UNE Maritime Decarbonization & Compliance Gateway

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.

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

With no annotations, the description carries the full burden, and it does disclose genuinely useful behavior: the Annex IV formula and the EUR 2,400/tonne VLSFO-equivalent reference rate. However, it omits the effect of consecutive_non_compliant_years (a statutory penalty multiplier), how voyage_scope affects the applied share, and whether an api_key is required, which are material for correct invocation.

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?

Two tightly packed sentences that lead with the outputs and then the governing formula. The second sentence restates the rate already embedded in the formula, which is mild redundancy, but there is no filler.

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 5-parameter tool with zero annotation coverage, zero schema description coverage, and no output schema, the description is not complete. An agent cannot determine parameter semantics, the non-compliance multiplier behavior, or the auth requirement from this text alone.

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 0% across 5 parameters, so the description must compensate and largely does not. It references 'deficit_gCO2eq' and 'actual_intensity', which are not even schema parameters, while leaving fuel_type, fuel_mass_metric_tonnes, voyage_scope, consecutive_non_compliant_years, and api_key completely unexplained.

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 names a specific verb (calculates) and three concrete outputs: FuelEU Maritime compliance balance, GHG intensity deficit, and statutory cash penalties. That is clearly distinct from siblings like calculate_fueleu_banking_borrowing or calculate_maritime_ets_surrender, though it never explicitly routes the agent away from them.

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?

There is no when-to-use, when-not-to-use, or alternative-tool guidance. The agent must infer from the tool name alone whether this is the right penalty tool versus the ETS surrender or banking/borrowing calculators.

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

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

With no annotations, the description carries the full burden, and it does contribute real behavioral content: the statutory phase-in rates (40/70/100%) disclose that the result is year-dependent, which is genuine context beyond a restated name. However, it never states that this is a pure, side-effect-free calculation, nor what it returns (EUA quantity vs. monetary exposure), leaving key behavioral gaps.

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 that front-loads the verb and resource, then adds the phase-in schedule as supporting detail. No filler, no redundancy.

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 5-parameter calculation tool with no annotations and no output schema, the description grounds the regulation and the year rates but says nothing about the return value (EUA count, EUR cost, or both) or units/precision. It is usable but not fully self-sufficient.

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 only 20%, so the description would ideally explain the other four parameters; instead it only reinforces reporting_year (already documented in the schema). The enum values (VLSFO/HFO/MGO/LNG/B24/B30, INTRA_EU/EXTRA_EU) and field names are largely self-evident, and the phase-in rates add year semantics, which keeps this at an adequate baseline rather than worse.

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?

Names a specific verb ('Calculates') and a precise resource ('EU ETS Maritime allowance (EUA) surrender obligations'), anchored to Directive (EU) 2023/959. The ETS framing implicitly separates it from the FuelEU-prefixed siblings, but it never states that distinction explicitly, so an agent that only skims could still confuse it with 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?

There is no when-to-use guidance, no exclusions, and no pointing to an alternative sibling. The regulatory scope and phase-in years hint at applicability, but the agent must infer the conditions under which this tool rather than the FuelEU penalty/banking tools is the right call.

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

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

With no annotations, the description carries the full burden, and it does add domain context: the results are 'certified' and 'aggregated', and the tool applies FuelEU Annex I rules with Article 2 scope validation. However, it says nothing about whether this is a pure computation or persists state, what permissions are needed, or how validation failures surface, leaving meaningful behavioral gaps for a tool with zero annotation coverage.

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 front-loaded sentence with no filler; the computed outputs are listed early and the regulatory scope follows. It is dense but every clause earns its place, with only minor loss of readability from packing three output metrics and two regulatory references into one sentence.

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 no-annotation, no-output-schema calculation tool the description usefully names the three output quantities, which partially substitutes for a return schema. Still missing are permission/state assumptions and any indication of how scope-validation failures are reported, so an agent has an incomplete picture of calling behavior.

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%, above the 50% baseline, so the schema documents ports, fuels and voyage scope reasonably well. The description adds only the notion of 'multi-leg voyages' (mapping to voyage_legs) and the returned metrics; it contributes no syntax or format detail beyond what the schema already provides, so the baseline 3 applies.

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 states a specific verb (calculates) and names three concrete output quantities (Well-to-Wake GHG intensity in gCO2eq/MJ, energy consumption in MJ, net compliance balance in tCO2eq) scoped to multi-leg maritime voyages under FuelEU Annex I. This clearly distinguishes it from siblings like calculate_fueleu_maritime_penalty and calculate_maritime_ets_surrender, though it never names an alternative explicitly.

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?

There is no when-to-use or when-not-to-use guidance and no mention of sibling tools, so an agent cannot tell from the description alone whether this should be called instead of calculate_fueleu_maritime_penalty or calculate_fueleu_banking_borrowing. The 'Article 2 scope validation' phrase hints at a domain constraint but gives no routing instruction.

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

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

With no annotations, the description carries the full behavioral burden. It usefully states that results are 'deterministic' and sourced from statutory FuelEU Maritime Annex II default tables, but it does not explicitly confirm read-only behavior, authentication needs, rate limits, or the response structure.

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 definition is a single front-loaded sentence with no wasted words. It names the metric families and data source directly, and is appropriately sized for a simple one-parameter lookup.

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 simple reference lookup with one fully documented parameter and no output schema, the description gives enough context: the metric types returned and the statutory data source. It could still mention units or response shape, but nothing essential to invocation is missing.

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%, and the single fuel_type parameter is already well documented with an enum and regulatory reference. The description adds no parameter-specific meaning beyond what the schema provides, so the 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?

The description gives a specific verb ('Returns') and resource ('statutory WtW, WtT, TtW, and LCV metrics from FuelEU Maritime Annex II default tables'), so the agent knows exactly what data is retrieved. It does not explicitly differentiate from the sibling calculation tools, but the lookup-versus-calculate distinction is implicit.

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?

Usage is implied: the tool returns statutory default-table emission factors, so an agent would infer it is used for reference values rather than voyage-specific calculations. No explicit when-to-use guidance, alternatives, or exclusions are provided, so it remains only minimally adequate.

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

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

No annotations are provided, so the description carries the full burden. It usefully discloses that the solver is deterministic and that it returns pool composition, 'verified statutory savings under Annex IV,' and governance flags. However, it never states whether it creates the 'certified transfer manifests' implied by the api_key parameter, nor any auth, rate-limit, or side-effect behavior.

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?

Three sentences, front-loaded with the core purpose followed by inputs/outputs and an audience note. It is compact, though the final sentence on Chinese/European shipowners is closer to positioning than operative instruction.

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 and no annotations, the description does cover what the tool returns at a high level. But for a solver whose nested 'ships' input and 'pooling_strategy' enum drive behavior, it omits parameter-level meaning and any statement of side effects or auth, leaving meaningful gaps for correct invocation.

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?

At 50% schema coverage, the description compensates partly by mapping the 'ships' array to 'compliance balances and market prices for compliance surplus,' matching the schema fields. But it says nothing about 'pooling_strategy' (whose GREEDY_COST_MINIMIZATION vs PRO_RATA distinction is unexplained anywhere), 'reporting_year', or how 'api_key' changes output, leaving the alternate strategy opaque.

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 states a specific verb ('Deterministic solver'), the exact regulatory basis (FuelEU Maritime Article 21 pool optimization), and the outputs (optimal pool composition, statutory savings, governance flags). This clearly separates it from the calculation siblings (banking/borrowing, penalty, ETS surrender, intensity), though it never names an alternative explicitly.

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 occasionally frames intended users ('Chinese and European shipowners operating on China-Europe routes') but gives no when-to-use guidance, no conditions that select it over 'calculate_fueleu_banking_borrowing' or the penalty/ETS siblings, and no exclusions. An agent must infer that this is the multi-vessel pooling path.

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

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

No annotations are provided, so the description carries the full burden. It mentions a free sandbox key with 50 credits, hinting at a rate/credit limit, but doesn't state whether the key is provisioned immediately, whether it expires, what happens on failure, or any authentication requirements.

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 efficient sentence that front-loads the core action and key detail (50 credits). Slightly dense with marketing language but no structural issues.

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?

Given two well-described parameters and no output schema, the description is minimally adequate. It doesn't explain the return (e.g., key format, delivery method) or any behavioral traits beyond the credit amount, leaving some gaps for correct invocation.

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% with clear descriptions for developer_email and use_case. The description adds no parameter-level detail beyond the schema, so baseline 3 applies.

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 states a specific action (provision a free sandbox API key) and quantifies the resource (50 credits), distinguishing it from sibling calculation tools which are all analytical.

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?

There is no guidance on when to use this tool versus alternatives, no mention of prerequisites (like whether a corporate email is needed or a sandbox vs production intent), and no exclusions. Implied usage only.

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