Strong foundation with well-structured tools and clear naming conventions. All 7 tools follow verb_noun pattern (get_*, search). Descriptions are present and substantive (avg ~120 chars), exceeding the 10-char minimum. Input schemas are properly typed with JSON Schema. However, parameter descriptions are sparse or missing in several tools (e.g., 'scope' in search lacks detail on structure; 'filter' lacks format guidance). Output schemas are not documented in the visible code. Error handling guidance is absent, tools do not indicate what to do on failure or how to recover. No tool annotations (readOnlyHint, etc.) despite all being read-only operations.

• Document output schemas for all tools. For search(), specify: returns array of {file, heading, snippet, score, rank}. For get_vault_tree(), specify: returns {root, children: [{name, path, type, token_count, ...}]}. For get_server_info(), specify all fields in the GetServerInfoResult type.
• Expand parameter descriptions: 'scope' in search should document structure (e.g., {file?: string, heading?: string, tag?: string}); 'filter' should provide syntax examples or link to filter grammar; 'heading' should clarify format (heading string vs path vs anchor).
• Add error handling guidance to tool descriptions. E.g., search: 'Returns empty array if no matches. If index is degraded, results may be incomplete, check get_server_info().index.degraded.' get_fragment: 'Returns null if file or heading not found. Call get_vault_tree() to verify file exists.'
• Add readOnlyHint: true to all 7 tool definitions. This signals to agents that these operations are safe to retry and have no side effects, enabling more aggressive caching and retry strategies.
• Clarify 'heading' parameter format across get_fragment and get_links. Document whether it accepts: (a) exact heading text, (b) heading path (e.g., 'Section > Subsection'), or (c) anchor ID. Provide an example.