Skip to main content
Glama
neriousy
by neriousy

gemini-consult

Consult Gemini for assistance when Claude needs help, additional context, or is stuck on a problem.

Instructions

Consult with Gemini when Claude needs help, additional context, or is stuck on a problem

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
questionYes
currentContextNo

Implementation Reference

  • The GeminiClient.consult() method that executes the tool logic for gemini-consult. It builds a prompt using the CONSULT template and runs the gemini CLI command with the gemini-2.5-flash model.
    async consult(question: string, currentContext?: string): Promise<string> {
      const prompt = PROMPTS.CONSULT.template(question, currentContext);
      return this.executeCommand('gemini-2.5-flash', prompt);
    }
  • The ToolConfig schema definition for gemini-consult, defining its name, description, model (gemini-2.5-flash), parameters (question required, currentContext optional), and Claude command configuration.
    'gemini-consult': {
      name: 'gemini-consult',
      description: 'Consult with Gemini when Claude needs help, additional context, or is stuck on a problem',
      promptKey: 'CONSULT',
      model: 'gemini-2.5-flash',
      parameters: {
        question: {
          schema: z.string(),
          description: 'The question, problem, or situation where Claude needs help or additional context',
          required: true,
        },
        currentContext: {
          schema: z.string().optional(),
          description: 'Current context about what Claude is working on, error messages, or relevant code',
          required: false,
        },
      },
      command: {
        name: 'consult',
        description: 'Get quick development guidance and advice from Gemini. Use this when you need architectural advice, best practices, or are stuck on a problem. Gemini will provide high-level guidance without code snippets.',
        usage: '/consult <question or problem>',
        example: '/consult What\'s the best way to handle form validation in React with TypeScript?',
        parameterMapping: {
          question: '{{arg1}}',
          currentContext: '{{@.}}',
        },
      },
    },
  • src/server.ts:35-40 (registration)
    The routing case in server.ts that registers the gemini-consult tool handler. When the tool name matches 'gemini-consult', it routes to geminiClient.consult() with question and currentContext params.
    case 'gemini-consult':
      response = await geminiClient.consult(
        params.question as string,
        params.currentContext as string | undefined
      );
      break;
  • The CONSULT prompt template used by gemini-consult. It instructs Gemini to provide development guidance (no code), structured with Understanding, Guidance, Approach Options, and Next Steps sections.
      CONSULT: {
        systemContext: GEMINI_ROLE,
        template: (question: string, currentContext?: string) => `Provide development guidance for this question:
    
    **Question**: ${question}
    
    ${currentContext ? `**Current Context**: ${currentContext}\n` : ''}
    
    IMPORTANT CONSTRAINTS:
    - DO NOT provide code snippets or implementations
    - DO NOT suggest specific code changes
    - ONLY provide conceptual guidance and best practices
    
    OUTPUT FORMAT - Structure your response with:
    
    ## Understanding
    - Clarify the core challenge
    - Identify key considerations
    
    ## Guidance
    - Best practices for this scenario
    - Common patterns to consider
    - Pitfalls to avoid
    
    ## Approach Options
    - Different ways to tackle this
    - Trade-offs for each approach
    
    ## Next Steps
    - How to proceed (conceptually)
    - What to research or validate
    - Key decisions to make
    
    Keep advice practical but high-level. NO CODE.`,
      },
Behavior2/5

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

No annotations are provided, so the description must fully disclose behavioral traits. It only states to 'consult with Gemini' without detailing what that entails (e.g., API call, latency, potential for hallucination, or any side effects). The lack of transparency is a significant gap.

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 a single sentence and concisely states the purpose, but it is too brief. Important details are omitted, which harms clarity. Conciseness should not sacrifice completeness; this does not earn a higher score.

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 tool's simplicity (two parameters, no output schema), the description is incomplete. It fails to explain what the response will be, any limitations of Gemini, or how to frame the question. The sibling tools suggest a broader set of AI assist capabilities, but this description lacks adequate context for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, yet the description adds no meaning beyond the schema. It does not explain what the 'question' parameter should contain (e.g., a natural language query) or how 'currentContext' should be used. The agent receives minimal guidance on parameter usage.

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 purpose: to consult Gemini when Claude needs help. It uses a specific verb 'consult' and resource 'Gemini', and provides context (when stuck, needs context). It distinguishes from siblings like explain-concept or debug-assist by being a general consultation rather than a specific analysis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says when to use: when Claude needs help, additional context, or is stuck. This is clear usage context. However, it does not mention when not to use nor provide alternatives, missing some negative guidance.

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/neriousy/gemini-mcp'

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