Skip to main content
Glama

create-project-with-headings

Create structured projects in Things 3 with predefined headings, tasks, deadlines, and organization to manage work systematically.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesTitle of the new project to create in Things
goalNoShort description of what the project is trying to achieve
work_typeNoOptional category like design, software, content, workshop, personal
methodologyNoOptional methodology or framework to reflect in the heading structure
notesNoNotes for the project
whenNotoday, tomorrow, anytime, someday, YYYY-MM-DD or YYYY-MM-DD@HH:MM
deadlineNoDeadline date for the project
tagsNoTag names to apply to the project
area-idNoArea UUID to place the project into
areaNoArea title to place the project into
headingsNoExplicit headings to create. If omitted, headings are inferred.
todosNoTop-level to-dos to create in the project after the headings
todos_by_headingNoMap of heading title to to-do titles that should be created under that heading
revealNoReveal the newly created project in Things

Implementation Reference

  • The implementation of the 'create-project-with-headings' MCP tool. It defines the input schema, handles the request, builds a structured payload, and uses Things' JSON URL scheme to perform the creation.
      "create-project-with-headings",
      {
        title: z.string().describe("Title of the new project to create in Things"),
        goal: z
          .string()
          .optional()
          .describe("Short description of what the project is trying to achieve"),
        work_type: z
          .string()
          .optional()
          .describe("Optional category like design, software, content, workshop, personal"),
        methodology: z
          .string()
          .optional()
          .describe("Optional methodology or framework to reflect in the heading structure"),
        notes: z.string().optional().describe("Notes for the project"),
        when: z.string().optional().describe("today, tomorrow, anytime, someday, YYYY-MM-DD or YYYY-MM-DD@HH:MM"),
        deadline: z.string().optional().describe("Deadline date for the project"),
        tags: z.array(z.string()).optional().describe("Tag names to apply to the project"),
        "area-id": z.string().optional().describe("Area UUID to place the project into"),
        area: z.string().optional().describe("Area title to place the project into"),
        headings: z.array(z.string()).min(1).optional().describe("Explicit headings to create. If omitted, headings are inferred."),
        todos: z.array(z.string()).optional().describe("Top-level to-dos to create in the project after the headings"),
        todos_by_heading: z
          .record(z.array(z.string()))
          .optional()
          .describe("Map of heading title to to-do titles that should be created under that heading"),
        reveal: z.boolean().optional().describe("Reveal the newly created project in Things"),
      },
      async ({
        title,
        goal,
        work_type,
        methodology,
        notes,
        when,
        deadline,
        tags,
        area,
        "area-id": areaId,
        headings,
        todos,
        todos_by_heading,
        reveal,
      }) => {
        const inferredHeadings = uniqueHeadingNames(
          headings?.length
            ? headings
            : inferHeadingTemplate({
                projectTitle: `${title} ${methodology ?? ""}`.trim(),
                goal,
                workType: work_type,
              })
        );
    
        const payload = buildStructuredProjectPayload({
          title,
          notes,
          when,
          deadline,
          tags,
          area,
          areaId,
          headings: inferredHeadings,
          todosByHeading: todos_by_heading,
          todos,
        });
        const data = JSON.stringify(payload);
        const enriched = await enrichWriteParams("json", {
          data,
          reveal,
        });
        const url = await openThingsURL("json", buildURLParams(enriched));
    
        return buildTextResponse(`Created structured project "${title}" with headings`, {
          title,
          goal: goal ?? null,
          workType: work_type ?? null,
          methodology: methodology ?? null,
          headings: inferredHeadings,
          todosByHeading: todos_by_heading ?? {},
          todos: todos ?? [],
          payload,
          url,
          guidance:
            "Use this tool for brand-new projects that need headings. For existing projects, inspect headings first and ask the user to create missing headings manually.",
        });
      }
    );
Behavior1/5

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

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

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

Completeness1/5

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

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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/soycanopa/SupaThings-MCP'

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