Two tools with basic schemas and descriptions, but significant gaps in parameter documentation, output schema clarity, and error handling guidance. Tool names follow verb_noun convention (get_*), but descriptions lack depth on when/why to use each tool. Parameters have type definitions but minimal context. Error handling returns text responses without structured guidance for LLM recovery. No tool annotations (readOnlyHint, etc.) despite both being read-only operations.

• Add format constraints to address parameter: 'Ethereum address (0x-prefixed hex string, 42 characters total, e.g. 0x1234...abcd)'
• Document output schema in tool definitions: {type: 'object', properties: {content: {type: 'array', items: {type: 'object', properties: {type: {type: 'string'}, text: {type: 'string'}}}}}}
• Enhance error responses with structured guidance: return {content: [{type: 'text', text: 'Invalid address format. Expected 0x-prefixed 42-char hex string. Retry with valid address.'}]} for user-fixable errors
• Expand tool descriptions to 100-150 chars explaining when to use: 'Get the MON token balance for a Monad testnet address. Use this to check account funding before transactions. Requires valid 0x-prefixed address.'
• Add readOnlyHint: true annotation to both tools to signal they are safe to retry and have no side effects