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

Annotations specify readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false. The description adds valuable context: 'deterministic', 'pinned official fixtures', 'without provider calls', 'no automatic legal decision', and the cost/payment mechanism ($0.02/call, x402 USDC on base). It does not contradict the annotations; while it doesn't fully disclose potential side effects of a non-read-only operation, the 'calculate/get' wording and demo mode suggest computation rather than external mutation.

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 compact and front-loaded: three sentences cover purpose, inputs, method, outputs, and even pricing/payment. Each sentence carries new information and there is no filler or redundancy. This is an optimally concise yet informative description.

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 complex tool with six parameters and no output schema, the description gives a useful overview of output categories (gas, fuel, segment, truth-ledger, confidence, limitation, receipt evidence) and clarifies it is not a legal decision provider. It omits explicit mention of runtime modes (decision vs synthetic_demo) and cross-field validation rules, but the detailed input schema covers those, so the combination is sufficiently complete for an agent to invoke it correctly.

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?

The input schema has 100% description coverage, with each parameter fully documented (patterns, enums, constraints, formats). The description adds little parameter-specific detail beyond a high-level characterization of inputs as 'buyer-supplied vessel, route, and fuel facts', which is already implied by the schema. It meets the baseline for heavily described schemas but does not compensate or augment the schema meaningfully.

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 description opens with a specific verb 'Calculate' and a clear object ('deterministic EU ETS voyage exposure'), names inputs ('buyer-supplied vessel, route, and fuel facts') and method ('pinned official fixtures'). It then enumerates output types (gas, fuel, segment, truth-ledger, confidence, limitation, receipt evidence), which clearly distinguishes it from sibling tools that cover unrelated maritime/trade domains (e.g., panama-canal-queue, strait-of-hormuz).

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 conveys a clear use-case: calculating EU ETS exposure from buyer-supplied facts, and explicitly notes it operates 'without provider calls or an automatic legal decision', which defines appropriate vs. inappropriate use. However, it does not name alternative tools or provide an explicit 'when not to use' list beyond those boundaries, making the guidance clear but not exhaustive.

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