판례·결정례 검색

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds a non-obvious behavioral default that the annotations cannot convey: precedent search defaults to case-name matching only, so body/fact-pattern searches silently miss results unless options.search is changed. It does not discuss result limits/truncation behavior or error cases, so it falls 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?

Purpose is front-loaded and nearly every clause carries information, but the description is one long run-on sentence packed with parenthetical enumerations. The 23-domain list in the opening sentence and repeated field lists consume space that could be structured as domain→option pairs, making it harder to scan under time pressure.

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, nested-options, 23-domain tool with no output schema, the description covers the decision-critical parts: which domain to pick, when to enable body search, and which nested options exist. It does not describe the shape of returned results or how paging/sort codes behave across domains, which leaves a residual gap.

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 earns above baseline because the options object is a loosely typed bag (additionalProperties: {}) and the description supplies the actual per-domain option keys and value encodings (search 1/2/'both', ministry code requirement, explYd, gana, caseNumber, etc.). It also mentions options.includeText and options.detailLimit, which are not documented in the schema at all.

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 states a specific verb+resource: an integrated search across 23 Korean-law domains, with the domain parameter choosing the source. It explicitly enumerates the domain families (판례, 해석례, 헌재, 행심, 조세심판, 관세, 부처 해석, 재심사 재결 등), which makes it clearly distinguishable from siblings such as search_law and get_decision_text.

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 routing guidance that would otherwise require guessing: domain='precedent' plus options.includeText for full text, options.search='both' when the agent wants legal reasoning/fact patterns rather than case-name matches, and explicit source-to-domain mappings (NTS replies → 'nts', labor ministry → 'moel' with search=2, local tax → 'mois', all other ministries → 'ministry' with a ministry code, industrial-accident review → 'iaciac', employment-insurance review → 'eiac'). That is when-to-use-which guidance in concrete terms.

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