기업집단 구조 조회

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

With no annotations, the description carries the full burden and discloses key behaviors: EGROUP_API_KEY requirement, annual May 1 data refresh with yearly caching, DART join constraint (법인등록번호, not name), naming convention (에스케이 not SK), and financial units in KRW. These are non-obvious traits that materially affect tool invocation and output interpretation.

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 longer than average but each sentence adds value: core purpose first, then critical caveats and cross-references. Bullet points break down complex details efficiently. Not as lean as the TDQS 4.3 example, but no filler or repetition.

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?

For a 5-parameter tool with no output schema and no annotations, the description covers essential context: data source freshness, join limitations, API key requirement, and usage in compliance workflows. It could be more explicit about exact return structure (e.g., field names for overview), but it gives sufficient operational guidance for an agent to select and call the tool effectively.

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?

Schema coverage is 100%, so baseline is 3, but description adds significant semantics beyond schema: notes group name/code format, explains compact for token reduction, details join_dart fallback behavior, and maps include_financials fields to check_disclosure_duty inputs. The main gap is lack of exact output field names for the base response, but the description enriches each parameter meaningfully.

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 it returns the overview (동일인·대표회사·소속회사 수) and all subsidiaries for FTC-designated corporate groups, with a specific verb "돌려줍니다". It distinguishes itself by emphasizing the subsidiary list as the population for FTC disclosure obligations, separate from sibling tools like get_financials or resolve_entity.

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?

Provides explicit guidance: include_financials output can be directly used as inputs for check_disclosure_duty, and unresolved DART joins should be supplemented via resolve_entity(fetchJurirNo=true). It also notes annual data refresh timing, which helps determine when to use this tool for periodic compliance checks.

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