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

Annotations only say readOnly and openWorld; the description adds material context they cannot carry: a per-call price ($0.002 USDC), the payment rails (x402 on Base, Solana or Arc), and the billing rule that failed calls are free — critical for an agent deciding whether to retry or batch. It also discloses that output is candidate headings/subheadings rather than an authoritative classification, so the agent knows the result is advisory.

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?

Three sentences, front-loaded with the action and returned fields, then the scope limitation, then pricing. Nothing is padded and each sentence carries decision-relevant information.

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, the description need not describe return shape; it still characterizes results qualitatively as candidate headings/subheadings. For a read-only, two-parameter lookup, purpose, scope limit, and cost model are all covered, leaving no gap an agent needs filled before calling.

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 both parameters are already described with examples ('8703', 'motor cars'; '1 to 20, default 5'). The description restates the prefix/keyword duality without adding syntax, format constraints, or matching behavior beyond the schema, so the baseline 3 for schema-driven parameters 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 and resource ('Finds Harmonized System (HS) codes from UN Comtrade's HS reference list') plus the two lookup axes (code prefix, description keyword) and the returned fields (code, official description, hierarchy level). It also draws an explicit boundary — 'it does not decide the legal tariff code for a shipment' — which separates it from duty calculators and tariff-consultation siblings.

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 tool's domain is clearly implied (reference lookup of HS headings/subheadings by prefix or keyword) and the exclusion 'does not decide the legal tariff code for a shipment' tells the agent when this is the wrong tool for a compliance determination. It stops short of naming the sibling to use instead (e.g. customs_duty_calc or eu_taric_consultation), so 4 rather than 5.

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