Skip to main content
Glama

summarizeWhiteboard

Generate concise summaries of Heptabase whiteboards in text or structured formats, optionally including statistics, to streamline information extraction and analysis.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
formatNotext
includeStatisticsNo
whiteboardIdYes

Implementation Reference

  • Main handler function for the summarizeWhiteboard tool. Fetches whiteboard data and generates summary based on format.
    export async function summarizeWhiteboard(
      dataService: HeptabaseDataService,
      params: z.infer<typeof summarizeWhiteboardSchema>
    ) {
      const data = await dataService.getWhiteboard(params.whiteboardId, {
        includeCards: true,
        includeConnections: true
      });
    
      let summary = '';
      
      if (params.format === 'text') {
        summary = await generateTextSummary(data, params);
      } else {
        summary = await generateStructuredSummary(data, params);
      }
    
      return {
        content: [{
          type: 'text',
          text: summary
        }]
      };
    }
  • Zod schema defining input parameters for the summarizeWhiteboard tool.
    export const summarizeWhiteboardSchema = z.object({
      whiteboardId: z.string(),
      format: z.enum(['text', 'structured']).optional().default('text'),
      includeStatistics: z.boolean().optional().default(false)
    });
  • src/server.ts:684-694 (registration)
    Registers the summarizeWhiteboard tool with the MCP server, including schema and wrapper handler that ensures data service initialization.
    this.tools.summarizeWhiteboard = {
      inputSchema: summarizeWhiteboardSchema,
      handler: async (params) => {
        await this.ensureDataServiceInitialized();
        return summarizeWhiteboard(this.dataService, params);
      }
    };
    
    this.server.tool('summarizeWhiteboard', summarizeWhiteboardSchema.shape, async (params: z.infer<typeof summarizeWhiteboardSchema>) => {
      return this.tools.summarizeWhiteboard.handler(params);
    });
  • Helper function to generate text summary of whiteboard, used by the main handler.
    }
    
    async function generateMarkdownExport(data: any, params: any): Promise<string> {
      const lines: string[] = [];
      
      lines.push(`# ${data.whiteboard.name}`);
      lines.push('');
      
      if (params.includeMetadata) {
        lines.push('## Metadata');
        lines.push(`- Created: ${data.whiteboard.createdTime}`);
        lines.push(`- Last Modified: ${data.whiteboard.lastEditedTime}`);
        lines.push(`- Created By: ${data.whiteboard.createdBy}`);
        lines.push('');
      }
      
      if (data.cards?.length > 0) {
        lines.push('## Cards');
        lines.push('');
        
        for (const card of data.cards) {
          lines.push(`### ${card.title}`);
          
          const content = JSON.parse(card.content);
          const text = extractTextFromContent(content);
          lines.push(text);
          lines.push('');
        }
      }
      
      if (data.connections?.length > 0) {
        lines.push('## Connections');
        lines.push('');
        
        for (const connection of data.connections) {
          lines.push(`- ${connection.beginId} → ${connection.endId}`);
        }
        lines.push('');
      }
      
      return lines.join('\n');
    }
    
    async function generateHtmlExport(data: any, params: any): Promise<string> {
      const lines: string[] = [];
      
      lines.push('<!DOCTYPE html>');
      lines.push('<html>');
      lines.push('<head>');
      lines.push(`<title>${data.whiteboard.name}</title>`);
      lines.push('</head>');
      lines.push('<body>');
      lines.push(`<h1>${data.whiteboard.name}</h1>`);
      
      if (params.includeMetadata) {
        lines.push('<div class="metadata">');
        lines.push(`<p>Created: ${data.whiteboard.createdTime}</p>`);
        lines.push(`<p>Last Modified: ${data.whiteboard.lastEditedTime}</p>`);
        lines.push(`<p>Created By: ${data.whiteboard.createdBy}</p>`);
        lines.push('</div>');
      }
      
      if (data.cards?.length > 0) {
        lines.push('<h2>Cards</h2>');
        
        for (const card of data.cards) {
          lines.push(`<div class="card">`);
          lines.push(`<h3>${card.title}</h3>`);
          
          const content = JSON.parse(card.content);
          const text = extractTextFromContent(content);
          lines.push(`<p>${text}</p>`);
          lines.push('</div>');
        }
      }
      
      lines.push('</body>');
      lines.push('</html>');
      
      return lines.join('\n');
    }
    
    async function generateTextSummary(data: any, params: any): Promise<string> {
  • Utility function to extract text from Heptabase card content structures, used in summary generation.
    function extractTextFromContent(content: any): string {
      if (typeof content === 'string') {
        return content;
      }
      
      if (content.text) {
        return content.text;
      }
      
      if (content.content && Array.isArray(content.content)) {
        return content.content
          .map((item: any) => extractTextFromContent(item))
          .filter(Boolean)
          .join(' ');
      }
      
      return '';
    }
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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/LarryStanley/heptabse-mcp'

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