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

Goes well beyond the readOnly/idempotent/openWorld annotations by disclosing that this is a keyword table rather than a binding classification, that results must be confirmed before filing, and full access mechanics: $0.005/call over x402 on Base, prepaid x-credit-token header for unlimited use, 1 free call/day, no API key needed. That is exactly the behavioral context an agent needs before deciding to spend on a call.

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?

Front-loaded transformation statement followed by the caveat, required input, and payment model — all in a short block with no filler. The payment detail is long but load-bearing for a paid tool, so it earns its space; slight density cost keeps it from a 5.

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?

An output schema exists, so return-value explanation is unnecessary, and the description covers the remaining gaps: scope of the hint (non-binding), input requirement, and the full auth/billing path. Nothing an agent needs to invoke this correctly is missing.

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?

Only one parameter, and schema coverage is 100%, so the schema already documents 'q' as a string product description. The description merely restates 'Required input: q' without adding format, length, or language constraints. Baseline 3 is appropriate when the schema does the work.

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 transformation (product text → HS chapter/heading hints) with a concrete resource and examples (electronics, apparel, coffee, pharma). It also immediately scopes the claim ('keyword table only — not a binding customs classification'), so the agent knows exactly what class of output to expect. No sibling tool overlaps this space, so differentiation is inherently satisfied.

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?

It gives clear usage context ('confirm before filing', implying pre-classification triage) and explains the required input up front. It does not name an alternative tool or an explicit when-not-to-use condition, but there is no close sibling to route against, so the guidance is effectively complete.

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