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

No annotations are provided, so the description carries the full behavioral burden. It does disclose the data source (official TFDA-published violation records), which implies a read-only, authoritative lookup, but says nothing about freshness/staleness of the data, result limits, or what a hit vs. no-hit means.

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?

Two compact clauses with the category tag front-loaded and the usage cue second; nothing is redundant. Slightly denser than ideal for a non-Chinese-reading consumer, but no wasted sentences.

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 two-optional-parameter read lookup with 100% schema coverage, the description covers the what and the when. However, with no output schema, it never sketches what the response contains (record fields, violation type, penalty, etc.), leaving the return shape entirely unknown.

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 description coverage is 100%, so both params (days default 180, keyword for product or vendor name) are already fully documented in the schema. The description adds no additional meaning about how days or keyword interact, so the baseline 3 applies.

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 (查詢/query) and resource (台灣食藥署公布的違規食品廣告) plus the violation scope (誇大療效等), so the agent knows exactly what dataset is being read. It does not explicitly differentiate from nearby tools such as creator__check_ad_claims or health__check_product_safety, which is the only thing keeping it from a 5.

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?

Gives an explicit trigger condition — use when the user asks whether a health-food advertisement is legal — which maps directly onto a real user phrasing. It offers no negative guidance or named alternatives (e.g. when to prefer creator__check_ad_claims instead), so it stops short of a 5.

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