Three well-named, read-only tools with clear descriptions and proper Zod schemas. All tools follow verb_noun naming (glossary_define, glossary_search, glossary_list_categories). Descriptions are substantive (100 - 180 chars) and explain WHEN to use each tool. Input parameters have type definitions and descriptions. However, output schemas are not formally documented, responses are text-only with no structured field definitions. Error handling is basic (no recovery guidance for failed searches). Missing tool annotations (readOnlyHint) despite all tools being read-only. No pagination support on search despite potentially large result sets.

• Add readOnlyHint: true to all three tool definitions to signal safety to agents.
• Document output schemas: glossary_define should return {term, category, platforms, definition, relatedTerms, uri}; glossary_search should return {matches: [{term, slug, category, shortDefinition}], total, nextCursor}.
• Convert glossary_search category parameter to an enum constraint (z.enum(['Platform Policy', 'Legal & Regulatory', ...])) instead of free-form string.
• Add cursor-based pagination to glossary_search: accept optional cursor parameter, return nextCursor in response, and document the limit cap (50) in description.
• Enhance error messages: when glossary_search returns no matches, suggest 'Try glossary_list_categories to explore available topics' or 'Try glossary_search with a broader keyword'.