별표·서식 조회

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered structurally. The description adds real behavioral context beyond that: it downloads the annex file and extracts text when bylSeq is given, and extracts the body directly when query narrows to a single annex. However, it never says what a multi-match response looks like versus a single-match extraction, leaving the return shape ambiguous.

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?

Purpose and the core lawName+'별표N' pattern are front-loaded, and every sentence carries usable information (amounts in annexes, retroactive lookup, query-over-number advice). It is a dense run-on block with parenthetical asides and some overlap with the schema text, which keeps it from a 5.

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?

With 7 parameters, a 100% covered schema, and full annotations, the description supplies the missing decision context: retroactive date semantics, jurisdiction/naming quirks, and narrowing strategy. There is no output schema, and the description only partially covers the return shape (file-download text vs. direct body extraction vs. presumably a list when ambiguous), so a small gap remains.

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 description coverage is 100%, so the baseline is 3; every parameter already carries an inline description with examples (jo, knd enum, bySeq, annexNo). The description's date and query guidance largely restates what is already written in those schema fields, adding little genuinely new parameter meaning. The interaction hint that query is safer than a number when the annex number varies is the main marginal contribution.

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 resource and retrieval method: 별표/서식 (annexes/forms) of a Korean statute, extracted via lawName + '별표N'. It also notes that monetary amounts and standards often live in annexes rather than the main text, which clarifies what kind of content this tool returns. It never names the sibling get_law_text as the alternative for main-article text, so the differentiation is implicit rather than explicit.

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 clear context for the date parameter (retroactive standards at time of permit/construction/disposition, renamed statutes) and advises using query by annex name because annex numbering shifts over time. This is genuine when-to-use guidance. It stops short of stating when NOT to use it or naming a sibling to fall back on.

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