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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is sourcing and cost: data is read 'live from HMRC' / official USITC search, results include a source link, and search returns at most 5 candidates. It also discloses the per-call price ($0.005), which is useful for agent budgeting and is not in any structured field. Minor gap: no mention of behavior on invalid or unmatched codes.

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 with the primary action and the fallback mode, then market coverage; the core content is dense and useful. Some promotional filler ('Built for AI agents, customs brokers and e-commerce teams who need a sourced duty rate, not a guess') and the price note could be trimmed without loss.

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, and the description does compensate by enumerating return fields for both markets (hierarchy, MFN rate, preferential rates, Chapter 99 refs, units, source link; UK adds VAT and trade remedies). It falls short only on edge cases — no behavior stated for when neither `code` nor `query` is passed, or for unmatched codes.

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%, so baseline is 3, but the description adds real meaning: it explains the `code` vs `query` trade-off (lookup vs. candidate discovery), what each returns, and how `market` selects the US vs. UK tariff source. `originCountry`, which is relevant to preferential rates, is only explained by the schema.

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?

Leads with a concrete verb+resource ('Send a US HTS code and get the official description hierarchy, the general (MFN) duty rate...') and immediately covers both operating modes (code lookup vs. description search) and both markets (US HTS vs. UK Trade Tariff). No sibling tool in the list overlaps, and the tool's scope is unmistakable after the first sentence.

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?

Explicitly routes between the two input modes with 'No code yet? Send a plain product description and get up to 5 candidate codes' and states the switch for the other market via `"market": "UK"`. There are no sibling alternatives to exclude, but it never states what happens if neither `code` nor `query` is supplied, which matters since both are optional.

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