Two tools with minimal descriptions (Japanese, under 50 chars each) and basic schemas. Tool names follow verb_noun pattern (getSpreadsheet, getSheetData) but descriptions lack WHAT/WHEN/WHY context required for LLM selection. Input schemas present but sparse, only 'url' and 'sheetName' with minimal descriptions. No output schema documented. No error handling guidance, no pagination support, no parameter constraints (enums, ranges). Descriptions are in Japanese, limiting LLM comprehension in English-first agents. No tool annotations (readOnlyHint present in metadata but not in schema). Composition is reasonable (two focused tools) but lacks chaining metadata (e.g., sheet IDs in response).

• Rewrite tool descriptions in English, 50-200 characters, answering: What does it do? When to use it? What does it return? E.g., 'Fetch metadata and sheet names from a Google Spreadsheet. Call this first to discover available sheets before reading data.'
• Document output schemas for both tools. getSpreadsheet should return {id, name, url, sheets: [{id, name, rowCount, columnCount}]}. getSheetData should return {data: [[...]], rowCount, columnCount, nextCursor?}.
• Add parameter descriptions in English with format guidance: 'url: Google Spreadsheet URL (https://docs.google.com/spreadsheets/d/...) or spreadsheet ID (alphanumeric string).'
• Implement pagination for getSheetData: add optional 'limit' (1-1000, default 100) and 'offset' (default 0) parameters. Return {data, rowCount, totalRows, hasMore}.
• Add error recovery guidance: catch API errors and return structured {error, suggestion} e.g., 'Spreadsheet not found. Verify the URL is correct and you have read access.'