Skip to main content
Glama

kb_onboard

Collect initial user information through interactive onboarding questions to build a knowledge base for AI context across sessions.

Instructions

Start interactive onboarding to collect initial information. Returns questions for the specified category.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
categoryNoCategory of questions to askall

Implementation Reference

  • Main handler for kb_onboard tool execution. Determines the onboarding category, fetches corresponding questions from onboardingForms, and returns a structured JSON response with the questions.
    case 'kb_onboard': {
      const category = (args as any).category || 'all';
      let questions: any[] = [];
      
      if (category === 'all') {
        questions = [
          ...onboardingForms.initial,
          ...onboardingForms.professional,
          ...onboardingForms.preferences,
          ...onboardingForms.projects
        ];
      } else if (onboardingForms[category as keyof typeof onboardingForms]) {
        questions = onboardingForms[category as keyof typeof onboardingForms];
      }
    
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify({
              category,
              totalQuestions: questions.length,
              questions: questions.map(q => ({
                id: q.id,
                question: q.question,
                type: q.type,
                field: q.field,
                required: q.required,
                options: q.options
              }))
            }, null, 2)
          }
        ]
      };
    }
  • Tool schema definition including name, description, and inputSchema specifying the optional 'category' parameter.
    {
      name: 'kb_onboard',
      description: 'Start interactive onboarding to collect initial information. Returns questions for the specified category.',
      inputSchema: {
        type: 'object',
        properties: {
          category: {
            type: 'string',
            enum: ['initial', 'professional', 'preferences', 'projects', 'all'],
            description: 'Category of questions to ask',
            default: 'all'
          }
        }
      }
    },
  • Data structure defining all onboarding questions used by the kb_onboard handler for interactive user onboarding.
    export const onboardingForms: Record<string, OnboardingQuestion[]> = {
      initial: [
        {
          id: 'personal_name',
          question: 'What is your full name?',
          category: 'personal',
          field: 'name',
          type: 'text',
          required: true
        },
        {
          id: 'personal_birth_year',
          question: 'What year were you born?',
          category: 'personal',
          field: 'birthYear',
          type: 'number',
          required: false
        },
        {
          id: 'personal_location',
          question: 'Where are you currently located? (City, Country)',
          category: 'personal',
          field: 'currentLocation',
          type: 'text',
          required: false
        },
        {
          id: 'personal_languages',
          question: 'What languages do you speak? (comma-separated)',
          category: 'personal',
          field: 'languages',
          type: 'multiselect',
          required: false
        },
        {
          id: 'personal_pronouns',
          question: 'What are your pronouns?',
          category: 'personal',
          field: 'pronouns',
          type: 'text',
          required: false
        }
      ],
      professional: [
        {
          id: 'prof_occupation',
          question: 'What is your occupation/job title?',
          category: 'professional',
          field: 'occupation',
          type: 'text',
          required: true
        },
        {
          id: 'prof_experience',
          question: 'How many years of experience do you have?',
          category: 'professional',
          field: 'yearsOfExperience',
          type: 'number',
          required: false
        },
        {
          id: 'prof_industry',
          question: 'What industry do you work in?',
          category: 'professional',
          field: 'industry',
          type: 'text',
          required: false
        },
        {
          id: 'prof_specializations',
          question: 'What are your specializations? (comma-separated)',
          category: 'professional',
          field: 'specializations',
          type: 'multiselect',
          required: false
        },
        {
          id: 'prof_skills',
          question: 'What are your main technical skills? (comma-separated)',
          category: 'professional',
          field: 'skills',
          type: 'multiselect',
          required: false
        }
      ],
      preferences: [
        {
          id: 'pref_communication',
          question: 'How do you prefer communication? (formal/casual/technical)',
          category: 'preferences',
          field: 'communicationStyle',
          type: 'select',
          options: ['formal', 'casual', 'technical', 'balanced'],
          required: false
        },
        {
          id: 'pref_detail',
          question: 'How detailed should responses be?',
          category: 'preferences',
          field: 'responseDetail',
          type: 'select',
          options: ['concise', 'detailed', 'balanced'],
          required: false
        },
        {
          id: 'pref_technical',
          question: 'What is your technical expertise level?',
          category: 'preferences',
          field: 'technicalLevel',
          type: 'select',
          options: ['beginner', 'intermediate', 'expert'],
          required: false
        }
      ],
      projects: [
        {
          id: 'proj_current',
          question: 'What projects are you currently working on? (comma-separated)',
          category: 'projects',
          field: 'currentProjects',
          type: 'multiselect',
          required: false
        },
        {
          id: 'proj_tech',
          question: 'What technologies are you using? (comma-separated)',
          category: 'projects',
          field: 'technologies',
          type: 'multiselect',
          required: false
        },
        {
          id: 'proj_goals',
          question: 'What are your current goals? (comma-separated)',
          category: 'projects',
          field: 'goals',
          type: 'multiselect',
          required: false
        }
      ]
    };
  • src/index.ts:422-425 (registration)
    Registers the listTools capability which exposes the kb_onboard schema to MCP clients.
    // Handler for listing tools
    server.setRequestHandler(ListToolsRequestSchema, async () => {
      return { tools };
    });
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 states the tool 'Returns questions for the specified category,' which implies a read-only, non-destructive operation, but lacks details on interactivity (e.g., user prompts, session handling), response format, or potential side effects. This is inadequate for a tool that initiates an interactive 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 highly concise and front-loaded, consisting of two clear sentences that directly state the tool's purpose and output. There's no wasted language or redundancy, making it efficient and easy to parse for an AI agent.

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 complexity (interactive onboarding with no output schema) and lack of annotations, the description is incomplete. It doesn't explain the interactive nature (e.g., how questions are presented or answered), return format, or how it integrates with other tools like kb_update_* for storing responses. This leaves significant gaps for agent understanding.

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?

The description mentions 'specified category,' aligning with the single parameter 'category' in the input schema. With 100% schema description coverage, the schema fully documents the parameter's enum values and default. The description adds minimal semantic context (e.g., that categories relate to 'questions to ask'), but doesn't elaborate beyond what the schema provides, meeting the baseline of 3.

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 verb ('Start interactive onboarding') and resource ('collect initial information'), specifying what the tool does. It distinguishes from siblings like kb_quick_setup or mcp_instruct_onboarding by focusing on question collection rather than setup or instruction. However, it doesn't explicitly differentiate from all siblings (e.g., kb_get_* tools), keeping it at 4 rather than 5.

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 when to choose it over siblings like kb_quick_setup for setup, kb_get_* tools for retrieving information, or mcp_instruct_onboarding for instruction. There's no context on prerequisites, timing, or exclusions, leaving usage unclear.

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/hlsitechio/mcp-instruct'

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