Two tools with clear, action-verb names (find_hyperbits, fetch_hyperbit) and reasonable descriptions (95 - 120 chars). Input schemas are present with proper JSON Schema structure, types, and descriptions for all parameters. However, output schemas are not documented in the source code, critical for LLM planning. Parameters lack constraints (e.g., limit has no maximum; tags array has no item count bounds). Error handling and recovery guidance are absent. No tool annotations visible. Descriptions are adequate but could be more prescriptive about when to use each tool and what to do with results.

• Document output schemas for both tools. Specify: find_hyperbits returns {results: [{id, name, tags, ...}], total_count, next_cursor?}; fetch_hyperbit returns {id, name, metadata, html_source, helpers, embed_snippet, ...}.
• Add constraints to parameters: limit (minimum: 1, maximum: 100, default: 20); tags (maxItems: 10, minItems: 0). Include these in descriptions: 'Maximum 100 results per query; default 20.'
• Add error recovery guidance: 'If no results found, try broader query terms or fewer tags. If ID not found, call find_hyperbits to discover available IDs.'
• Enhance fetch_hyperbit description: 'Fetch a specific hyperbit by its ID (from find_hyperbits) or exact display name. If you only have a partial name, call find_hyperbits first.'
• Add tool annotations: readOnlyHint=true and idempotentHint=true for both tools to signal to agents that these are safe to retry and do not modify state.