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

The annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety needs no restating. The description instead adds genuine behavioural context: the regulatory basis (Reg (EU) 2023/956), the exact decomposition of the calculation (Art. 31 adjustment, CBAM factor times the Reg (EU) 2025/2620 benchmark), and the currency of the cost output in EUR. It stops short of stating assumptions, rounding, or what happens when the CN code is outside CBAM scope.

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?

A single sentence with the verb and output set front-loaded and no filler. It is dense with regulatory parentheticals, which marginally hurts first-pass readability but every clause carries substantive information.

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?

With no output schema, the description compensates by enumerating exactly what is returned (emissions, free allocation adjustment, certificate count, euro cost), which is the key missing structured data. Given fully described parameters and strong annotations, the definition is nearly self-sufficient; the only real gap is the unmentioned optional carbon price parameter and any preconditions tied to cbam_scope.

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 all five parameters are already documented and the baseline of 3 applies. The description restates the four required inputs (including the 2026-2034 year range already in the schema) but omits the optional carbonPricePaid Art. 9 deduction entirely, adding no semantic depth beyond what the schema provides.

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 the specific verb 'Calculate' with a precise multi-part resource: embedded direct and indirect emissions, the Art. 31 free allocation adjustment, required CBAM certificates, and total euro cost. The scope is anchored to a named regulation and to four concrete input dimensions, which clearly separates it from the sibling tools (defaults, scope, price, changes, status).

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?

The description makes the call context clear (an imported product, given CN code, origin, tonnes and year), so usage is implied rather than ambiguous. However, it never routes the agent between this tool and siblings like cbam_defaults or cbam_certificate_price, and gives no when-not conditions or prerequisites such as whether the product must first be confirmed in scope via cbam_scope.

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