Server has 4 tools with basic schemas and descriptions, but significant quality gaps. Tool names lack action verbs (echo, printEnv are acceptable; webToGrareco and textToGrareco are vague about transformation intent). Descriptions exist but are minimal (10-50 chars for utility tools; 60-80 chars for core tools). Parameter descriptions are present but lack detail on constraints, formats, or error cases. No output schemas documented. No error handling guidance. No tool annotations (readOnlyHint, destructiveHint). Core tools (webToGrareco, textToGrareco) lack clarity on what 'graphic recording format HTML' means to an LLM, no example output structure provided.

• Rename webToGrareco → convert_web_to_grareco and textToGrareco → convert_text_to_grareco to follow verb_noun convention.
• Add English descriptions (100-200 chars) explaining what 'graphic recording format HTML' means, when to use each tool, and what output structure to expect.
• Document output schema for both conversion tools: return object with fields like {html: string, summary: string, elements: array} so LLMs know what to extract.
• Add error handling guidance: 'If URL fetch fails, suggest user provide text directly via textToGrareco. If API rate limit hit, retry after 60 seconds.'
• Add tool annotations: set readOnlyHint=true for all tools in schema to signal they are safe to call without user confirmation.

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

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