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

With no annotations, the description carries the full burden and does well: it discloses concrete behavioral rules the agent would otherwise not know, including the 2% borrowing ceiling, the 1.1x penalty factor, and the multi-year consecutive limit. It remains silent on return format and whether results are recomputed deterministically per call, but the regulatory constraints are substantial context.

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 dense sentence front-loads the tool's identity, then enumerates the specific computations in a scannable list. No filler or restated name.

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 specialized regulatory calculator with no output schema and 6 parameters, the description explains the domain rules but leaves the shape of the result (e.g., whether it returns an optimal banking/borrowing schedule or a scalar) unstated. Given the schema covers most params and there is no output schema to lean on, this is adequate but leaves a meaningful gap about what the agent receives back.

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 67%, so the schema already documents most parameters including the signed compliance balance and consecutive-year cap. The description adds regulatory meaning to the computation (why the 2% cap and 1.1x factor matter) but doesn't clarify the ambiguous vessel_id/reporting_year semantics or units beyond what the schema states. Baseline 3 is appropriate.

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 precise verb and regulatory resource: a deterministic solver for FuelEU Maritime Article 20 banking/borrowing, and explicitly names Article 21 pooling as the alternative it compares against. This distinguishes it from sibling tools like optimize_fueleu_pool_allocation and calculate_fueleu_maritime_penalty.

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 mention of 'optimal arbitrage vs Article 21 pooling' implies when this tool is relevant (deciding between banking and pooling), but there is no explicit when-to-use vs when-not-to-use guidance or prerequisites. It routes loosely but doesn't state conditions for selecting this over calculate_fueleu_maritime_penalty.

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