판례·결정례 검색

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

Annotations already cover read-only, idempotent, open-world, non-destructive, so the description only needs incremental behavior. It delivers: the non-obvious default that precedent search matches case names only, and the includeText/detailLimit toggle needed for full body text. Pagination, result caps, and response shape are not described, keeping 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 unified-search premise, and every subsequent sentence carries routing or mode-selection information. Deducted for re-listing all 21 domain names parenthetically, which duplicates the enum, and for a dense single block with no structure that makes the search-mode distinction easy to miss.

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-object tool with no output schema, the description covers the hard parts: domain routing, name-vs-body search modes, and text inclusion. It leaves page/display/sort behavior and the differing result shapes across the 21 domains to the schema or the agent's discovery.

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%, but the enum values are cryptic strings ('iaciac', 'eiac', 'moel'), and the description does the real work of translating them into sources. It also documents options.includeText and options.detailLimit, which appear nowhere in the schema's options description (only additionalProperties: {} allows them) — genuine value beyond structured fields.

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 opens with a specific verb+resource (통합검색) and states the exact scope: 21 named Korean legal domains in one call, with the domain parameter selecting the corpus. It also distinguishes the body-text variant ('판례 본문까지 필요하면 domain=precedent, options.includeText=true'), so an agent can tell it apart from get_decision_text without opening a schema.

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?

Strong routing guidance: it maps real-world needs to specific enum values (국세청 해석 → nts, 고용노동부 질의회시 → moel, 산재보험 재심사 → iaciac, 고용보험 재심사 → eiac) and explains that precedent search defaults to case-name lookup, so doctrinal or fact-pattern exploration needs options.search='both'. It stops short of naming sibling tools (get_decision_text, search_law) as explicit alternatives.

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