business_details

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

Even without annotations, the description covers critical behavioral traits: it warns about low-reliability segment data falling back to raw markdown, explains context_mode behavior with candidate mode, cautions against misreading fixed asset tables, instructs to verify report name, and details parameter interactions (bsns_year+reprt_code overriding period). This goes well beyond basic disclosure.

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

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

The description is very long but well-structured with clear sections (desc, when, rule, period, fields, etc.) and front-loads the core purpose. While verbose, every part adds necessary detail for a complex tool. A more concise organization could improve readability, but it remains serviceable.

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

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

Given the tool's complexity (8 parameters, multiple conditional behaviors, interaction with siblings), the description is remarkably complete. It covers purpose, usage context, parameter semantics, behavioral nuances, and warnings. The presence of an output schema reduces the need to detail return values, allowing the description to focus on input and behavior.

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

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

With 0% schema coverage, the description takes full responsibility for parameter meaning. It explains each parameter in detail: fields as comma-separated list with standard vs financial options, period with 'latest'/'annual'/'quarterly' and interaction with bsns_year/reprt_code, bsns_year and reprt_code with explicit DART codes and usage, context_mode and context_chars with behavior. All parameters are adequately described.

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

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

The description clearly states the tool's purpose: extracting business segment details (sales, profit, production, R&D, orders, customers) from a specific Korean regulatory report (DART). It distinguishes itself from sibling tools like financial_metrics (for company-wide financials) and valuation, making its unique role evident.

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

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

The description provides explicit when-to-use guidance ('회사의 사업부문·생산·수주·고객 구조가 필요할 때'), when-not-to-use (for financials use financial_metrics, for valuation use valuation, for financial institutions use other tools), and how to handle historical data via repeated calls. It also mentions alternative tools explicitly.

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