
                return endDate && new Date(endDate) < new Date();
              })
            )
          ]);
    
          const allStalledItems = [...stalledTasks, ...stalledProjects];
          const now = new Date();
          
          let response = `Stalled items in Decide realm (past due dates):\n`;
          if (allStalledItems.length === 0) {
            response += 'No stalled items found. Great job staying on track! 🎉';
          } else {
            response += allStalledItems.map(item => {
              const isTask = item.recordType === 'Task';
              const name = isTask ? item.fields?.taskName?.value : item.fields?.projectName?.value;
              const endDate = item.fields?.endDate?.value;
              const daysOverdue = Math.ceil((now.getTime() - new Date(endDate).getTime()) / (24 * 60 * 60 * 1000));
              const type = isTask ? 'Task' : 'Project';
              return `- ${name} (${item.recordName}) - ${daysOverdue} day${daysOverdue > 1 ? 's' : ''} overdue [${type}]`;
            }).join('\n');
          }
          
          return { content: [{ type: 'text', text: response }] };
        },
        async () => {
          // Mock implementation
          const now = new Date();
          const yesterday = new Date(now.getTime() - 86400000).toISOString();
          const weekAgo = new Date(now.getTime() - 7 * 86400000).toISOString();
          
          const mockItems = [
            { 
              recordName: 'task_stalled_1', 
              taskName: 'Review project requirements', 
              endDate: yesterday,
              contextRecordName: 'context_work',
              realmId: 2,
              stalledReason: 'Past due date - needs rescheduling'
            },
            { 
              recordName: 'project_stalled_1', 
              projectName: 'Client presentation prep', 
              endDate: weekAgo,
              contextRecordName: 'context_work',
              realmId: 2,
              stalledReason: 'Week overdue - may need scope revision'
            }
          ];
          
          let response = `Stalled items in Decide realm (past due dates):\n`;
          response += mockItems.map(item => {
            const type = item.recordName.startsWith('task_') ? 'Task' : 'Project';
            const name = item.taskName || (item as any).projectName;
            const daysOverdue = Math.ceil((now.getTime() - new Date(item.endDate).getTime()) / (24 * 60 * 60 * 1000));
            return `- ${name} (${item.recordName}) - ${daysOverdue} day${daysOverdue > 1 ? 's' : ''} overdue`;
          }).join('\n');
          
          return { content: [{ type: 'text', text: response }] };
        }
      );
    }
  • Helper method in CloudKitService that performs the core CloudKit query for stalled tasks: Tasks in Decide realm (realmId=2) with past endDate, sorted by endDate ascending (most overdue first). Called by production handler.
    async getTasksInDecideStalled(): Promise<ZenTaskticTask[]> {
      const now = new Date().getTime();
      
      return this.queryRecords<ZenTaskticTask>('Task', {
        filterBy: [
          { fieldName: 'realmId', fieldValue: 2, comparator: 'EQUALS' },
          { fieldName: 'endDate', fieldValue: now, comparator: 'LESS_THAN' }
        ],
        sortBy: [{ fieldName: 'endDate', ascending: true }] // Most overdue first
      });
    }
  • Helper method to fetch all projects in a given realm, used in production handler to get Decide projects then filter stalled ones client-side.
    async getProjectsByRealm(realmId: number): Promise<ZenTaskticProject[]> {
      return this.queryRecords<ZenTaskticProject>('Projects', {
        filterBy: [{ 
          fieldName: 'realmId', 
          fieldValue: realmId,
          comparator: 'EQUALS' 
        }],
        sortBy: [{ fieldName: 'lastModified', ascending: false }]
      });
    }
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 what the tool does but doesn't describe behavioral traits like what 'stalled' means operationally, whether this is a read-only operation, potential rate limits, authentication needs, or the format of returned data. This is inadequate for a tool with zero annotation coverage.

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 purpose without any wasted words. It is appropriately sized and front-loaded, making it easy to understand at a glance.

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 the tool's complexity (simple query with 0 parameters) and the absence of annotations and output schema, the description is minimally adequate. It specifies the resource and realm but lacks details on what 'stalled' entails, return format, or behavioral context, leaving gaps in completeness for effective agent use.

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 tool has 0 parameters, and the input schema has 100% description coverage (though empty). The description doesn't need to explain parameters, so it meets the baseline expectation. No additional parameter information is required or provided.

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 ('Find') and the target resources ('stalled items (tasks + projects) in Decide realm'), which provides specific verb+resource information. However, it doesn't explicitly differentiate from sibling tools like 'get_ready_items_in_decide' or 'get_undecided_items_in_decide' that also operate on items in the Decide realm, missing full sibling differentiation.

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. It doesn't mention prerequisites, exclusions, or compare to sibling tools such as 'get_ready_items_in_decide' or 'get_undecided_items_in_decide', leaving usage context entirely implied from the tool name alone.

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/dragosroua/addtaskmanager-mcp-server'

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