Skip to main content
Glama
dragosroua

addTaskManager MCP Server

by dragosroua

do_mark_project_as_done

Mark a project as completed in the Do realm to track progress and maintain workflow organization within the ADD framework.

Instructions

Mark projects as completed in Do realm.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
projectRecordNameYesProject record name

Implementation Reference

  • src/index.ts:535-544 (registration)
    Tool registration in the listTools response, defining the tool name, description, and input schema.
      name: 'do_mark_project_as_done',
      description: 'Mark projects as completed in Do realm.',
      inputSchema: {
        type: 'object',
        properties: {
          projectRecordName: { type: 'string', description: 'Project record name' }
        },
        required: ['projectRecordName']
      }
    },
  • Input schema requiring 'projectRecordName' as a string.
    inputSchema: {
      type: 'object',
      properties: {
        projectRecordName: { type: 'string', description: 'Project record name' }
      },
      required: ['projectRecordName']
    }
  • Core handler function: validates project exists and is in Do realm (ID 3), simulates completion by setting endDate and moving to 'Done' (mock; production would update CloudKit record).
    private async markProjectAsDone(projectRecordName: string) {
      // Validate that project is in Do realm before marking as done
      const item = await this.mockFetchItem(projectRecordName, 'Project');
      if (!item) {
        throw new McpError(ErrorCode.InvalidParams, `Project ${projectRecordName} not found`);
      }
      if (item.realmId !== REALM_DO_ID) {
        throw new McpError(ErrorCode.InvalidParams, `Project ${projectRecordName} must be in Do realm to mark as done. Current realm: ${item.realmId}. Move to Do realm first.`);
      }
      
      const completionTime = new Date().toISOString();
      // Mock marking project as done via CloudKit - this would also mark all subtasks as done
      return { content: [{ type: 'text', text: `Project ${projectRecordName} and all subtasks marked as done at ${completionTime}. Moved to Done collection (realm 4).` }] };
    }
  • src/index.ts:735-738 (registration)
    Dispatch/registration in CallToolRequestSchema switch statement, validating args and calling the handler.
    case 'do_mark_project_as_done':
      this.validateArgs(args, ['projectRecordName']);
      return await this.markProjectAsDone(args.projectRecordName);
  • Helper function used by handler to fetch/mock project data for realm validation.
    private async mockFetchItem(itemRecordName: string, itemType: 'Task' | 'Project'): Promise<any> {
      // Mock different scenarios based on record name patterns
      const baseItem = {
        recordName: itemRecordName,
        type: itemType,
        lastModified: new Date().toISOString()
      };
    
      // Simulate different states for validation testing
      if (itemRecordName.includes('assess')) {
        return { ...baseItem, realmId: REALM_ASSESS_ID, contextRecordName: null, endDate: null };
      } else if (itemRecordName.includes('undecided')) {
        return { ...baseItem, realmId: REALM_DECIDE_ID, contextRecordName: null, endDate: null };
      } else if (itemRecordName.includes('stalled')) {
        const yesterday = new Date(Date.now() - 86400000).toISOString();
        return { ...baseItem, realmId: REALM_DECIDE_ID, contextRecordName: 'context_work', endDate: yesterday };
      } else if (itemRecordName.includes('ready')) {
        const tomorrow = new Date(Date.now() + 86400000).toISOString();
        return { ...baseItem, realmId: REALM_DECIDE_ID, contextRecordName: 'context_work', endDate: tomorrow };
      } else if (itemRecordName.includes('do')) {
        const today = new Date().toISOString();
        return { ...baseItem, realmId: REALM_DO_ID, contextRecordName: 'context_work', endDate: today };
      } else {
        // Default to Assess realm item
        return { ...baseItem, realmId: REALM_ASSESS_ID, contextRecordName: null, endDate: null };
      }
    }
Behavior2/5

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

No annotations are provided, so the description carries full burden. It states the action ('Mark projects as completed') but lacks critical behavioral details: whether this is a destructive/mutative operation, what permissions are required, how completion affects project status (e.g., moves it out of 'Do' realm), error conditions, or response format. For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

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 with zero waste. It front-loads the core action ('Mark projects as completed') and specifies the context ('in Do realm'). Every word earns its place, making it easy to parse quickly.

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?

Given the tool's complexity (a mutation operation with no annotations and no output schema), the description is incomplete. It lacks details on behavioral impact (e.g., what 'completed' means operationally), error handling, or return values. For a tool that changes project state, more context is needed to guide the agent effectively.

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%, with the single parameter 'projectRecordName' documented in the schema. The description adds no additional parameter semantics beyond implying it operates on projects. Since the schema fully describes the parameter, the baseline score of 3 is appropriate—the description doesn't compensate but doesn't need to given high schema coverage.

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 verb ('Mark') and resource ('projects'), specifying the action and target. It distinguishes from siblings like 'do_mark_task_as_done' by focusing on projects rather than tasks, but doesn't fully differentiate from other project-related tools like 'assess_archive_project_to_collection' in terms of purpose. The purpose is clear but could be more specific about what 'completed' entails in this context.

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 (e.g., projects must be in the 'Do' realm), exclusions (e.g., cannot mark archived projects), or compare to siblings like 'assess_archive_project_to_collection' or 'decide_move_project_to_do'. The agent must infer usage from the tool name and context 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