source_search

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

Annotations declare readOnlyHint=true, so the safety profile is already covered. The description goes beyond that by disclosing the return payload (전체 건수·ID·사건번호·일자·링크), which matters because no output schema exists. It still says nothing about pagination behavior, result limits, or per-source quirks, keeping it short of 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?

A single dense sentence, front-loaded with the resource list and ending with the return fields; no filler or restatement of the tool name. The source enumeration is long but each item is load-bearing for source selection, so it earns its length.

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?

This is a high-complexity tool (11 parameters, 9% schema coverage, no output schema, annotations covering only read-only safety). The description addresses return values and source types but leaves query syntax, date format (maxLength 12), pagination, sort semantics, and the meaning of org/court/region entirely undocumented, so an agent cannot call it confidently beyond the simplest case.

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 only 9% — of 11 parameters, only 'source' carries a description. The description partially compensates by mapping Korean source names onto the English enum values (헌재결정→constitutional, 조세심판→tax_tribunal, 자치법규→ordinance, etc.) and noting the max-4 parallel array form, which is genuinely useful for the one required parameter. It adds nothing for query, field, sort, page, size, org, court, region, dateFrom, or dateTo.

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?

Names a specific verb (검색/search) and enumerates the exact resource classes it covers — 판례, 헌재결정, 조세심판, 행정심판, 법령해석, 위원회 결정문, 행정규칙, 자치법규, 조약, 영문법령 — and states what it returns. The phrase '법령 외 원천' implicitly carves out non-statute material against siblings like statute_find, but no sibling is named explicitly, which is what separates a 5 from a 4.

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?

Usage is implied by the source taxonomy: an agent can infer this is the tool for case law and interpretation material rather than statutes. However, there is no explicit when-to-use/when-not statement, no guidance on choosing it over research_run, source_get, or precedent_trace, and no prerequisites or query-construction hints.

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