enhance_prompt_gemini

Improve AI prompts using Gemini API strategies like Few-Shot examples and structured formatting to increase response quality and clarity.

Instructions

Input Schema

TableJSON Schema

Name	Required	Description
`prompt`	Yes	The original prompt to enhance
`agent_role`	No	The role of the agent that will receive this prompt (e.g., "Specification Agent", "Planning Agent")
`strategies`	No	Specific Gemini strategies to apply. If not provided, all strategies will be applied.

Implementation Reference

src/tools/prompt/enhancePromptGemini.ts:47-123 (handler)

Main handler function implementing the enhance_prompt_gemini tool. Applies Gemini prompting strategies (few-shot, output-format, etc.) to enhance the input prompt, generates structured output with improvements.

export async function enhancePromptGemini(args: {
  prompt: string;
  agent_role?: string;
  strategies?: string[];
}): Promise<ToolResult> {
  const { prompt, agent_role, strategies } = args;

  const allStrategies = ['few-shot', 'output-format', 'context-placement', 'decomposition', 'parameters'];
  const strategiesToApply = strategies && strategies.length > 0 ? strategies : allStrategies;

  const enhancements: PromptEnhancement[] = [];

  // 1. Few-Shot Examples
  if (strategiesToApply.includes('few-shot')) {
    enhancements.push({
      strategy: 'Few-Shot 예시 추가',
      description: '2-3개의 고품질 예시를 추가하여 모델이 패턴을 학습하도록 유도',
      applied: addFewShotExamples(prompt, agent_role),
      improvement: '형식, 표현, 범위를 명확히 하여 일관성 향상'
    });
  }

  // 2. Output Format Specification
  if (strategiesToApply.includes('output-format')) {
    enhancements.push({
      strategy: '출력 형식 명시화',
      description: 'XML 태그나 마크다운 헤더로 구조화된 형식 지정',
      applied: specifyOutputFormat(prompt, agent_role),
      improvement: '원하는 응답 구조를 명확히 하여 파싱 용이성 향상'
    });
  }

  // 3. Context Placement
  if (strategiesToApply.includes('context-placement')) {
    enhancements.push({
      strategy: '컨텍스트 배치 최적화',
      description: '긴 컨텍스트를 특정 요청 전에 배치 (Gemini 3 최적화)',
      applied: optimizeContextPlacement(prompt),
      improvement: '모델이 컨텍스트를 더 효과적으로 활용'
    });
  }

  // 4. Prompt Decomposition
  if (strategiesToApply.includes('decomposition')) {
    enhancements.push({
      strategy: '프롬프트 분해',
      description: '복잡한 작업을 여러 단계로 분해하여 체인화',
      applied: decomposePrompt(prompt, agent_role),
      improvement: '각 단계의 출력 품질 향상, 디버깅 용이'
    });
  }

  // 5. Parameter Tuning Suggestions
  if (strategiesToApply.includes('parameters')) {
    enhancements.push({
      strategy: '매개변수 튜닝 제안',
      description: 'Temperature, Top-K, Top-P, Max Tokens 최적 값 제안',
      applied: suggestParameters(prompt, agent_role),
      improvement: '작업 유형에 맞는 모델 동작 최적화'
    });
  }

  const result = {
    original_prompt: prompt,
    agent_role: agent_role || 'Generic Agent',
    strategies_applied: strategiesToApply,
    enhancements,
    enhanced_prompt: combineEnhancements(prompt, enhancements),
    summary: generateSummary(enhancements)
  };

  const output = formatOutput(result);

  return {
    content: [{ type: 'text', text: output }]
  };
}

src/tools/prompt/enhancePromptGemini.ts:5-38 (schema)

ToolDefinition schema defining the input schema, description, and annotations for the enhance_prompt_gemini tool.

export const enhancePromptGeminiDefinition: ToolDefinition = {
  name: 'enhance_prompt_gemini',
  description: '프롬프트 개선|제미나이 전략|품질 향상|prompt enhancement|gemini strategies|quality improvement - Enhance prompts using Gemini API prompting strategies (Few-Shot, Output Format, Context)',
  inputSchema: {
    type: 'object',
    properties: {
      prompt: {
        type: 'string',
        description: 'The original prompt to enhance'
      },
      agent_role: {
        type: 'string',
        description: 'The role of the agent that will receive this prompt (e.g., "Specification Agent", "Planning Agent")'
      },
      strategies: {
        type: 'array',
        items: {
          type: 'string',
          enum: ['few-shot', 'output-format', 'context-placement', 'decomposition', 'parameters']
        },
        description: 'Specific Gemini strategies to apply. If not provided, all strategies will be applied.'
      }
    },
    required: ['prompt']
  },
  annotations: {
    title: 'Enhance Prompt (Gemini Strategies)',
    audience: ['user', 'assistant'],
    readOnlyHint: true,
    destructiveHint: false,
    idempotentHint: true,
    openWorldHint: false
  }
};

src/index.ts:155-212 (registration)

Registration of the tool handler in the toolHandlers object used for dynamic dispatch in callToolRequest handler.

const toolHandlers: Record<string, ToolHandler> = {
  // Time & UI
  'get_current_time': getCurrentTime,
  'preview_ui_ascii': previewUiAscii,

  // Memory - Basic
  'save_memory': saveMemory,
  'recall_memory': recallMemory,
  'update_memory': updateMemory,
  'delete_memory': deleteMemory,
  'list_memories': listMemories,
  'prioritize_memory': prioritizeMemory,

  // Memory - Graph (v2.0 NEW)
  'link_memories': linkMemories,
  'get_memory_graph': getMemoryGraph,
  'search_memories_advanced': searchMemoriesAdvanced,
  'create_memory_timeline': createMemoryTimeline,

  // Memory - Session Context (v2.1 NEW)
  'get_session_context': getSessionContext,

  // Code Analysis
  'find_symbol': findSymbol,
  'find_references': findReferences,
  'analyze_dependency_graph': analyzeDependencyGraph,

  // Code Quality
  'get_coding_guide': getCodingGuide,
  'apply_quality_rules': applyQualityRules,
  'validate_code_quality': validateCodeQuality,
  'analyze_complexity': analyzeComplexity,
  'check_coupling_cohesion': checkCouplingCohesion,
  'suggest_improvements': suggestImprovements,

  // Thinking
  'create_thinking_chain': createThinkingChain,
  'analyze_problem': analyzeProblem,
  'step_by_step_analysis': stepByStepAnalysis,
  'format_as_plan': formatAsPlan,

  // Planning
  'generate_prd': generatePrd,
  'create_user_stories': createUserStories,
  'analyze_requirements': analyzeRequirements,
  'feature_roadmap': featureRoadmap,

  // Prompt
  'enhance_prompt': enhancePrompt,
  'analyze_prompt': analyzePrompt,
  'enhance_prompt_gemini': enhancePromptGemini,

  // Reasoning
  'apply_reasoning_framework': applyReasoningFramework,

  // Analytics (v2.0 NEW)
  'get_usage_analytics': getUsageAnalytics
};

src/index.ts:88-145 (registration)

Registration of the tool definition in the tools array returned by listToolsRequest handler.

const tools = [
  // Core Utilities (2)
  getCurrentTimeDefinition,
  previewUiAsciiDefinition,

  // Memory Management - Basic (6)
  saveMemoryDefinition,
  recallMemoryDefinition,
  updateMemoryDefinition,
  deleteMemoryDefinition,
  listMemoriesDefinition,
  prioritizeMemoryDefinition,

  // Memory Management - Graph (4) - v2.0 NEW
  linkMemoriesDefinition,
  getMemoryGraphDefinition,
  searchMemoriesAdvancedDefinition,
  createMemoryTimelineDefinition,

  // Memory Management - Session Context (1) - v2.1 NEW
  getSessionContextDefinition,

  // Code Analysis - Semantic (2)
  findSymbolDefinition,
  findReferencesDefinition,

  // Code Analysis - Advanced (1) - v2.0 NEW
  analyzeDependencyGraphDefinition,

  // Code Quality (6)
  getCodingGuideDefinition,
  applyQualityRulesDefinition,
  validateCodeQualityDefinition,
  analyzeComplexityDefinition,
  checkCouplingCohesionDefinition,
  suggestImprovementsDefinition,

  // Thinking & Planning (8)
  createThinkingChainDefinition,
  analyzeProblemDefinition,
  stepByStepAnalysisDefinition,
  formatAsPlanDefinition,
  generatePrdDefinition,
  createUserStoriesDefinition,
  analyzeRequirementsDefinition,
  featureRoadmapDefinition,

  // Prompt Engineering (3)
  enhancePromptDefinition,
  analyzePromptDefinition,
  enhancePromptGeminiDefinition,

  // Reasoning (1)
  applyReasoningFrameworkDefinition,

  // Analytics (1) - v2.0 NEW
  getUsageAnalyticsDefinition
];

src/tools/prompt/enhancePromptGemini.ts:123-125 (helper)
Supporting helper functions that implement individual Gemini strategies and format the final output.
```
}

// Helper methods
```

Hi-AI