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

Annotations already establish the safe-read profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuine provenance context—content is drawn from the official 好運器 '台灣進口報關流程指南' and current 試算規則—which hints at authority and freshness, a trait not captured by annotations. It stops short of stating update cadence or coverage limits.

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?

One dense but front-loaded sentence-pair: verb+resource first, then scope enumeration, then source, then example questions. Every clause earns its place, though the long comma-separated scope list is slightly heavy.

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?

With an output schema present, return-format explanation is not needed, and the description thoroughly defines subject-matter coverage. It does not, however, note any limitations (e.g., jurisdiction scope, whether figures are current), leaving minor gaps for a reference 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?

The tool takes zero parameters, which is the baseline-4 case; the empty schema is fully consistent with a pure knowledge-retrieval tool. The description adds no parameter meaning because none exist.

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+resource (取得...簡易申報規定) and then enumerates the exact topics covered (適用條件, C1/C2/C3, EZ WAY, NT$2,000 免稅, 半年 6 次, 營業稅 5%). An agent can immediately tell this is a regulatory-knowledge tool rather than a calculator like lucky_import_tax_estimate.

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?

Provides concrete usage context via example questions it is '適合回答' (多少錢要繳稅／什麼是簡易申報／EZWay 是什麼／C1 C2 C3 差在哪). This clearly signals when to reach for it, but it never names a sibling alternative or an exclusion (e.g., vs. lucky_import_tax_estimate or lucky_ccc_tariff_lookup), so routing against neighbors is left to inference.

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