Server exhibits significant definition quality gaps. Tool descriptions are present but generic (avg ~60 chars, below 194-char baseline). Input schemas visible but lack parameter descriptions, critical for LLM tool selection. No output schemas documented. Duplicate tool names ('identify_regulatory_body' appears twice with identical signatures) signal composition issues. Tools are READ_ONLY but lack explicit idempotentHint annotations. Error handling guidance absent from descriptions. No evidence of parameter constraints (enums, ranges, formats) despite tools accepting document_types arrays.

• Rename duplicate 'identify_regulatory_body' tools to 'identify_esma_regulatory_body' and 'identify_csrc_regulatory_body' to enable LLM disambiguation.
• Add parameter descriptions for all array/enum inputs. E.g., 'document_types: List of regulatory document categories (e.g., MiFID II, MiFIR, Prospectus Regulation, Market Abuse Regulation, MiCA). Case-sensitive. Required.'
• Document output schemas for each tool. E.g., fetch_esma_documents returns {documents: [{id, title, type, url, date_published}], total_count, next_cursor}. Enables LLM chaining.
• Expand tool descriptions to 100-200 chars. Include WHEN to call (e.g., 'Call this first to discover available document types before fetching'), WHAT it returns, and any prerequisites.
• Add error handling guidance to descriptions. E.g., 'If connectivity fails, check network and retry. If documents not found, try broader document_types or call get_esma_local_documents to see cached inventory.'

Inferred effective spec: <=2025-11-25.

• Relies on Logging (deprecated) - log to stderr or use OpenTelemetry