Ledgr exposes 6 read-only financial tools with consistent naming (verb_noun pattern: get*, search*) and basic descriptions. All tools have input schemas with type definitions and parameter descriptions. However, descriptions are terse (avg 45 chars, well below the 194-char baseline), lack context on WHEN to use each tool, and omit dependency hints. Output schemas are not documented, LLMs cannot plan downstream calls or extract structured data reliably. No error handling guidance. Parameter constraints are minimal (only getMonthlyTrends and getUpcomingBills have min/max bounds). The tools are well-composed (single responsibility, read-only), but descriptions need expansion to meet LLM-optimization standards.

• Expand all descriptions to 100 - 200 characters. Include WHAT the tool does, WHEN to use it (vs similar tools), and WHAT it returns. Example: 'Get spending breakdown by category for a date range. Use this to analyze spending patterns by category; use searchTransactions to find specific transactions. Returns array of {category, amount, percentage}.'
• Document output schemas for all tools. Add a 'Returns' section to each description or a separate schema block. Example: 'Returns: {categories: [{name: string, amount: number, percentage: number}]}'
• Add error recovery hints. Example for searchTransactions: 'If no results, try expanding the date range or removing filters. If category name is unknown, call getSpendingByCategory first to see available categories.'
• Specify parameter formats and constraints in descriptions. Example: 'startDate (YYYY-MM-DD format, required if endDate is set)' and 'category (case-insensitive; partial matches accepted)'.
• Add tool-chaining hints. Example in getSpendingByCategory: 'To drill into a specific category, call searchTransactions with the category name.'

Inferred effective spec: 2025-06-18+.

• Relies on Dynamic Client Registration (deprecated) - use Client ID Metadata Documents (CIMD)