kcsc_formula

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

No annotations are provided, so the description carries full burden. It discloses that formulas are GIF images (not text, no alt/MathML), that recognition of subscripts may be faulty, and that the designer performs final cross-checking. It also notes the image numbers match 〔그림 N〕. This is transparent about limitations and output format, though it doesn't state error behavior or auth requirements.

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 front-loaded with the core purpose, followed by parameter explanations and a caveat about recognition errors. It is moderately long but every sentence adds value—no fluff. The structure is logical and scannable, though slightly verbose compared to minimal examples.

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 no output schema and no annotations, the description covers the essential operational details: what it returns (image), how parameters work, the numbering convention, and the recognition risk. It could be more explicit about the exact return structure (e.g., an array of image URLs) but the description is sufficient for an agent to invoke it correctly.

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 0%, and the description compensates fully. It explains each parameter: code (기준 코드, e.g., KDS 14 31 10), section (조항번호, must be narrowed), code_type (only when codes overlap), and max_images (max count, 0 default 40). This adds meaning far beyond the schema's bare property names.

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 fetches the section's formula as a 'GIF image' (수식을 이미지 그대로 가져온다), specifying the verb and resource. It distinguishes from text-reading tools by emphasizing the image nature, though it doesn't explicitly name sibling tools. The purpose is unambiguous and easily tells agents when to use it.

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?

It gives specific usage guidance: 'section: 반드시 좁혀서 지정한다' (must be specified narrowly) and explains params like code_type only when codes overlap, and max_images default. It implies when to use this tool (when exact formula images are needed) but doesn't explicitly state when not to use alternatives or contrast with kcsc_read/search. Still, the context is clear.

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