Skip to main content
Glama

agentic_codegen_execute

Generate and test code automatically for GitHub issues using AI-driven development workflows. Analyzes issues, creates code, and prepares pull requests to streamline software development processes.

Instructions

CodeGenAgent実行 - AI駆動コード生成・テスト自動生成

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
descriptionYesタスク詳細
issue_numberYesGitHub Issue番号
priorityNo優先度
titleYesタスクタイトル

Implementation Reference

  • The handler function `handleCodeGenExecute` that implements the core logic of the tool by triggering the GitHub Actions workflow for the codegen agent using `gh workflow run agentic-system.yml -f agent=codegen`.
      private async handleCodeGenExecute(args: {
        issue_number: number;
        title: string;
        description: string;
        priority?: string;
      }) {
        try {
          // Trigger GitHub Actions workflow
          const { stdout } = await execAsync(
            `gh workflow run agentic-system.yml -f agent=codegen -f issue_number=${args.issue_number}`,
            { cwd: process.env.GITHUB_REPOSITORY_PATH || process.cwd() }
          );
    
          return {
            content: [
              {
                type: 'text',
                text: `## 🤖 CodeGenAgent起動
    
    **Issue**: #${args.issue_number}
    **Title**: ${args.title}
    **Priority**: ${args.priority || 'P2-中'}
    
    ✅ GitHub Actionsワークフローを起動しました
    
    進捗は Issue #${args.issue_number} で確認できます
    Workflow: https://github.com/${process.env.GITHUB_REPOSITORY}/actions`
              }
            ]
          };
        } catch (error) {
          return {
            content: [
              {
                type: 'text',
                text: `❌ エラー: ${error instanceof Error ? error.message : 'Unknown error'}\n\nGitHub CLIとワークフローファイルを確認してください`
              }
            ]
          };
        }
      }
  • The input schema defining the parameters for the agentic_codegen_execute tool: issue_number (number, required), title (string, required), description (string, required), priority (string enum, optional).
    inputSchema: {
      type: 'object',
      properties: {
        issue_number: {
          type: 'number',
          description: 'GitHub Issue番号'
        },
        title: {
          type: 'string',
          description: 'タスクタイトル'
        },
        description: {
          type: 'string',
          description: 'タスク詳細'
        },
        priority: {
          type: 'string',
          enum: ['P0-緊急', 'P1-高', 'P2-中', 'P3-低'],
          description: '優先度'
        }
      },
      required: ['issue_number', 'title', 'description']
    }
  • server.ts:40-66 (registration)
    The tool object registration in the TOOLS array used by the listTools handler.
    {
      name: 'agentic_codegen_execute',
      description: 'CodeGenAgent実行 - AI駆動コード生成・テスト自動生成',
      inputSchema: {
        type: 'object',
        properties: {
          issue_number: {
            type: 'number',
            description: 'GitHub Issue番号'
          },
          title: {
            type: 'string',
            description: 'タスクタイトル'
          },
          description: {
            type: 'string',
            description: 'タスク詳細'
          },
          priority: {
            type: 'string',
            enum: ['P0-緊急', 'P1-高', 'P2-中', 'P3-低'],
            description: '優先度'
          }
        },
        required: ['issue_number', 'title', 'description']
      }
    },
  • server.ts:226-227 (registration)
    The switch case dispatching calls to the agentic_codegen_execute tool to its handler function within the CallToolRequest handler.
    case 'agentic_codegen_execute':
      return await this.handleCodeGenExecute(args as any);
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions AI-driven code generation and test automation but doesn't specify what happens during execution (e.g., does it modify files, run tests, require specific permissions, or have rate limits?). For a tool that likely performs significant operations, this lack of detail is a notable gap.

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 very concise with a single phrase, which is efficient and front-loaded. However, it's arguably too brief for a tool with significant functionality, potentially under-specifying rather than being optimally concise. It could benefit from slightly more detail without becoming verbose.

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 AI-driven code generation and test automation, no annotations, and no output schema, the description is incomplete. It doesn't cover what the tool returns, error conditions, or behavioral aspects like side effects. For a tool with 4 parameters and likely substantial operations, this minimal description is inadequate.

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?

Schema description coverage is 100%, so the schema already documents all parameters (description, issue_number, priority, title). The description doesn't add any meaning beyond this, such as explaining how parameters interact (e.g., how issue_number relates to GitHub) or providing examples. Baseline 3 is appropriate when the schema handles parameter documentation adequately.

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 'CodeGenAgent実行 - AI駆動コード生成・テスト自動生成' states the tool executes AI-driven code generation and test automation, which is a clear purpose. However, it's somewhat vague about the specific verb ('実行' means execute/run) and doesn't explicitly distinguish this code generation tool from sibling tools like 'agentic_pr_create' or 'agentic_review_execute' that might also involve code-related operations.

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 prerequisites (like needing a GitHub issue), context for code generation tasks, or how it differs from sibling tools such as 'agentic_issue_analyze' or 'agentic_pr_create'. Users must infer usage from parameter names alone.

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/ShunsukeHayashi/agentic-mcp-server'

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