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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new behavior: results are collapsed by topic via group=True and must be expanded with show, n is capped at 20, weird results should trigger a filter-free retry, and region gaps surface as region_gap/region_fallback. Return-format detail duplicates the existing output schema rather than adding to it.

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 is front-loaded and the remaining content is a tight bullet list where each bullet carries actionable guidance rather than filler. Minor waste comes from restating the Korean purpose line in English and from listing the return shape that the output schema already defines.

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 6-parameter, 0%-coverage search tool, the description covers query phrasing, filtering hints, grouping, result limits, retry strategy, and regional fallback, which is enough for an agent to call it correctly. The output schema removes any need to explain return values, and the only remaining gap is the precise syntax for org and dtype beyond the API/FILE hint.

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 0%, so the description carries the whole burden and largely does so: query format is shown by example, fields is illustrated with fields=['위도','경도'], group's collapsing behavior is explained, n's ceiling is stated, and dtype is enumerated (API/FILE) with org identified as the agency filter. Only the exact accepted values/syntax for org are left unspecified.

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 gives a specific verb and resource ('Search Korean public datasets by topic'), scopes it to datagokr, and shows concrete query examples ('전국 주차장', '재난문자 API'). It also draws a boundary against the sibling 'fields' tool for column-only queries, so an agent can distinguish it without opening the schemas.

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 explicitly routes to alternatives ('컬럼만 조건이면 `fields` 툴', 'group_ids의 id를 show로 펼치세요') and gives practical conditions: retry after dropping filters, cap n at 20, split evaluation-style queries into 2-3 searches, fall back to region_fallback. It does not address when NOT to use search versus get_preview, record, or download_url, so it stops short of full when/when-not coverage.

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