Three read-only tools with clear, domain-specific descriptions (avg 156 chars). All tools have proper verb-noun naming (search_*, read_*) and documented input schemas with types. However, output schemas are not explicitly documented in the source code, only inferred from descriptions. Parameter descriptions are present but minimal. No error handling guidance, no pagination support despite potential for large result sets, and no tool annotations (readOnlyHint despite all being read-only). Schemas are visible and typed, placing this in the fair-to-good range, but missing production-grade output documentation and error recovery patterns.

• Document output schemas explicitly. Define the structure of search results (e.g., array of {ang: integer, gurmukhi: string, transliteration: string, english: string}) and read_ang response. Include this in tool descriptions or as a separate schema reference.
• Add pagination to search_* tools. Introduce limit (default 20, max 100) and offset parameters. Return total_count and next_offset in responses to enable multi-page result traversal.
• Add readOnlyHint: true to all three tools in the tool registration. This signals to agents that these operations are safe to retry and have no side effects.
• Enhance error handling descriptions. Document what happens when: search returns no results, ang is out of range (1-1430), or query is malformed. Provide actionable recovery hints (e.g., 'Try a shorter query' or 'Valid ang range is 1 - 1430').
• Expand parameter descriptions to 50 - 100 chars. For search_english and search_roman, clarify: expected query length, supported characters, whether partial matches are supported, and any normalization applied (e.g., 'Supports diacritics and compound aliases per search-normalization.json').