Skip to main content
Glama

project_create

Create a new project as the top-level container for all work. Define its name, description, status, and tags to organize tasks and epics.

Instructions

Create a new project. Projects are the top-level container for all work.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesProject name
descriptionNoProject description
statusNoProject statusactive
tagsNoTags for categorization

Implementation Reference

  • The actual handler function for the 'project_create' tool. It inserts a new project into the SQLite database (using the name, description, status, and tags from args) and logs the creation activity.
    function handleProjectCreate(args: Record<string, unknown>) {
      const db = getDb();
      const name = args.name as string;
      const description = (args.description as string) ?? null;
      const status = (args.status as string) ?? 'active';
      const tags = JSON.stringify((args.tags as string[]) ?? []);
    
      const project = db
        .prepare(
          'INSERT INTO projects (name, description, status, tags) VALUES (?, ?, ?, ?) RETURNING *'
        )
        .get(name, description, status, tags);
    
      const row = project as Record<string, unknown>;
      logActivity(db, 'project', row.id as number, 'created', null, null, null, `Project '${name}' created`);
    
      return project;
    }
  • The input schema definition for 'project_create' tool. Declares the tool name, description, and expected input parameters: name (required string), description, status (enum with default 'active'), and tags (array of strings).
    {
      name: 'project_create',
      description: 'Create a new project. Projects are the top-level container for all work.',
      annotations: { title: 'Create Project', readOnlyHint: false, destructiveHint: false, idempotentHint: false, openWorldHint: false },
      inputSchema: {
        type: 'object',
        properties: {
          name: { type: 'string', description: 'Project name' },
          description: { type: 'string', description: 'Project description' },
          status: {
            type: 'string',
            enum: ['active', 'on_hold', 'completed', 'archived'],
            default: 'active',
            description: 'Project status',
          },
          tags: {
            type: 'array',
            items: { type: 'string' },
            description: 'Tags for categorization',
          },
        },
        required: ['name'],
      },
    },
  • src/index.ts:10-49 (registration)
    Registration point: imports 'definitions' and 'handlers' from projects.ts. The definition is spread into ALL_TOOLS (line 24), and the handler is spread into ALL_HANDLERS (line 38). The handler lookup occurs in the CallToolRequestSchema handler at line 81.
    import { definitions as projectDefs, handlers as projectHandlers } from './tools/projects.js';
    import { definitions as epicDefs, handlers as epicHandlers } from './tools/epics.js';
    import { definitions as taskDefs, handlers as taskHandlers } from './tools/tasks.js';
    import { definitions as subtaskDefs, handlers as subtaskHandlers } from './tools/subtasks.js';
    import { definitions as noteDefs, handlers as noteHandlers } from './tools/notes.js';
    import { definitions as dashboardDefs, handlers as dashboardHandlers } from './tools/dashboard.js';
    import { definitions as searchDefs, handlers as searchHandlers } from './tools/search.js';
    import { definitions as activityDefs, handlers as activityHandlers } from './tools/activity.js';
    import { definitions as commentDefs, handlers as commentHandlers } from './tools/comments.js';
    import { definitions as templateDefs, handlers as templateHandlers } from './tools/templates.js';
    import { definitions as exportImportDefs, handlers as exportImportHandlers } from './tools/export-import.js';
    import { closeDb } from './db.js';
    
    const ALL_TOOLS: Tool[] = [
      ...projectDefs,
      ...epicDefs,
      ...taskDefs,
      ...subtaskDefs,
      ...noteDefs,
      ...commentDefs,
      ...templateDefs,
      ...dashboardDefs,
      ...searchDefs,
      ...activityDefs,
      ...exportImportDefs,
    ];
    
    const ALL_HANDLERS: Record<string, (args: Record<string, unknown>) => unknown> = {
      ...projectHandlers,
      ...epicHandlers,
      ...taskHandlers,
      ...subtaskHandlers,
      ...noteHandlers,
      ...commentHandlers,
      ...templateHandlers,
      ...dashboardHandlers,
      ...searchHandlers,
      ...activityHandlers,
      ...exportImportHandlers,
    };
  • Exports the handlers mapping, which maps 'project_create' to the handleProjectCreate function.
    export const handlers: Record<string, ToolHandler> = {
      project_create: handleProjectCreate,
      project_list: handleProjectList,
      project_update: handleProjectUpdate,
    };
  • The logActivity helper used by the handler to record the 'created' action in the activity_log table.
    export function logActivity(
      db: Database.Database,
      entityType: string,
      entityId: number,
      action: string,
      fieldName: string | null,
      oldValue: string | null,
      newValue: string | null,
      summary: string
    ): void {
      db.prepare(
        `INSERT INTO activity_log (entity_type, entity_id, action, field_name, old_value, new_value, summary)
         VALUES (?, ?, ?, ?, ?, ?, ?)`
      ).run(entityType, entityId, action, fieldName, oldValue, newValue, summary);
    }
Behavior3/5

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

Annotations already indicate this is a non-read-only, non-destructive operation. The description adds that projects are top-level containers, but does not disclose side effects, authentication needs, or rate limits. No contradiction with annotations.

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?

Two short sentences that are front-loaded with the action and provide a brief context. No unnecessary words or redundancy.

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?

Despite good annotations and schema, the description omits return value information (no output schema) and does not describe default behaviors for optional parameters like status. A more complete description would mention created project details.

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?

Input schema coverage is 100% with descriptions for all parameters. The description adds no additional parameter information beyond the schema, so baseline of 3 applies.

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' and the resource 'projects', and explains that projects are top-level containers. This distinguishes it from siblings like project_list and project_update.

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?

No guidance on when to use this tool versus alternatives like project_update or epic_create. The description does not mention prerequisites, context, or when not to use it.

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/spranab/saga-mcp'

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