Two simple text-manipulation tools with minimal descriptions and no output schema documentation. Tool names lack action verbs (reverse-text, uppercase should be reverse_text, convert_to_uppercase). Descriptions are extremely brief (10-30 chars, below the 34-char p10 baseline). Input schemas are present and properly typed, but parameter descriptions are generic. No error handling guidance, no pagination, no composition hints. No tool annotations (readOnlyHint, idempotentHint). This is a toy example, not production-grade.

• Rename tools to verb_noun format: 'reverse_text' and 'convert_to_uppercase'. This helps LLMs parse intent from the name alone.
• Expand descriptions to 50-150 chars. Example: 'Reverse the input text and return the result. Useful for palindrome checks or text manipulation tasks.'
• Document output schema explicitly. Specify that both tools return a single TextContent object with a 'text' field containing the transformed string.
• Add tool annotations to the schema: set 'readOnlyHint: true' and 'idempotentHint: true' for both tools to signal safety properties to LLMs.
• Improve error handling: return structured error responses with actionable guidance. E.g., 'Missing required parameter: text. Provide a non-empty string to reverse or convert.'

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

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