Skip to main content
Glama

start_task

Initiate tasks in Buildable projects by specifying a task ID, approach, duration, and notes. Integrates with AI assistants for efficient task management using the Model Context Protocol (MCP).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
approachNoOptional approach or strategy for the task
estimated_durationNoEstimated duration in minutes
notesNoOptional notes about the task
task_idYesThe ID of the task to start

Implementation Reference

  • MCP tool handler for 'start_task' that validates inputs, calls the BuildableMCPClient.startTask method, formats the response as MCP content, and handles client connection errors.
    async ({ task_id, approach, estimated_duration, notes }) => {
      if (!this.client) {
        throw new Error('Not connected to Buildable API');
      }
    
      const result = await this.client.startTask(task_id, {
        approach,
        estimated_duration,
        notes,
      });
    
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify(result, null, 2),
          },
        ],
      };
    }
  • src/cli.ts:58-92 (registration)
    Registration of the 'start_task' MCP tool on the McpServer instance, including name, Zod input schema, and handler function.
    this.server.tool(
      'start_task',
      {
        task_id: z.string().describe('The ID of the task to start'),
        approach: z
          .string()
          .optional()
          .describe('Optional approach or strategy for the task'),
        estimated_duration: z
          .number()
          .optional()
          .describe('Estimated duration in minutes'),
        notes: z.string().optional().describe('Optional notes about the task'),
      },
      async ({ task_id, approach, estimated_duration, notes }) => {
        if (!this.client) {
          throw new Error('Not connected to Buildable API');
        }
    
        const result = await this.client.startTask(task_id, {
          approach,
          estimated_duration,
          notes,
        });
    
        return {
          content: [
            {
              type: 'text',
              text: JSON.stringify(result, null, 2),
            },
          ],
        };
      }
    );
  • Zod schema defining input parameters for the 'start_task' tool: required task_id and optional approach, estimated_duration, notes.
    {
      task_id: z.string().describe('The ID of the task to start'),
      approach: z
        .string()
        .optional()
        .describe('Optional approach or strategy for the task'),
      estimated_duration: z
        .number()
        .optional()
        .describe('Estimated duration in minutes'),
      notes: z.string().optional().describe('Optional notes about the task'),
    },
  • BuildableMCPClient.startTask helper method that sends POST request to the Buildable API /tasks/{taskId}/start endpoint to start the task, updates connection status, and handles errors.
    async startTask(
      taskId: string,
      options: StartTaskOptions = {}
    ): Promise<StartTaskResponse> {
      this.log('debug', `Starting task ${taskId}...`);
    
      try {
        const response = await this.makeRequest<StartTaskResponse>(
          'POST',
          `/tasks/${taskId}/start`,
          {
            ai_assistant_id: this.aiAssistantId,
            estimated_time_minutes: options.estimated_duration,
            notes: options.notes,
            approach: options.approach,
          }
        );
    
        this.log('info', `Successfully started task ${taskId}`);
    
        // Update connection status to 'working'
        await this.updateConnectionStatus('working', taskId);
    
        return response.data!;
      } catch (error) {
        this.log('error', `Failed to start task ${taskId}:`, error);
        throw error;
      }
    }
  • TypeScript interfaces defining StartTaskOptions (input options for startTask) and StartTaskResponse (expected API response structure).
    export interface StartTaskOptions {
      approach?: string;
      estimated_duration?: number;
      notes?: string;
    }
    
    export interface StartTaskResponse {
      success: boolean;
      task_id: string;
      message: string;
      started_at: string;
      guidance?: {
        step_by_step: string[];
        key_considerations: string[];
        testing_requirements: string[];
        documentation_needs: string[];
      };
    }
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

Related 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/chunkydotdev/bldbl-mcp'

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