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

Annotations already cover safety (readOnlyHint=true, openWorldHint=false), and the description adds material behavior the annotations do not: a $0.15 USDC x402 charge per call, the exact unpaid-call behavior (returns payment requirements), and the two retry mechanisms (X-PAYMENT/PAYMENT-SIGNATURE header or params._meta["x402/payment"]). The remaining gap is the response shape, but no output schema exists so this is a meaningful omission rather than a covered one.

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 scope statement and the exclusions are front-loaded, so an agent learns the boundaries before the payment mechanics. The billing and retry sentences are dense but each carries operational necessity. The duplicated Chinese sentence conveys no information beyond the preceding English exclusion clause and is the one wasted element.

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?

No output schema exists, so the description must convey the return shape; it does so in outline by describing rows of base HTS data plus a Chapter 99 sample. Payment failure and retry paths are fully specified, which is the highest-risk behavior for this tool. Only the response structure (fields, ordering, whether 'layers' are separate rows) and the undocumented limit parameter remain unclear.

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 sits at 50%: query is documented as 'HTS code or English product keyword' while limit has no description. The prose adds no parameter-level meaning beyond that — it never clarifies accepted code formats (e.g. 6- vs 10-digit HTS) or what limit constrains. With half the parameters documented by the schema, the baseline of 3 is the right landing point rather than a penalty.

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 names a concrete resource and scope: 'USITC base HTS rows plus a Chapter 99 (9903.88) China-related additional-duty sample,' which tells an agent exactly what data comes back. It also fences the scope with 'not total China-origin duties, not Section 301 product mapping, not AD/CVD or exclusions.' It stops short of naming the sibling us_hts_tariff_lookup or explaining how the two differ, so it falls one step below the top score.

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 'INFORMATIONAL ONLY' framing and the three explicit exclusions imply when the tool is appropriate (rough duty-layer orientation, not compliance determination). However, no positive when-to-use trigger is given, and the nearest siblings (us_hts_tariff_lookup, trade_compliance_pack, landed_margin) are never referenced, leaving the agent to infer which tool to reach for.

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