Skip to main content
Glama

get_wwdc_video

Read-only

Retrieve complete WWDC session content including full transcript, code examples, and resources for offline access.

Instructions

Access complete WWDC session content including full transcript, code examples, and resources. Use after finding videos with list_wwdc_videos or search_wwdc_content. Provides offline access to entire session content.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearYesWWDC year. Example: "2025"
videoIdYesSession ID. Example: "10101" for keynote, "238" for session 238.
includeTranscriptNoInclude full session transcript with timestamps. Default: true
includeCodeNoInclude all code examples from the session. Default: true

Implementation Reference

  • Main handler function that loads video data via loadVideoData(year, videoId) and formats the result using formatVideoDetail(). Catches and logs errors.
    /**
     * Get WWDC video details
     */
    export async function handleGetWWDCVideo(
      year: string,
      videoId: string,
      includeTranscript: boolean = true,
      includeCode: boolean = true,
    ): Promise<string> {
      try {
        // Load video data directly
        const video = await loadVideoData(year, videoId);
    
        return formatVideoDetail(video, includeTranscript, includeCode);
    
      } catch (error) {
        logger.error('Failed to get WWDC video:', error);
        const errorMessage = error instanceof Error ? error.message : String(error);
        return `Error: Failed to get WWDC video: ${errorMessage}`;
      }
    }
  • Formats video details including title, speakers, topics, resources, chapters, transcript (with timestamped segments), code examples, and related videos.
    function formatVideoDetail(
      video: WWDCVideo,
      includeTranscript: boolean,
      includeCode: boolean,
    ): string {
      let content = `# ${video.title}\n\n`;
      content += `**WWDC${video.year}** | [Watch Video](${video.url})\n\n`;
    
      // Basic information
      if (video.duration) {
        content += `**Duration:** ${video.duration}\n`;
      }
      if (video.speakers && video.speakers.length > 0) {
        content += `**Speakers:** ${video.speakers.join(', ')}\n`;
      }
      if (video.topics.length > 0) {
        content += `**Topics:** ${video.topics.join(', ')}\n`;
      }
    
      // Resource links
      if (video.resources.hdVideo || video.resources.sdVideo || video.resources.resourceLinks) {
        content += '\n**Resources:**\n';
        if (video.resources.hdVideo) {
          content += `- [HD Video](${video.resources.hdVideo})\n`;
        }
        if (video.resources.sdVideo) {
          content += `- [SD Video](${video.resources.sdVideo})\n`;
        }
        if (video.resources.resourceLinks && video.resources.resourceLinks.length > 0) {
          video.resources.resourceLinks.forEach(link => {
            content += `- [${link.title}](${link.url})\n`;
          });
        }
      }
    
      // Chapters
      if (video.chapters && video.chapters.length > 0) {
        content += '\n## Chapters\n\n';
        video.chapters.forEach(chapter => {
          content += `- **${chapter.timestamp}** ${chapter.title}\n`;
        });
      }
    
      // Transcript
      if (includeTranscript && video.transcript) {
        content += '\n## Transcript\n\n';
    
        // If there are timestamped segments, use them
        if (video.transcript.segments.length > 0) {
          video.transcript.segments.forEach(segment => {
            content += `**${segment.timestamp}**\n`;
            content += `${segment.text}\n\n`;
          });
        } else {
          // Show full transcript text
          content += video.transcript.fullText;
        }
      }
    
      // Code examples
      if (includeCode && video.codeExamples && video.codeExamples.length > 0) {
        content += '\n## Code Examples\n\n';
    
        video.codeExamples.forEach((example, index) => {
          if (example.title) {
            content += `### ${example.title}`;
          } else {
            content += `### Code Example ${index + 1}`;
          }
    
          if (example.timestamp) {
            content += ` (${example.timestamp})`;
          }
          content += '\n\n';
    
          content += `\`\`\`${example.language}\n`;
          content += example.code;
          content += '\n\`\`\`\n\n';
    
          if (example.context) {
            content += `*${example.context}*\n\n`;
          }
        });
      }
    
      // Related videos
      if (video.relatedVideos && video.relatedVideos.length > 0) {
        content += '\n## Related Videos\n\n';
        video.relatedVideos.forEach(related => {
          content += `- [${related.title}](${related.url}) (WWDC${related.year})\n`;
        });
      }
    
      return content;
    }
  • Zod schema for get_wwdc_video input: year (string), videoId (string), includeTranscript (boolean, default true), includeCode (boolean, default true).
    export const getWWDCVideoSchema = z.object({
      year: z.string().describe('WWDC year'),
      videoId: z.string().describe('Video ID'),
      includeTranscript: z.boolean().default(true).describe('Include transcript'),
      includeCode: z.boolean().default(true).describe('Include code examples'),
    });
  • Tool definition/registration with name 'get_wwdc_video', description, inputSchema (type: object with year, videoId, includeTranscript, includeCode), and annotations.
    {
      name: 'get_wwdc_video',
      description: 'Access complete WWDC session content including full transcript, code examples, and resources. Use after finding videos with list_wwdc_videos or search_wwdc_content. Provides offline access to entire session content.',
      inputSchema: {
        type: 'object',
        properties: {
          year: {
            type: 'string',
            description: 'WWDC year. Example: "2025"',
          },
          videoId: {
            type: 'string',
            description: 'Session ID. Example: "10101" for keynote, "238" for session 238.',
          },
          includeTranscript: {
            type: 'boolean',
            description: 'Include full session transcript with timestamps. Default: true',
          },
          includeCode: {
            type: 'boolean',
            description: 'Include all code examples from the session. Default: true',
          },
        },
        required: ['year', 'videoId'],
      },
      annotations: {
        title: 'Get WWDC Video',
        readOnlyHint: true,
      },
    },
  • Handler registration in the toolHandlers map: validates args with getWWDCVideoSchema, calls handleGetWWDCVideo, returns formatted text content.
    get_wwdc_video: async (args, _server) => {
      const validatedArgs = getWWDCVideoSchema.parse(args);
      const result = await handleGetWWDCVideo(
        validatedArgs.year,
        validatedArgs.videoId,
        validatedArgs.includeTranscript,
        validatedArgs.includeCode,
      );
      return { content: [{ type: 'text', text: result }] };
    },
Behavior4/5

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

Annotations already include readOnlyHint=true, so the bar is lower. The description adds context about providing offline access and full content, which is valuable. No contradictions.

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?

Two sentences: first states purpose, second gives usage guidance. No extraneous information, front-loaded with key details.

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

Completeness5/5

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

Given no output schema, the description sufficiently explains the tool returns complete session content with transcript, code, and resources. It also mentions offline access, covering all necessary context.

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 coverage is 100%, so the description does not need to add much. However, it does not elaborate on parameters beyond what the schema already provides, maintaining the baseline of 3.

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

Purpose5/5

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

The description clearly states the tool accesses complete WWDC session content including transcript, code examples, and resources. It distinguishes itself from siblings by specifying it is used after finding videos with list_wwdc_videos or search_wwdc_content.

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 states to use after finding videos with list_wwdc_videos or search_wwdc_content, providing clear context. No when-not-to-use instructions are given, but the guidance is sufficient for an agent.

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/kimsungwhee/apple-docs-mcp'

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