Skip to main content
Glama

board_create_project

Create a new project to group related tasks and sessions under a shared goal. Use for major initiatives; defaults to active status and medium priority.

Instructions

Create a new project to group tasks and sessions under a shared goal. Projects are the top-level container — every task and session must belong to one. Use sparingly: create a new project for major initiatives (3+ related tasks), not for every piece of work. New projects are created with status='active' and priority='medium' (unless overridden). Returns { id, name, status, priority, message }.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesProject name — short, human-readable title shown everywhere the project is referenced
descriptionNoOptional longer description of the project's scope, goals, or context. Omit if the name is self-explanatory.
priorityNoPortfolio-level importance — drives weekly focus and default sort order in board_get_projects. This is DISTINCT from task.priority, which orders execution within a single project. Use critical/high for projects that should dominate the coming week; medium for steady-state work (default); low for back-burner initiatives you want visible but not pressing. Defaults to 'medium' when omitted.
metadataNoOptional key/value metadata (e.g., linked doc paths, deadlines, stakeholder names). Merged shallowly on board_update_project.

Implementation Reference

  • The async handler function for board_create_project. It receives { name, description, priority, metadata }, creates a Firestore document in the 'projects' collection with status='active' and default priority='medium', then returns the new project's ID, name, status, priority, and a success message.
      async ({ name, description, priority, metadata }) => {
        const now = Timestamp.now();
        const resolvedPriority: Priority = priority ?? "medium";
        const docRef = await db.collection("projects").add({
          name,
          description: description ?? null,
          status: "active",
          priority: resolvedPriority,
          metadata: metadata ?? {},
          created_at: now,
          updated_at: now,
        });
    
        return {
          content: [
            {
              type: "text" as const,
              text: JSON.stringify(
                {
                  id: docRef.id,
                  name,
                  status: "active",
                  priority: resolvedPriority,
                  message: `Project "${name}" created successfully`,
                },
                null,
                2
              ),
            },
          ],
        };
      }
    );
  • Zod input schema for board_create_project. Defines the 'name' (required string), 'description' (optional string), 'priority' (optional enum critical/high/medium/low), and 'metadata' (optional record of string to unknown) parameters.
    {
      name: z.string().describe("Project name — short, human-readable title shown everywhere the project is referenced"),
      description: z
        .string()
        .optional()
        .describe("Optional longer description of the project's scope, goals, or context. Omit if the name is self-explanatory."),
      priority: z
        .enum(["critical", "high", "medium", "low"])
        .optional()
        .describe("Portfolio-level importance — drives weekly focus and default sort order in board_get_projects. This is DISTINCT from task.priority, which orders execution within a single project. Use critical/high for projects that should dominate the coming week; medium for steady-state work (default); low for back-burner initiatives you want visible but not pressing. Defaults to 'medium' when omitted."),
      metadata: z
        .record(z.string(), z.unknown())
        .optional()
        .describe("Optional key/value metadata (e.g., linked doc paths, deadlines, stakeholder names). Merged shallowly on board_update_project."),
    },
  • Registration of the 'board_create_project' tool via server.tool(), called within the registerProjectTools() function.
    server.tool(
      "board_create_project",
      "Create a new project to group tasks and sessions under a shared goal. Projects are the top-level container — every task and session must belong to one. Use sparingly: create a new project for major initiatives (3+ related tasks), not for every piece of work. New projects are created with status='active' and priority='medium' (unless overridden). Returns { id, name, status, priority, message }.",
      {
        name: z.string().describe("Project name — short, human-readable title shown everywhere the project is referenced"),
        description: z
          .string()
          .optional()
          .describe("Optional longer description of the project's scope, goals, or context. Omit if the name is self-explanatory."),
        priority: z
          .enum(["critical", "high", "medium", "low"])
          .optional()
          .describe("Portfolio-level importance — drives weekly focus and default sort order in board_get_projects. This is DISTINCT from task.priority, which orders execution within a single project. Use critical/high for projects that should dominate the coming week; medium for steady-state work (default); low for back-burner initiatives you want visible but not pressing. Defaults to 'medium' when omitted."),
        metadata: z
          .record(z.string(), z.unknown())
          .optional()
          .describe("Optional key/value metadata (e.g., linked doc paths, deadlines, stakeholder names). Merged shallowly on board_update_project."),
      },
      async ({ name, description, priority, metadata }) => {
        const now = Timestamp.now();
        const resolvedPriority: Priority = priority ?? "medium";
        const docRef = await db.collection("projects").add({
          name,
          description: description ?? null,
          status: "active",
          priority: resolvedPriority,
          metadata: metadata ?? {},
          created_at: now,
          updated_at: now,
        });
    
        return {
          content: [
            {
              type: "text" as const,
              text: JSON.stringify(
                {
                  id: docRef.id,
                  name,
                  status: "active",
                  priority: resolvedPriority,
                  message: `Project "${name}" created successfully`,
                },
                null,
                2
              ),
            },
          ],
        };
      }
    );
  • The Project interface type used for the project data structure created by board_create_project.
    export interface Project {
      name: string;
      description: string | null;
      status: "active" | "paused" | "completed" | "archived";
      priority: Priority;
      metadata: Record<string, unknown>;
      created_at: Timestamp;
      updated_at: Timestamp;
    }
    
    export interface Task {
  • Valid state transitions map used for status management of projects, relevant context for the board_create_project handler.
    const validTransitions: Record<string, readonly string[]> = {
      active: ["paused", "completed", "archived"],
      paused: ["active", "completed", "archived"],
      completed: ["archived", "active"], // allow re-opening
      archived: ["active"], // allow un-archiving; caller can re-transition afterward
    };
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses defaults ('status='active', priority='medium' unless overridden'), the return structure, and the shallow merge behavior for metadata. It does not discuss auth or idempotency, but the description is sufficient for a creation tool.

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 five sentences, front-loaded with purpose, followed by usage guidelines, then defaults and return value. Every sentence adds value, with no redundancy or empty words. It is appropriately sized for the tool's complexity.

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

Completeness5/5

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

Given the lack of output schema and annotations, the description covers all essential aspects: creation purpose, defaults, return format, and usage guidelines. It also clarifies a nuanced parameter (priority). This completeness allows an AI agent to use the tool correctly without additional context.

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

Parameters5/5

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

Schema coverage is 100%, so baseline is 3. The description adds significant value: it explains the priority field's distinction from task.priority, suggests usage levels, and provides examples for metadata. Each parameter gets extra context beyond the schema, making this highly informative.

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 verb ('Create'), resource ('project'), and purpose ('to group tasks and sessions under a shared goal'). It distinguishes from sibling tools like board_create_task and board_create_session by emphasizing that projects are the top-level container. This meets the highest standard of purpose clarity.

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

Usage Guidelines4/5

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

The description provides explicit when-to-use guidance: 'Use sparingly: create a new project for major initiatives (3+ related tasks), not for every piece of work.' It implies that for small pieces of work, existing projects or task creation should be used. While it does not name alternatives explicitly, the sibling tool names provide enough context for an AI agent.

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/HuntsDesk/ve-vibe-board'

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