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 enumerates exactly what is returned (attained/required/reference CII, four boundaries, current and all-year ratings, corrective-action-plan flag, every IMO parameter with citation) and discloses strict validation behavior — unknown fields, ship types and fuels are refused with an error naming the field. It omits whether the computation is deterministic/pure and any statement about side effects, which keeps it short of a 5.

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 description is front-loaded — purpose first, then required inputs, then return payload, then optional corrections and validation behavior. Every sentence carries information, though the input-listing sentence is somewhat redundant with the enum and schema descriptions and could be trimmed.

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, and the description compensates fully by detailing the returned metrics, the all-years rating behavior, the corrective-action-plan determination, and the citation output. For an 8-parameter tool with a nested fuel array and a nested corrections object, the description covers input expectations, error behavior, and output shape without gaps.

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%, so the 3 baseline applies, but the description goes beyond it by explaining the capacity basis rule (deadweight vs gross tonnage) in prose, tying previous_ratings to the three-consecutive-D corrective-action-plan rule, and enumerating the optional G5 correction families (voyage adjustments, electrical/boiler deductions, reefers, STS/shuttle tankers). These are semantic relationships between parameters, not restatements of the schema.

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 first sentence names a specific regulatory computation (IMO CII plus A–E rating for 2023-2030) and anchors it to MARPOL Annex VI reg. 28 and G1–G5, which immediately separates it from the emission-factor siblings like calculate_activity and calculate_freight. An agent can identify the resource, the output, and the domain without opening the schema.

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?

It states the concrete inputs needed to invoke it (ship type, capacity basis, distance, fuel by fuel) and flags the optional G5 correction path, so the entry conditions are clear. It also notes the 'Not pinnable with as_of' constraint. However, it never names an alternative sibling or an exclusion case (e.g. when to prefer calculate_freight or calculate_activity for voyage emissions), so routing is implied rather than explicit.

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