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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so safety is covered. The description adds genuinely behavioral context: it fans out to multiple APIs in parallel and auto-detects scenario from the query when unspecified, which tells the agent to expect higher latency and broader output. It does not warn about response-size limits in the description body itself (the #158 truncation caveat lives only in the includeHistory parameter).

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 core distinction — complex parallel research only — is front-loaded before the enumeration, which is the right ordering. The pipe-delimited task/scenario list is dense but information-bearing rather than padded; it is long, though, and the scenario guidance spills into a second clause that could be tightened.

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 13-parameter aggregator with no required params, the description does the hard work of explaining which task/scenario combinations are legal and coherent. With no output schema, the return shape (what sections a full_research vs. amendment_track response contains) is left entirely unspecified — the one meaningful gap for a tool that merges many sources.

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% and each parameter is already tagged with its governing task, so the schema carries most of the load. The description still adds value by supplying the per-task examples that the task enum's own description explicitly defers to ('도구 설명의 task 표 참조') — without the description the enum would be much less interpretable.

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?

States a specific verb and resource (다단계 법령 리서치 통합) and immediately constrains scope to '복합 질문 전용' — questions that require stitching multiple APIs in parallel. The eight enumerated tasks with concrete example queries make it unmistakable that this is the orchestrator, not a single-lookup sibling like search_law or get_law_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?

The task table is effectively a routing guide: each task names a question shape and an example, and it declares full_research as the fallback for unclear natural-language queries. Scenario compatibility per task is spelled out in the enum description. What's missing is an explicit statement of the negative case — that simple single-law lookups should go to the lighter siblings instead.

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