ETF 수익률·NAV 추이 조회

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

With no annotations provided, the description carries the full burden. It discloses data source (Kiwoom), the meaning of benchmark_index_code (from get_market_index), and the resolution difference for investor view. It does not mention error handling, rate limits, or explicitly state read-only behavior, but the get_ prefix and content make the nature clear.

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 a single dense paragraph, front-loaded with the main purpose and then breaking down the three views. Every sentence provides useful information, but the density and semicolon-heavy structure could be more readable with bullets or shorter sentences. Still, it is appropriately sized for the complexity.

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?

Since there is no output schema, the description needs to explain return content, and it does: it describes what each view returns (returns vs index, NAV/premium/tracking error, investor net buying) and the benchmark code source. It lacks response format details and edge-case behavior, but covers the essential usage contexts for a 3-view tool.

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?

Although schema coverage is 100%, the description adds substantial value: it explains the default benchmark index code (201 KOSPI200) and how to find other codes, clarifies the purpose of each view enum, and notes that days applies to daily/investor. This goes well beyond the schema's minimal descriptions.

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 retrieves ETF performance from three angles and enumerates each view: period returns with benchmark comparison, daily NAV/premium/tracking error, and investor net buying. It also distinguishes itself from siblings like get_etf_info (snapshot vs trend) and search_stock (code lookup), making the purpose unambiguous.

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?

Explicitly provides usage context for each view: period for returns, daily for checking fair value and index tracking, investor for foreign/institutional net flows. It also names alternatives (get_etf_info, search_stock) and clarifies when they are appropriate, effectively telling the agent when not to use this tool.

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