Skip to main content
Glama
emmron
by emmron

mcp__gemini__thinkdeep_enhanced

Analyze complex problems with enhanced AI reasoning, validate logical steps, ensure consistency, and track progress for accurate solutions across specialized domains.

Instructions

Extended AI reasoning with step validation, logical consistency checking, and progress tracking

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
domainNoProblem domain for specialized reasoning
problemYesComplex problem to analyze
thinking_depthNoDepth leveldeep
validate_stepsNoEnable step validation

Implementation Reference

  • The core handler function implementing the enhanced deep thinking tool. It constructs a detailed multi-step reasoning prompt based on input parameters (problem, depth, validation, domain), calls the AI analysis model, optionally performs a validation review, formats the output with emojis and sections, and includes performance monitoring.
        handler: async (args) => {
          const { problem, thinking_depth = 'deep', validate_steps = true, domain = 'general' } = args;
          validateString(problem, 'problem');
          
          const timer = performanceMonitor.startTimer('thinkdeep_enhanced');
          
          const depthLevels = {
            shallow: 3,
            medium: 5,
            deep: 7,
            profound: 10
          };
          
          const steps = depthLevels[thinking_depth] || 7;
          
          let prompt = `As an expert in ${domain}, think deeply about this problem through ${steps} progressive steps:
    
    Problem: ${problem}
    
    Approach this systematically:
    1. Problem decomposition and understanding
    2. Context analysis and assumptions
    3. Multiple solution approaches
    4. Logical reasoning and validation
    5. Potential obstacles and mitigations`;
    
          if (steps > 5) {
            prompt += `
    6. Alternative perspectives and counterarguments
    7. Synthesis and final reasoning`;
          }
          
          if (steps > 7) {
            prompt += `
    8. Edge cases and boundary conditions
    9. Implementation considerations
    10. Long-term implications and consequences`;
          }
          
          prompt += `
    
    For each step, provide:
    - Clear reasoning
    - Supporting evidence or logic
    - Potential weaknesses or gaps
    - Connection to previous steps
    
    ${validate_steps ? 'IMPORTANT: Validate each step before proceeding to the next.' : ''}
    
    End with a comprehensive synthesis of your deep thinking process.`;
    
          const analysis = await aiClient.call(prompt, 'analysis', { 
            complexity: 'complex',
            maxTokens: 4000
          });
          
          let result = `🧠 **Enhanced Deep Thinking** (${thinking_depth} - ${steps} steps)
    
    **Domain**: ${domain}
    **Validation**: ${validate_steps ? 'Enabled' : 'Disabled'}
    
    ${analysis}`;
    
          // If validation is enabled, run a consistency check
          if (validate_steps) {
            const validationPrompt = `Review this deep thinking analysis for logical consistency, gaps, and potential improvements:
    
    ${analysis}
    
    Provide:
    1. Logical consistency assessment (1-10 scale)
    2. Identified gaps or weaknesses
    3. Suggestions for improvement
    4. Overall quality score`;
    
            const validation = await aiClient.call(validationPrompt, 'review');
            
            result += `
    
    ---
    
    🔍 **Validation Report**
    
    ${validation}`;
          }
          
          timer.end();
          return result;
        }
  • The input schema defining parameters for the tool: problem (required string), thinking_depth (string default 'deep'), validate_steps (boolean default true), domain (string). Used by the registry to generate JSON schema.
    parameters: {
      problem: { type: 'string', description: 'Complex problem to analyze', required: true },
      thinking_depth: { type: 'string', description: 'Depth level', default: 'deep' },
      validate_steps: { type: 'boolean', description: 'Enable step validation', default: true },
      domain: { type: 'string', description: 'Problem domain for specialized reasoning' }
    },
  • The registerToolsFromModule method that iterates over the enhancedTools object (imported at line 7) and registers each tool including 'mcp__gemini__thinkdeep_enhanced' via registerTool. Called at line 237 for enhancedTools.
    registerToolsFromModule(toolsModule) {
      Object.entries(toolsModule).forEach(([name, tool]) => {
        this.registerTool(name, tool.description, tool.parameters, tool.handler);
      });
    }
  • Specific call that registers the enhancedTools module, including the target tool.
    this.registerToolsFromModule(enhancedTools);
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions 'step validation, logical consistency checking, and progress tracking' which gives some behavioral context, but doesn't address critical aspects like whether this is a read-only operation, what the output format might be, computational requirements, or potential limitations of the extended reasoning process.

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?

The description is extremely concise - a single phrase listing key capabilities. It's front-loaded with the core purpose and wastes no words. Every element ('extended AI reasoning', 'step validation', etc.) earns its place by specifying distinct functionality.

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?

For a complex reasoning tool with 4 parameters and no output schema, the description is insufficient. It doesn't explain what 'extended AI reasoning' means in practice, what format the reasoning output takes, how progress tracking manifests, or what constitutes successful validation. Without annotations or output schema, users lack critical information about what to expect from this tool.

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 4 parameters thoroughly. The description doesn't add any meaningful parameter semantics beyond what's in the schema - it doesn't explain how parameters like 'domain' or 'thinking_depth' affect the extended reasoning process, nor does it provide examples of valid values.

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

Purpose4/5

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

The description clearly states the tool's function as 'extended AI reasoning' with specific capabilities like step validation, logical consistency checking, and progress tracking. It uses a specific verb ('reasoning') and resource ('AI'), but doesn't explicitly distinguish it from sibling tools like 'mcp__gemini__ai_chat' or 'mcp__gemini__consensus_advanced' which might also involve reasoning.

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 what makes it different from other reasoning/analysis tools in the sibling list, nor does it specify appropriate contexts or prerequisites for its use.

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/emmron/gemini-mcp'

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