Two tools with basic schemas and descriptions, but significant gaps in parameter documentation and output schema clarity. doc_search has a reasonable description (145 chars) and three parameters with types, but 'category' lacks description detail and enum constraints. doc_search_status has minimal description (75 chars) and no parameters. Neither tool documents output structure, making it hard for LLMs to plan downstream actions. No error handling guidance. Naming follows verb_noun convention (search_, status) which is good, but descriptions lack WHEN/WHY context and recovery hints.

• Add explicit output schema documentation for both tools. For doc_search, document that results include {content, source, page, category, score}. For doc_search_status, document {indexed, total_chunks, total_files, categories, files}.
• Convert 'category' parameter to an enum: {"type": "string", "enum": ["eda", "company", "bugs", "default"], "description": "Document category filter. Use 'eda' for EDA tools (Innovus, ICC), 'company' for procedures, 'bugs' for bug reports, 'default' for general documents."}
• Expand doc_search_status description to ~150 chars: 'Check what documents are indexed and their categories. Call this first to verify indexing is complete, or to guide users on what topics are available for search.'
• Add error recovery hints: 'If no results found, try: (1) verify documents are indexed with doc-search index, (2) use broader search terms, (3) check category filter matches your documents.'
• Remove imperative language from doc_search description. Replace 'ALWAYS search BEFORE answering' with 'Use when user asks about EDA tools, company procedures, technical documentation, or specialized topics that may be indexed.'