Three tools with complete input schemas and descriptions, but significant gaps in parameter documentation and output schema specification. Tool names follow verb_noun convention (analyze_, compare_, save_). Descriptions are present (60-90 chars) but lack actionable context for LLM selection. Critical issue: no output schemas documented anywhere, LLMs cannot plan downstream calls or extract results. Parameter descriptions exist but are minimal (10-30 chars). The save_alrc tool includes input validation (ALRC format guard) but lacks error recovery guidance. No tool annotations (readOnlyHint/destructiveHint) despite clear semantic differences (two read-only, one write). Missing: pagination guidance, rate limits, and chaining IDs in responses.

• Add explicit output schemas to tools/list response. E.g., analyze_music should return {type: 'object', properties: {chords: [string], timbre: [string], dynamics: [number]}, required: [...]}.
• Expand parameter descriptions to 50-100 chars with format/constraint details. E.g., 'Absolute path to audio file (wav/mp3/flac, max 500MB, must exist on local filesystem)'.
• Add tool annotations in tools/list: readOnlyHint: true for analyze_music and compare_music; destructiveHint: true for save_alrc.
• Implement error recovery in save_alrc. When validate_alrc fails, return structured error: {error: 'Invalid ALRC format', line: N, expected: '...', received: '...', recovery: 'Fix line N and retry'}.
• Document result limits and chunking strategy. E.g., 'analyze_music returns up to 100 chord events; use onset_mode=true for complex music to reduce output size.'