Skip to main content
Glama

brainstorm

Generate creative ideas using structured frameworks like SCAMPER and Design Thinking, with domain-specific context and feasibility analysis for practical solutions.

Instructions

Generate novel ideas with dynamic context gathering. --> Creative frameworks (SCAMPER, Design Thinking, etc.), domain context integration, idea clustering, feasibility analysis, and iterative refinement.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesPrimary brainstorming challenge or question to explore
modelNoOptional model to use (e.g., 'gemini-2.5-flash'). If not specified, uses the default model (gemini-2.5-pro).
methodologyNoBrainstorming framework: 'divergent' (generate many ideas), 'convergent' (refine existing), 'scamper' (systematic triggers), 'design-thinking' (human-centered), 'lateral' (unexpected connections), 'auto' (AI selects best)auto
domainNoDomain context for specialized brainstorming (e.g., 'software', 'business', 'creative', 'research', 'product', 'marketing')
constraintsNoKnown limitations, requirements, or boundaries (budget, time, technical, legal, etc.)
existingContextNoBackground information, previous attempts, or current state to build upon
ideaCountNoTarget number of ideas to generate (default: 10-15)
includeAnalysisNoInclude feasibility, impact, and implementation analysis for generated ideas

Implementation Reference

  • The main handler function for the 'brainstorm' tool. It processes arguments, builds an enhanced prompt using helper functions, logs debug info, reports progress, and executes the Gemini CLI.
    execute: async (args, onProgress) => {
      const {
        prompt,
        model,
        methodology = 'auto',
        domain,
        constraints,
        existingContext,
        ideaCount = 12,
        includeAnalysis = true
      } = args;
    
      if (!prompt?.trim()) {
        throw new Error("You must provide a valid brainstorming challenge or question to explore");
      }
    
      let enhancedPrompt = buildBrainstormPrompt({
        prompt: prompt.trim() as string,
        methodology: methodology as string,
        domain: domain as string | undefined,
        constraints: constraints as string | undefined,
        existingContext: existingContext as string | undefined,
        ideaCount: ideaCount as number,
        includeAnalysis: includeAnalysis as boolean
      });
    
      Logger.debug(`Brainstorm: Using methodology '${methodology}' for domain '${domain || 'general'}'`);
      
      // Report progress to user
      onProgress?.(`Generating ${ideaCount} ideas via ${methodology} methodology...`);
      
      // Execute with Gemini
      return await executeGeminiCLI(enhancedPrompt, model as string | undefined, false, false, onProgress);
    }
  • Zod schema defining the input parameters and validation for the brainstorm tool.
    const brainstormArgsSchema = z.object({
      prompt: z.string().min(1).describe("Primary brainstorming challenge or question to explore"),
      model: z.string().optional().describe("Optional model to use (e.g., 'gemini-2.5-flash'). If not specified, uses the default model (gemini-2.5-pro)."),
      methodology: z.enum(['divergent', 'convergent', 'scamper', 'design-thinking', 'lateral', 'auto']).default('auto').describe("Brainstorming framework: 'divergent' (generate many ideas), 'convergent' (refine existing), 'scamper' (systematic triggers), 'design-thinking' (human-centered), 'lateral' (unexpected connections), 'auto' (AI selects best)"),
      domain: z.string().optional().describe("Domain context for specialized brainstorming (e.g., 'software', 'business', 'creative', 'research', 'product', 'marketing')"),
      constraints: z.string().optional().describe("Known limitations, requirements, or boundaries (budget, time, technical, legal, etc.)"),
      existingContext: z.string().optional().describe("Background information, previous attempts, or current state to build upon"),
      ideaCount: z.number().int().positive().default(12).describe("Target number of ideas to generate (default: 10-15)"),
      includeAnalysis: z.boolean().default(true).describe("Include feasibility, impact, and implementation analysis for generated ideas"),
    });
  • The brainstormTool is registered by being pushed into the toolRegistry array alongside other tools.
    toolRegistry.push(
      askGeminiTool,
      pingTool,
      helpTool,
      brainstormTool,
      fetchChunkTool,
      timeoutTestTool
    );
  • Key helper function that constructs the detailed, structured prompt for the brainstorming session using the provided configuration and methodology-specific instructions.
    function buildBrainstormPrompt(config: {
      prompt: string;
      methodology: string;
      domain?: string;
      constraints?: string;
      existingContext?: string;
      ideaCount: number;
      includeAnalysis: boolean;
    }): string {
      const { prompt, methodology, domain, constraints, existingContext, ideaCount, includeAnalysis } = config;
      
      // Select methodology framework
      let frameworkInstructions = getMethodologyInstructions(methodology, domain);
      
      let enhancedPrompt = `# BRAINSTORMING SESSION
    
    ## Core Challenge
    ${prompt}
    
    ## Methodology Framework
    ${frameworkInstructions}
    
    ## Context Engineering
    *Use the following context to inform your reasoning:*
    ${domain ? `**Domain Focus:** ${domain} - Apply domain-specific knowledge, terminology, and best practices.` : ''}
    ${constraints ? `**Constraints & Boundaries:** ${constraints}` : ''}
    ${existingContext ? `**Background Context:** ${existingContext}` : ''}
    
    ## Output Requirements
    - Generate ${ideaCount} distinct, creative ideas
    - Each idea should be unique and non-obvious
    - Focus on actionable, implementable concepts
    - Use clear, descriptive naming
    - Provide brief explanations for each idea
    
    ${includeAnalysis ? `
    ## Analysis Framework
    For each idea, provide:
    - **Feasibility:** Implementation difficulty (1-5 scale)
    - **Impact:** Potential value/benefit (1-5 scale)
    - **Innovation:** Uniqueness/creativity (1-5 scale)
    - **Quick Assessment:** One-sentence evaluation
    ` : ''}
    
    ## Format
    Present ideas in a structured format:
    
    ### Idea [N]: [Creative Name]
    **Description:** [2-3 sentence explanation]
    ${includeAnalysis ? '**Feasibility:** [1-5] | **Impact:** [1-5] | **Innovation:** [1-5]\n**Assessment:** [Brief evaluation]' : ''}
    
    ---
    
    **Before finalizing, review the list: remove near-duplicates and ensure each idea satisfies the constraints.**
    
    Begin brainstorming session:`;
    
      return enhancedPrompt;
    }
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. While it mentions 'dynamic context gathering' and lists capabilities like 'feasibility analysis' and 'iterative refinement,' it doesn't describe what the tool actually returns, how it handles the brainstorming process, whether it makes external API calls, or any performance characteristics. For a complex 8-parameter tool with no annotations, this is insufficient behavioral transparency.

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

Conciseness3/5

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

The description is relatively concise with two sentences, but the second sentence is a dense list of capabilities that could be better structured. The information is front-loaded with the core purpose, but the bullet-like list format in a single sentence reduces readability. Every element in the description serves a purpose, but the structure could be improved for clarity.

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 brainstorming tool with 8 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns (structured ideas, analysis format, etc.), how the different methodologies affect output, or provide examples of typical use cases. The description mentions capabilities but doesn't give enough context for an agent to understand the full behavioral scope of this sophisticated 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 8 parameters thoroughly. The description adds some context about 'dynamic context gathering' which relates to parameters like 'existingContext' and 'domain,' and mentions 'feasibility analysis' which relates to 'includeAnalysis.' However, it doesn't provide significant additional semantic meaning beyond what's already in the well-documented schema parameters.

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 purpose as 'Generate novel ideas with dynamic context gathering' which is a specific verb+resource combination. It distinguishes from sibling tools like 'ask-gemini' or 'fetch-chunk' by focusing specifically on idea generation rather than general querying or data retrieval. However, it doesn't explicitly contrast with these alternatives in the description text itself.

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 lists capabilities like 'Creative frameworks (SCAMPER, Design Thinking, etc.), domain context integration, idea clustering, feasibility analysis, and iterative refinement' but provides no explicit guidance on when to use this tool versus alternatives. There's no mention of when this tool is appropriate versus 'ask-gemini' for general questions or other sibling tools. The list of features implies usage scenarios but doesn't provide clear selection criteria.

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/jamubc/gemini-mcp-tool'

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