Stock and Index Price Display App for ChatGPT - provides real-time stock prices, index data, and market information with interactive widgets
Server has 4 tools with complete input schemas and basic descriptions. All tools follow verb_noun naming (get_*, search_*). However, descriptions are generic and lack actionable context for LLM selection. Parameter descriptions are minimal (e.g., 'Stock symbol' without format guidance). No output schemas documented. Error handling returns plain text without recovery guidance. Missing parameter constraints (enums for index_name, symbol validation patterns). No tool annotations (readOnlyHint present but not declared). Composition is sound, each tool has one responsibility, but descriptions don't explain WHEN to use each tool vs. alternatives.
Get market index information (Nifty 50, Nifty Midcap, Nifty Smallcap).
Display multiple stocks in a carousel format. Great for comparing stocks.
Get current price and details for a stock symbol. Returns a widget with stock information.
Search for stocks by name or symbol.
Parameter descriptions lack actionable constraints. 'Stock symbol (e.g., RELIANCE, TCS, INFY)' uses examples instead of format rules. Should state: 'Stock symbol: 1-10 uppercase letters, e.g., RELIANCE, TCS, INFY. Use search_stocks() if unsure of the symbol.'
Tool descriptions do not explain WHEN to use each tool or how they differ. 'Get current price and details for a stock symbol' is generic. Should clarify: 'Use for a single stock. For comparing multiple stocks, use get_multiple_stocks(). Returns current price, change %, and market data.'
No output schema documented. LLMs cannot plan downstream calls or extract fields. Code returns TextContent + EmbeddedResource with HTML, but schema structure (price, changePercent, symbol fields) is not declared in tool definition.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 58 | 2026-07-28+ | v2 |
Error handling returns plain text without recovery guidance. 'Error fetching stock data: <exception>' tells LLM nothing. Should return: 'Stock symbol not found. Try search_stocks("<query>") to find the correct symbol, or check that the symbol is valid (e.g., RELIANCE, TCS).'
index_name parameter accepts free-form string instead of enum. Description lists valid values ('NIFTY50, NIFTYMIDCAP150, NIFTYSMLCAP250') but schema does not enforce them. LLM may hallucinate invalid index names. Should use enum constraint in inputSchema.