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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint). Beyond that, the description adds provenance ('HMRC's own Integrated Online Tariff') and the nature of the results (classification path plus matching chapters/headings), which is useful context. It does not mention pagination or result-limit behavior in prose.

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 core action and return shape, then rationale and example. The caps-locked AUTHORITATIVE and PREFER OVER WEB SEARCH lines are emphatic but earn their place as routing signals. Slightly dense but no wasted sentences.

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, so the description carries the burden of describing returns — and it does: candidate codes, descriptions, classification path, chapters and headings. Combined with full annotation coverage and a complete schema, an agent has enough to call it correctly; only the sibling-tool routing is under-specified.

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%, so query, limit, and declarable_only are already documented in the schema. The description contributes only an inline example of the query format, adding marginal meaning over the schema. Baseline 3 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?

Uses a specific verb+resource ('Find the UK commodity code'), names the input mode (plain English or numeric code), and describes the return shape (10-digit codes with descriptions and full chapter→heading→commodity path). Sibling differentiation is only implicit — it hints at 'resolve a numeric code to the right endpoint' but never names uktariff_commodity or uktariff_heading.

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 explicit trigger phrases ('what commodity code is X', 'HS code for X in the UK') and a clear preference rule (PREFER OVER WEB SEARCH), which is strong routing guidance. However it never states when to use the sibling tools (uktariff_commodity, uktariff_heading) instead, 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.