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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds genuinely new behavioral detail by disclosing accepted input breadth (4-10 digits, i.e. short headings through full statistical suffixes) and by enumerating what the response contains (description, units, three duty-rate columns). It does not mention error behavior for invalid or unknown codes, which is the main remaining gap.

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?

Two short sentences with no filler; the zero-cost signal is front-loaded and the payload contents are stated compactly. The 'Free.' fragment is terse to the point of being slightly abrupt, but it earns its place by removing a cost concern before the agent reads further.

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?

There is no output schema, so the description carries the burden of describing returns, and it does so by naming the three rate columns and the unit/description fields. For a one-parameter read-only lookup this is nearly sufficient; only failure modes for unknown codes are left unaddressed.

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 the single parameter is documented with an example, so the baseline is 3. The description earns the extra point by adding a length range constraint (4-10 digits) that the schema does not express, telling the agent that truncated codes are acceptable input.

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 specific verb-and-resource pair — retrieve the description, units, and duty rates for a single HTSUS code — and the limited scope ('an HTSUS code', singular) implicitly contrasts with a search-style sibling. What's missing is an explicit statement separating it from hts_search or calculate_duty, so an agent must infer that this is a point lookup by exact code rather than a query.

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?

Usage is only implied: an agent can reasonably conclude this is the tool for looking up one known code, but nothing states when to prefer it over hts_search or when calculate_duty would be the right follow-up. No prerequisites (e.g., code must be valid/known beforehand) or exclusions are given.

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