Economy Intel MCP has 4 tools with basic descriptions and no visible input schemas in the source code. Tool names follow verb_noun convention (us_series, world_series, list_indicators, country_profile), but descriptions lack LLM-optimization guidance (e.g., when to use each tool vs. alternatives). Parameter descriptions exist but are generic ('Series identifier', 'Country name'). No output schemas documented. No error handling guidance visible. The Python example shows MCP calls but does not reveal the actual server-side tool registration or schema definitions.

• Add explicit JSON Schema definitions for all tool inputs. For us_series, define 'series' as an enum with all valid values (us_unemployment_rate, us_cpi, us_nonfarm_payrolls, etc.). For world_series, define 'country' and 'indicator' with enums or regex patterns and length constraints.
• Document output schemas for each tool. E.g., us_series returns {data: [{year: string, period: string, value: number}], metadata: {source: string, last_updated: string}}. This enables LLMs to extract and chain results.
• Expand tool descriptions to 100-150 characters with selection guidance. E.g., 'Fetch US macroeconomic series from BLS/Census. Use for US-only indicators (unemployment, CPI, payrolls). For global data, use world_series instead.'
• Add error handling guidance to descriptions. E.g., 'If series not found, call list_indicators to see available series. If API times out, retry after 5 seconds.'
• Implement pagination for list_indicators if it returns many results. Add limit and offset parameters, and return a total_count field so agents can iterate through all indicators.

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

• Relies on Stateful initialize / Mcp-Session-Id (removed; protocol is stateless) - make each request self-contained