Skip to main content
Glama

suggest-headings

Generate structured headings for Things 3 projects based on project goals and work type to organize tasks effectively.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_uuidNoOptional project UUID to inspect existing headings first
project_titleNoProject title if project_uuid is not available
goalNoShort description of what the project is trying to achieve
work_typeNoOptional category like design, software, content, workshop, personal
preferred_countNoPreferred number of headings to suggest

Implementation Reference

  • The "suggest-headings" tool implementation, which generates suggested headings for a project based on its title, goal, and work type, while taking existing headings into account if a project UUID is provided.
      "suggest-headings",
      {
        project_uuid: z
          .string()
          .optional()
          .describe("Optional project UUID to inspect existing headings first"),
        project_title: z
          .string()
          .optional()
          .describe("Project title if project_uuid is not available"),
        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"),
        preferred_count: z
          .number()
          .int()
          .min(3)
          .max(8)
          .optional()
          .describe("Preferred number of headings to suggest"),
      },
      async ({ project_uuid, project_title, goal, work_type, preferred_count }) => {
        const data = await withDatabase((db) => {
          const tasks = getAllTasks(db);
          const project = project_uuid
            ? tasks.find((task) => task.type === "project" && task.id === project_uuid)
            : undefined;
          const existingHeadings = project_uuid
            ? tasks
                .filter(
                  (task) =>
                    task.type === "heading" &&
                    task.projectId === project_uuid &&
                    !task.trashed
                )
                .map((task) => task.title)
            : [];
    
          return {
            projectTitle: project?.title ?? project_title ?? "",
            existingHeadings,
          };
        }).catch(() => ({
          projectTitle: project_title ?? "",
          existingHeadings: [] as string[],
        }));
    
        const baseSuggestions = inferHeadingTemplate({
          projectTitle: data.projectTitle,
          goal,
          workType: work_type,
        });
        const suggestedHeadings = uniqueHeadingNames(
          preferred_count ? baseSuggestions.slice(0, preferred_count) : baseSuggestions
        );
        const existingNormalized = new Set(
          data.existingHeadings.map((heading) => normalizeHeadingName(heading))
        );
        const missingHeadings = suggestedHeadings.filter(
          (heading) => !existingNormalized.has(normalizeHeadingName(heading))
        );
    
        const isExistingProject = Boolean(project_uuid);
    
        return buildTextResponse("Suggested heading structure for the project", {
          projectUuid: project_uuid ?? null,
          projectTitle: data.projectTitle || project_title || null,
          goal: goal ?? null,
          workType: work_type ?? null,
          existingHeadings: data.existingHeadings,
          suggestedHeadings,
          missingHeadings,
          creationMode: isExistingProject ? "existing-project" : "new-project",
          requiresManualCreation: isExistingProject && missingHeadings.length > 0,
          preferredCreationTool: isExistingProject ? null : "create-project-with-headings",
          userInstruction: isExistingProject
            ? (missingHeadings.length === 0
                ? "The existing project already has the suggested heading structure. You can continue creating or moving tasks into those headings."
                : buildHeadingCreationPrompt({
                    projectTitle: data.projectTitle || project_title,
                    suggestedHeadings,
                    missingHeadings,
                  }))
            : buildNewProjectStructurePrompt({
                projectTitle: data.projectTitle || project_title,
                suggestedHeadings,
              }),
          followUpInstruction: isExistingProject
            ? "If headings are missing in an existing project, ask the user to create them manually, then call get-headings or validate-headings before creating or moving tasks into them."
            : "For a new project, prefer create-project-with-headings or the JSON tool to create the project, headings, and optional to-dos in one operation.",
        });
      }
    );
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