legal_research

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, covering the safety profile. The description adds valuable behavioral context beyond this: parallel API orchestration ('여러 API를 병렬로 엮는'), auto-detection of task/scenario when unspecified ('미지정 시 쿼리에서 자동 감지'), and task-specific parameter requirements (document_review requires text, query required for all other tasks). No contradiction with annotations.

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?

The description is dense but well-structured: header stating purpose, task table with pipe-separated values and examples, scenario section with compatibility mapping, and a closing alternative-guidance sentence. Every segment earns its place for a 12-parameter, 8-task, 9-scenario complex tool. Slightly compressed formatting (pipe-separated) could hinder parsing, but no word is wasted.

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?

Given the complexity (12 params, 8 task modes, 9 scenarios, no output schema), this description is remarkably complete. It covers all task types with examples, all scenarios with task compatibility, auto-detection fallback behavior, parameter requirements per task, and alternative tool guidance. The opaqueness of no output schema is mitigated by clear task-result expectations embedded in each task description. This is a model description for a composite orchestration tool.

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. The description adds significant meaning beyond the schema by mapping parameters to tasks (mst/lawId→amendment_track, domain→dispute_prep, parentLaw→ordinance_compare, articles→law_system, text→document_review, fromDate/toDate→time_travel), providing the scenario compatibility matrix, and clarifying that document_review requires text while query is required for all other tasks. This contextual binding of parameters to workflows exceeds what the schema alone conveys.

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 clearly identifies the tool as a multi-stage legal research integration tool ('다단계 법령 리서치 통합 — 여러 API를 병렬로 엮는 복합 질문 전용'), enumerates 8 distinct task types with concrete examples ('음주운전 처벌 기준', '관세법 체계', '영업정지 근거'), and explicitly distinguishes it from siblings via the closing instruction to use search_law/get_law_text for single-lookup queries. The verb+resource+scope is specific and non-tautological.

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?

The description explicitly states this is for complex questions only ('복합 질문 전용') and names search_law/get_law_text as alternatives for simple lookups. It also documents task-scenario compatibility (law_system=delegation·impact, action_basis=penalty, etc.) and auto-detection behavior. However, it doesn't explicitly address how this tool relates to other siblings like ordinance_radar, legal_analysis, or search_decisions, which could be relevant alternatives for specific tasks.

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