Loading ToolBench

Reading the current corpus…

remote-mcp-azure-function MCP server · F · ToolBench

← Browse

remote-mcp-azure-function

github.com/dsaad68/remote-mcp-azure-function

MCP server deployed as Azure Functions that provides financial data retrieval tools via Alpha Vantage API

<=2025-11-25STREAMABLE_HTTP5 tools

37/100

Definition Quality48

Protocol Readiness32

Supportability23

Spec posture

Inferred effective spec <=2025-11-25·current baseline 2026-07-28

Static source inference · medium confidence · detected: Logging

Deprecated protocol patterns detected

Summary

This server has several significant gaps in definition quality. All 5 tools follow consistent verb_noun naming (get_*), which is good. However, parameter descriptions are minimal (only 'The stock symbol to fetch data for.'), tool descriptions lack critical details about prerequisites, return types, and use-case context. No output schemas are documented, making it impossible for LLMs to know what fields to expect. No error handling guidance is provided. The server uses a custom schema abstraction (Tool, ToolProperty classes in src/tools.py) that is not visible in the source, making it difficult to verify if proper JSON Schema is being generated. The descriptions are generic and do not distinguish between when to use get_company_overview vs get_income_statement, they all reference 'company information' and 'financial data' without explaining the semantic difference or what use cases each solves.

Tools (5)

get_balance_sheetread onlyauthsource verified48/100

This returns the annual and quarterly balance sheets for the company of interest, with normalized fields mapped to GAAP and IFRS taxonomies of the SEC. Data is generally refreshed on the same day a company reports its latest earnings and financials.

get_cash_flowread onlyauthsource verified48/100

This returns the annual and quarterly cash flow for the company of interest, with normalized fields mapped to GAAP and IFRS taxonomies of the SEC. Data is generally refreshed on the same day a company reports its latest earnings and financials.

get_company_overviewread onlyauthsource verified48/100

This returns the company information, financial ratios, and other key metrics for the equity specified. Data is generally refreshed on the same day a company reports its latest earnings and financials.

get_earningsread onlyauthsource verified48/100

This returns the annual and quarterly earnings (EPS) for the company of interest. Quarterly data also includes analyst estimates and surprise metrics.

get_income_statementread onlyauthsource verified48/100

This returns the annual and quarterly income statements for the company of interest, with normalized fields mapped to GAAP and IFRS taxonomies of the SEC. Data is generally refreshed on the same day a company reports its latest earnings and financials.

Issues (6)

CRITICALtool-schema-output ↗

No output schemas documented. Tools return raw API responses (dicts) with no guidance on field names, types, or expected structure. LLMs cannot reason about downstream tool chains or extract specific fields.

get_company_overviewget_income_statementget_balance_sheetget_cash_flowget_earnings

HIGHtool-description ↗

Descriptions are generic and do not differentiate use cases. All 5 tools have nearly identical descriptions ('This returns... Data is generally refreshed...'). LLMs cannot reason about when to use get_income_statement vs get_balance_sheet, both claim to return 'company information' without explaining the semantic distinction or which financial analysis goal each serves.

get_company_overviewget_income_statementget_balance_sheetget_cash_flowget_earnings

HIGHtool-description ↗

Parameter descriptions are minimal. The single parameter 'symbol' has a one-line description. No guidance on format (e.g., 'Uppercase ticker like AAPL, MSFT'), whether partial symbols are accepted, or what happens if the symbol is invalid or does not exist.

Recommendations

For each tool, add a specific, detailed description explaining the financial metric it returns, when an analyst would use it, and how it differs from related tools. Example: 'get_income_statement returns revenues, operating expenses, and net income across periods, use this to analyze profitability trends. Differs from get_company_overview (current financials) and get_earnings (EPS data).'
Document the output schema for each tool. Specify the top-level fields (e.g., for get_company_overview: MarketCap, PE, DividendYield, etc.) and their types. This enables LLMs to extract specific values in downstream reasoning.
Enhance parameter description for 'symbol': 'The stock ticker symbol in uppercase (e.g., AAPL, MSFT, GOOGL). Must be a valid equity symbol traded on major US exchanges.' Include validation error guidance: 'If the symbol is invalid or does not exist, the API returns {"Error": "..."}, try suggesting the user spell-check or search for the company name first.'
Add error classification and recovery hints. For example: 'If the response includes {"Error": "Invalid API call..."}, retry with a valid symbol. If it includes {"Error": "Thank you for using Alpha Vantage..."}, the daily API limit is reached, inform the user and try again tomorrow.'
Consider adding a batch tool (e.g., get_financial_summary) that calls multiple endpoints and returns a consolidated report, reducing the number of sequential tool calls needed for common use cases.
Document the data refresh cadence explicitly: 'Data is refreshed on the same day earnings are released, usually after market close. Intraday requests may return stale data.' This helps LLMs reason about data freshness.

Spec posture evidence

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

Relies on Logging (deprecated) - log to stderr or use OpenTelemetry

Score history

Overall score trend

↓ 2 points across a rubric change (v1 → v2)

37/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-22	F	37	<=2025-11-25	v2
2026-03-09	F	39	-	v1