Three tools with complete schemas and clear descriptions. Naming follows verb_noun pattern (list_, ask_, get_). Descriptions are well-written (100-150 chars) and explain WHEN to use each tool. However, parameter descriptions are minimal (5-20 chars), and output schemas are not documented. No error handling guidance or recovery paths. Tool composition is sound, each does one thing, but lacks pagination, result limits, and structured output documentation.

• Document output schemas for all three tools. Example: list_walkthroughs returns {walkthroughs: [{id: string, display_name: string, step_count: number, total_duration_s: number}]}. This enables LLMs to plan multi-step workflows.
• Expand parameter descriptions to 50-100 chars. For walkthrough_id, add: 'Stable identifier from list_walkthroughs. Format: lowercase alphanumeric with hyphens (e.g., onboarding-flow-v2).' For question, add: 'Natural language query about walkthrough content, steps, timing, or narration.'
• Add error recovery guidance. When walkthrough_id is invalid, return: 'Walkthrough not found. Call list_walkthroughs() to see available IDs.' When ask_walkthrough fails, suggest: 'Try get_transcript() to read the full walkthrough manually.'
• Implement pagination for list_walkthroughs. Add optional limit (default 20, max 100) and offset parameters. Return {walkthroughs: [...], total: number, has_more: boolean}. Document in description: 'Returns up to 20 walkthroughs per call.'
• Document ask_walkthrough citations format. Clarify: 'citations is an array of step IDs (e.g., ["step-1", "step-3"]) that Claude drew from. Include these in your response to the user for traceability.'