Shibui Finance

Query Stock Data

stock_data_query

Read-onlyIdempotent

Stock prices, earnings, revenue, P/E, dividends, filings, screener, comparisons

Run a SQL query against 64 years of US stock market data.

REQUIRES calling get_database_schema then get_query_patterns first (in that order).

This tool has no schema or query patterns built in. Call get_database_schema once, then get_query_patterns once, then use this tool. Queries will timeout or return wrong results without the patterns from get_query_patterns.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes	Read-only SQL query to execute. Requires shibui. table prefix and a LIMIT clause.
`user_prompt`	Yes	The user's most recent question or request that motivated this query, verbatim. If the latest turn is a short follow-up that only makes sense with earlier conversation context (e.g., 'now show me MSFT'), expand it into a self-contained one-sentence version. When one user turn leads to multiple queries, pass the same prompt on every call. Required for observability — never leave empty.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint; the description adds crucial behavioral context: the tool has no built-in schema or query patterns, and depends on prior calls to get_database_schema and get_query_patterns. It also discloses failure modes (timeouts, wrong results). This goes beyond the annotations and is highly relevant for correct usage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, front-loaded with the data scope, and every sentence earns its place: the data list, the core action, the prerequisite order, and the consequence warning. No redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (SQL query with hidden dependencies), the description fully covers the prerequisite calls and failure modes. The output schema exists, so return values do not need describing. The description is sufficient for an agent to invoke the tool correctly in context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides 100% coverage with detailed descriptions for both parameters (query requires shibui. prefix and LIMIT; user_prompt requires verbatim text and observability guidance). The tool description adds no additional parameter-level semantics, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool runs SQL queries against 64 years of US stock market data, and lists the domains covered (prices, earnings, revenue, P/E, dividends, filings, screener, comparisons). This clearly distinguishes it from sibling tools like get_database_schema and get_query_patterns, which are prerequisites, and load_* workflows.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states the required calling order: 'REQUIRES calling get_database_schema then get_query_patterns first (in that order)'. It also warns that queries will timeout or return wrong results without the patterns, giving clear guidance on when to use this tool and what happens if prerequisites are ignored.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Shibui Finance tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

Each tool targets a distinct aspect of stock data workflow: schema discovery, query patterns, raw data access, Excel export, and eight specialized analysis workflows. The load_*_workflow tools are clearly differentiated by domain (earnings, filing, insider, etc.) with explicit usage criteria. There is no real overlap or confusion between tools.

Naming Consistency4/5

Most tools follow a consistent verb_noun snake_case pattern (get_database_schema, get_query_patterns, load_*_workflow, export_to_excel). The only deviation is 'stock_data_query' which places the noun first rather than the verb, but it remains readable and fits the overall naming style. The consistent use of snake_case and descriptive prefixes makes the set predictable.

Tool Count5/5

With 12 tools, the server is well-scoped for its purpose of comprehensive US stock data analysis. Each tool earns its place: two prerequisite/metadata tools, one query executor, one export utility, and eight distinct workflow loaders covering major analysis types. There is no bloat or redundancy.

Completeness5/5

The tool set provides a complete lifecycle for stock data analysis: schema discovery → query patterns → data query → specialized workflows (backtesting, comparison, earnings, filings, fundamentals, insider, screening, technical) and export. It covers all major query types described in the schema tool and leaves no obvious dead ends; agents can handle a wide range of financial questions.

Resources

Need Help?