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

With no annotations the description carries the full burden and does substantial work: it discloses the third-party provider (Atlas Data), a 24 h cache, the 0.03 USD per-call price via x402, the underlying regulation/benchmark sources, and an estimate caveat for the unpublished 2026-Q4 price plus a 'not legal advice / not binding' disclaimer. It stops short of describing error behavior or the shape of the response.

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?

The core purpose is front-loaded in the opening clause before the regulatory citations and disclaimers, and every sentence carries real information (coverage limits, cost, caching, legal caveat). It is dense and long, but not padded.

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?

For a 9-parameter tool with no output schema, the description covers data sources, coverage boundaries, pricing, caching, and an explicit estimate caveat, which is close to complete. The main gap is that it only gestures at return values ('certificates and cost per import line') without describing the per-line output fields an agent would receive.

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 the schema already documents all 9 parameters in detail, making 3 the baseline. The description adds only light context — that productionRoute normally comes from the default-value table and that the carbon price is a 'simplified Art. 9 deduction' — but does not explain the interrelationship of items vs lines vs the singular default fields.

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 resource (EU CBAM certificates and cost estimate) and the exact scope (up to 20 import lines of CN code/country/tonnes/date) plus the secondary mode ('or list the quarterly certificate prices'). This is unmistakably distinct from every sibling tool in the list (vat, sanctions, co2, etc.).

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?

Clearly frames the calculation context and the two modes, and states a hard exclusion ('Electricity is not covered'), which is genuinely useful usage guidance. It does not name an alternative tool or spell out when a caller should prefer listPrices mode over calculate, so it stops short of explicit when/when-not routing.

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