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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's job is to add output-shape context — and it does: changed text marked in 【 】, the delegation vs citation distinction, the length warning, and that English input yields an English answer. Pagination behavior is only implied via the schema, which keeps it below a 5.

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?

Front-loaded with the core purpose and the two modes, then per-kind definitions, then practical notes. Dense but every sentence carries information; the mixed Korean/English parentheticals add length but are necessary for the domain terminology.

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, no-output-schema tool, the description covers output formats, scoping advice, and the edition modifier. Minor gaps remain around paging behavior and default page size, but the schema already documents the page parameter, so an agent can call this 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 100%, so baseline is 3, but the description goes further by defining what each kind enum actually returns and by explaining that edition=시행예정 surfaces amendments promulgated but not yet in force. That is genuine meaning beyond the terse enum labels.

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?

States a specific verb and resource ('Compare a Korean law's articles before and after amendment') and immediately names the two distinct modes (신구법 vs 3단 비교), which cleanly separates it from siblings like get_article or get_law_status that fetch rather than compare.

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?

Gives a concrete usage constraint: three-tier output is long, so an article should be supplied — that steers the agent toward narrowing the scope. It also explains when each kind applies (amendment text vs delegation vs citation), though it never explicitly says when to prefer a sibling tool over this one.

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