Skip to main content
Glama

add_project

Create a new project in Things.app with title, notes, tags, scheduling, and initial tasks to organize work and track progress.

Instructions

Create a new project in Things.app. Add notes, tags, assign to areas, and pre-populate with initial to-dos.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesProject title (required). Clear name describing the project goal, outcome, or deliverable
notesNoProject description, objectives, scope, or additional context (max 10,000 characters). Supports markdown formatting for rich text documentation
whenNoSchedule when to start working on this project. Use "today" to start immediately, "tomorrow" to start next day, "evening" to start later today, "anytime" for flexible timing, "someday" for future consideration, or ISO date format (YYYY-MM-DD) for specific start date
deadlineNoSet a deadline for project completion in ISO date format (YYYY-MM-DD). Creates deadline tracking and reminders in Things.app
tagsNoArray of tag names for categorizing and organizing the project (max 20 tags). Tags help with filtering and project management
areaIdNoID of the area of responsibility to assign this project to. Use this when you know the specific area ID
areaNameNoName of the area of responsibility to assign this project to (e.g., "Work", "Personal", "Health", "Finance"). Areas help organize projects by life domain
initialTodosNoArray of initial to-do item descriptions to create within the project (max 50 items). Each string becomes a separate task within the project
completedNoMark the project as completed immediately upon creation (default: false). Useful for logging already completed projects
canceledNoMark the project as canceled immediately upon creation (default: false). Useful for recording projects that are no longer viable
creationDateNoOverride the creation date with a specific ISO8601 datetime (YYYY-MM-DDTHH:MM:SS). Useful for importing historical project data
completionDateNoSet a specific completion date using ISO8601 datetime (YYYY-MM-DDTHH:MM:SS). Only used when completed is true

Implementation Reference

  • Handler function that logs the action, maps input parameters to Things.app URL parameters, builds the URL using buildThingsUrl, opens the URL to create the project, and returns a success message.
    async (params) => {
      try {
        logger.info('Adding new project', { title: params.title });
        
        const urlParams: Record<string, any> = {
          title: params.title
        };
    
        // Map schema parameters to Things URL scheme parameters
        if (params.notes) urlParams.notes = params.notes;
        if (params.when) urlParams.when = params.when;
        if (params.deadline) urlParams.deadline = params.deadline;
        if (params.tags) urlParams.tags = params.tags.join(',');
        if (params.areaId) urlParams['area-id'] = params.areaId;
        if (params.areaName) urlParams.area = params.areaName;
        if (params.initialTodos) urlParams['to-dos'] = params.initialTodos.join('\n');
        if (params.completed) urlParams.completed = params.completed;
        if (params.canceled) urlParams.canceled = params.canceled;
        if (params.creationDate) urlParams['creation-date'] = params.creationDate;
        if (params.completionDate) urlParams['completion-date'] = params.completionDate;
        
        const url = buildThingsUrl('add-project', urlParams);
        logger.debug('Generated URL', { url });
        
        await openThingsUrl(url);
        
        return {
          content: [{
            type: "text",
            text: `Successfully created project: ${params.title}`
          }]
        };
      } catch (error) {
        logger.error('Failed to add project', { error: error instanceof Error ? error.message : error });
        throw error;
      }
    }
  • Zod schema defining the structure and validation rules for the input parameters of the add_project tool.
    const addProjectSchema = z.object({
      title: z.string().min(1).describe('Project title (required). Clear name describing the project goal, outcome, or deliverable'),
      notes: z.string().max(10000).optional().describe('Project description, objectives, scope, or additional context (max 10,000 characters). Supports markdown formatting for rich text documentation'),
      when: z.enum(['today', 'tomorrow', 'evening', 'anytime', 'someday'])
        .or(z.string().regex(/^\d{4}-\d{2}-\d{2}$/))
        .optional()
        .describe('Schedule when to start working on this project. Use "today" to start immediately, "tomorrow" to start next day, "evening" to start later today, "anytime" for flexible timing, "someday" for future consideration, or ISO date format (YYYY-MM-DD) for specific start date'),
      deadline: z.string()
        .regex(/^\d{4}-\d{2}-\d{2}$/)
        .optional()
        .describe('Set a deadline for project completion in ISO date format (YYYY-MM-DD). Creates deadline tracking and reminders in Things.app'),
      tags: z.array(z.string().min(1))
        .max(20)
        .optional()
        .describe('Array of tag names for categorizing and organizing the project (max 20 tags). Tags help with filtering and project management'),
      areaId: z.string()
        .optional()
        .describe('ID of the area of responsibility to assign this project to. Use this when you know the specific area ID'),
      areaName: z.string()
        .optional()
        .describe('Name of the area of responsibility to assign this project to (e.g., "Work", "Personal", "Health", "Finance"). Areas help organize projects by life domain'),
      initialTodos: z.array(z.string().min(1))
        .max(50)
        .optional()
        .describe('Array of initial to-do item descriptions to create within the project (max 50 items). Each string becomes a separate task within the project'),
      completed: z.boolean()
        .optional()
        .default(false)
        .describe('Mark the project as completed immediately upon creation (default: false). Useful for logging already completed projects'),
      canceled: z.boolean()
        .optional()
        .default(false)
        .describe('Mark the project as canceled immediately upon creation (default: false). Useful for recording projects that are no longer viable'),
      creationDate: z.string()
        .regex(/^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}/)
        .optional()
        .describe('Override the creation date with a specific ISO8601 datetime (YYYY-MM-DDTHH:MM:SS). Useful for importing historical project data'),
      completionDate: z.string()
        .regex(/^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}/)
        .optional()
        .describe('Set a specific completion date using ISO8601 datetime (YYYY-MM-DDTHH:MM:SS). Only used when completed is true')
    });
  • Registration function that calls server.tool to register the 'add_project' tool with its name, description, schema, and handler on the MCP server.
    export function registerAddProjectTool(server: McpServer): void {
      server.tool(
        'add_project',
        'Create a new project in Things.app. Add notes, tags, assign to areas, and pre-populate with initial to-dos.',
        addProjectSchema.shape,
        async (params) => {
          try {
            logger.info('Adding new project', { title: params.title });
            
            const urlParams: Record<string, any> = {
              title: params.title
            };
    
            // Map schema parameters to Things URL scheme parameters
            if (params.notes) urlParams.notes = params.notes;
            if (params.when) urlParams.when = params.when;
            if (params.deadline) urlParams.deadline = params.deadline;
            if (params.tags) urlParams.tags = params.tags.join(',');
            if (params.areaId) urlParams['area-id'] = params.areaId;
            if (params.areaName) urlParams.area = params.areaName;
            if (params.initialTodos) urlParams['to-dos'] = params.initialTodos.join('\n');
            if (params.completed) urlParams.completed = params.completed;
            if (params.canceled) urlParams.canceled = params.canceled;
            if (params.creationDate) urlParams['creation-date'] = params.creationDate;
            if (params.completionDate) urlParams['completion-date'] = params.completionDate;
            
            const url = buildThingsUrl('add-project', urlParams);
            logger.debug('Generated URL', { url });
            
            await openThingsUrl(url);
            
            return {
              content: [{
                type: "text",
                text: `Successfully created project: ${params.title}`
              }]
            };
          } catch (error) {
            logger.error('Failed to add project', { error: error instanceof Error ? error.message : error });
            throw error;
          }
        }
      );
    }
  • src/index.ts:22-22 (registration)
    Invocation of the registerAddProjectTool function during main server initialization to enable the tool.
    registerAddProjectTool(server);
  • TypeScript interface defining the parameters for add-project in Things.app URL scheme.
    export interface AddProjectParams {
      title: string;
      notes?: string;
      when?: WhenValue;
      deadline?: string;
      tags?: string;
      area?: string;
      'to-dos'?: string;
      completed?: boolean;
      canceled?: boolean;
    }
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. While it mentions the creation action and some capabilities, it doesn't disclose important behavioral traits like whether this requires authentication, what happens on duplicate project names, whether creation is synchronous or asynchronous, error conditions, or what the response looks like. For a creation tool with 12 parameters and no annotations, this is a significant gap.

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 front-loads the core purpose ('Create a new project in Things.app') and then lists key capabilities. Every word earns its place with no redundancy or unnecessary elaboration.

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?

For a creation tool with 12 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what happens after creation, what the return value is, error handling, or important behavioral constraints. The description covers the 'what' but not the 'how' or 'what happens next' that an agent needs to use this tool 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?

The schema description coverage is 100%, so the schema already documents all 12 parameters thoroughly. The description mentions 'add notes, tags, assign to areas, and pre-populate with initial to-dos' which maps to some parameters, but doesn't add meaningful semantic context beyond what's already in the schema descriptions. The baseline of 3 is appropriate when the schema does the heavy lifting.

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 action ('Create a new project') and the resource ('in Things.app'), with specific details about what can be added (notes, tags, areas, initial to-dos). It distinguishes from sibling tools like 'add_todo' by focusing on project creation rather than task creation.

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

Usage Guidelines3/5

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

The description implies usage for creating projects with various attributes, but doesn't explicitly state when to use this tool versus alternatives like 'update_project' or 'add_todo'. It provides context about what can be done but lacks explicit guidance on when this specific tool is appropriate versus other options.

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/wbopan/things-mcp'

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