Skip to main content
Glama
kevinlin

Spec-driven Development MCP Server

by kevinlin

spec_coding_execute_start

Start task execution phase with guidance for implementing features in spec-driven development workflows, using session and feature identifiers to proceed with structured coding tasks.

Instructions

Start the task execution phase and provide guidance for task execution

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
session_idYesSession identifier
feature_nameYesFeature name
task_idNoOptional: Specify the task ID to execute; if not specified, the next unfinished task will be executed

Implementation Reference

  • The main handler function `executeStart` that implements the logic for the `spec_coding_execute_start` tool. It generates execution guidance using a template.
    export async function executeStart(
      params: ExecuteStartParams
    ): Promise<string> {
      const { session_id, feature_name, task_id = 'next_uncompleted' } = params;
      console.error(`[MCP] Starting execution for feature: ${feature_name}, task: ${task_id}`);
      
      // 使用 execute-task.md 模板
      const template = await readTemplate('execute-task.md', {
        feature_name,
        session_id,
        task_id
      });
      
      return `# ⚙️ Task Execution Stage (5/5)
    
    ## Feature: ${feature_name}
    
    Congratulations! Now entering the final execution stage. Based on the completed requirements, design, and task planning, let's start executing development tasks one by one.
    
    ### Workflow Progress:
    - [x] 1. Goal Collection ✅
    - [x] 2. Requirements Gathering ✅
    - [x] 3. Design Documentation ✅
    - [x] 4. Task Planning ✅
    - [x] 5. **Task Execution** ← Current Stage
    
    ---
    
    ${template}
    
    ---
    
    **Session Information**:
    - Session ID: \`${session_id}\`
    - Feature Name: \`${feature_name}\`
    - Current Task: \`${task_id}\`
    - All Documents: ✅ Completed
    
    Now please start executing the development tasks!`;
    }
  • The tool specification including name, description, and input schema for `spec_coding_execute_start`, used for listing and validation.
    {
      name: 'spec_coding_execute_start',
      description: 'Start the task execution phase and provide guidance for task execution',
      inputSchema: {
        type: 'object',
        properties: {
          session_id: { 
            type: 'string', 
            description: 'Session identifier' 
          },
          feature_name: { 
            type: 'string', 
            description: 'Feature name' 
          },
          task_id: { 
            type: 'string', 
            description: 'Optional: Specify the task ID to execute; if not specified, the next unfinished task will be executed' 
          }
        },
        required: ['session_id', 'feature_name']
      }
    }
  • src/server.ts:239-241 (registration)
    The switch case in the CallToolRequest handler that registers and dispatches to the `executeStart` function for `spec_coding_execute_start`.
    case 'spec_coding_execute_start':
      result = await executeStart(args as any);
      break;
  • TypeScript interface defining the input parameters for the handler, matching the tool's input schema.
    export interface ExecuteStartParams {
      session_id: string;
      feature_name: string;
      task_id?: string;
    }
  • src/server.ts:14-14 (registration)
    Import statement registering the `executeStart` handler function.
    import { executeStart } from './tools/execute.js';
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'start the task execution phase' and 'provide guidance,' but fails to detail critical aspects such as what 'guidance' entails (e.g., is it instructional output, a status update, or something else?), whether this operation is read-only or mutative, potential side effects, or any permissions or rate limits. This lack of information makes it difficult for an agent to understand the tool's behavior beyond a basic action.

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

Conciseness4/5

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

The description is concise, consisting of a single sentence that directly states the tool's action. It's front-loaded with the core purpose, though it could be more specific. There's no unnecessary verbiage, making it efficient in length, but the vagueness slightly reduces its effectiveness.

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?

Given the complexity implied by starting an execution phase and providing guidance, along with no annotations and no output schema, the description is incomplete. It doesn't explain what 'guidance' means in terms of output, potential errors, or behavioral traits. For a tool that likely involves a multi-step process (as suggested by sibling names), more context is needed to help the agent use it correctly.

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?

The input schema has 100% description coverage, with clear documentation for each parameter (session_id, feature_name, task_id). The description adds no additional meaning beyond the schema, as it doesn't explain how these parameters relate to 'starting the task execution phase' or 'providing guidance.' Given the high schema coverage, a baseline score of 3 is appropriate, as the schema adequately covers parameter semantics without extra description input.

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

Purpose3/5

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

The description states the tool 'Start[s] the task execution phase and provide[s] guidance for task execution,' which indicates a purpose involving initiating execution and offering guidance. However, it's somewhat vague—'task execution phase' lacks specificity about what exactly is executed, and 'provide guidance' is ambiguous about the nature of that guidance. It doesn't clearly distinguish this tool from its siblings, such as 'spec_coding_tasks_start' or 'spec_coding_workflow_start,' which might also involve starting phases.

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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention any prerequisites, context, or exclusions, nor does it reference sibling tools like 'spec_coding_tasks_start' or 'spec_coding_workflow_start' to help differentiate usage. This leaves the agent without clear direction on when this specific tool is appropriate.

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/kevinlin/spec-coding-mcp'

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