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

Annotations only declare readOnlyHint and openWorldHint, so the description carries and delivers real behavioral value: it discloses return contents (description, chapter, validity dates, declarable flag, basic duty rate), the null-when-empty edge case, the coverage limitation on duty measures, and – critically – the paid-call model ($0.002 USDC via x402 on Base/Solana/Arc, failed calls not charged). That payment and failure-charging detail is exactly the kind of pre-invocation context an agent needs and cannot get from annotations or schema.

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?

Purpose and return contents are front-loaded, followed by the coverage caveat, with pricing tucked into the final sentence – a logical order. It is dense but every clause carries information; slight density in the return-field enumeration 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 the description need not document full return structures, yet it still summarizes the key fields, flags the null duty-rate case and the unexpanded per-partner measures, and explains billing. For a single-parameter read-only lookup, nothing an agent needs to call it correctly or anticipate cost 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?

Schema description coverage is 100% and the schema already supplies the 10-digit format with an example (0901110000) and the 'existing leaf code' constraint. The description's '10-digit commodity code' restates rather than extends that, so per the coverage rule the baseline of 3 is appropriate.

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+scope: 'UK Global Tariff commodity lookup by 10-digit commodity code from the official UK Trade Tariff API'. An agent can immediately distinguish this from siblings like logistics_eu_taric_consultation, logistics_china_customs_tariffs, or logistics_world_customs_tariff_wits by the UK-specific jurisdiction and the 10-digit leaf-code requirement.

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 clear operative context – 10-digit leaf code required, and explicitly warns 'Full duty measures per trading partner are not expanded', which tells the agent when this tool is not sufficient. However, it does not name the alternative siblings (e.g. logistics_customs_duty_calc, logistics_hs_code_classifier) that should be used instead for per-partner duty measures or code classification, leaving that inference to the agent.

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