Bindler regulatory calculators

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 substantive behavior: coverage of all six Annex I sectors, credit for carbon price already paid in the origin country, and pricing the same basket across years for trajectory visibility. It does not state determinism, idempotency, or failure modes for invalid sectors, so it falls 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?

Front-loaded with the core action and regulation, then splits scope and rationale. The middle sentence is a dense run-on bundling three capabilities, which slightly reduces scannability, but there is essentially no filler text.

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 deterministic computation tool with a fully documented schema and no output schema, the description covers inputs, domain scope, and the uncertainty it removes. It leaves open the shape of the returned cost breakdown, but nothing required to invoke it correctly 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%, so the schema already documents year, sector enum, and the certificate price requirement. The description adds mild meaning by tying origin_carbon_price_eur_per_tonne to a paid-in-origin credit and framing certificate_price as market-tracking, but does not deepen syntax or units beyond the schema. Baseline 3.

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 specific verb ('Compute') and a precisely-scoped resource (CBAM certificate cost of importing goods into the EU), anchored to named regulations and a year range. It is unmistakably distinct from the unrelated siblings eu_ai_act_classify and uae_corporate_tax.

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?

Explicitly directs use ('Use this rather than estimating') and explains why ('the phase-in factor changes every year and is the figure most often wrong'). It does not name a specific alternative tool or state exclusions, but the sibling set is unrelated, so this is strong contextual guidance.

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 discloses the shape of the result (risk class, obligation set with article numbers, application date, fine ceiling) and implies deterministic rule application over recall, but says nothing about determinism, versioning of the regulation, permissions, or rate limits. Output content is covered; operational behavior is not.

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, each earning its place: purpose and return values first, scope of coverage second, usage guidance third. No filler and the most decision-relevant content is front-loaded.

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 10-parameter tool with no output schema, the description compensates by enumerating return values and the regulatory scope covered. It lacks detail on ambiguous inputs (e.g. how role interacts with prohibited practice) and output structure, but an agent has enough to call it correctly and interpret the answer.

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 70%, so the schema already documents most parameters, and the description adds no parameter-level syntax or format detail beyond the enum lists in the schema. It does supply framing that maps to key inputs -- Article 6(3) exemption, Annex III, staggered application dates -- which slightly reinforces their meaning.

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 and resource ('Classify an AI system under Regulation (EU) 2024/1689') and enumerates the exact outputs returned: risk class, obligation set with article numbers, application date, and maximum fine. It also scopes coverage to Articles 5, 6/Annex III, 53, and 50, which no sibling tool (cbam_cost, uae_corporate_tax) overlaps with.

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 an explicit when-to-use rationale -- 'Use this rather than recalling the classification' -- and justifies it by naming the error-prone parts (Annex III list, Article 6(3) exemption, staggered dates). It stops short of naming a sibling alternative or stating exclusions, but the guidance is clear and actionable.

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 the return format (line-by-line with the Article cited per line), which is real behavioral context. However, it says nothing about determinism, side effects, required vs. optional inputs, or how unspecified/optional parameters are defaulted, leaving meaningful gaps for a computation tool.

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 sentences, front-loaded with the purpose before the rule list, and every clause adds substantive domain information rather than filler. It is dense and slightly long, but no sentence is wasted.

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 23-parameter financial computation with no annotations and no output schema, the description adequately covers the conceptual output (line-by-line computation with Articles) and the main rules, but leaves the majority of input parameters undefined and gives no guidance on defaults or error behavior. Minimum viable, with clear 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 description coverage is only 35% across 23 parameters, so the description must compensate, but it only touches concepts mapping to a subset (revenue/SBR threshold, QFZP de minimis, interest limitation, loss relief). Many parameters (interest_income, foreign_tax_credit, fines_and_penalties, participation_exemption_income, depreciation_and_amortisation, member_of_a_multinational_group, etc.) are unexplained in both schema and description, so it does not close the coverage gap.

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 specific verb and resource ('Compute UAE Corporate Tax payable for one tax period') and names the governing law (Federal Decree-Law 47 of 2022). It also specifies the output shape ('full computation line by line with the Article behind each line'), so an agent can tell instantly this is a deterministic tax computation, distinct from the unrelated siblings cbam_cost and eu_ai_act_classify.

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?

Explicitly says 'Use this instead of estimating UAE Corporate Tax' and explains why the tool is preferable (thresholds and the SBR/QFZP/interest-cap interaction are 'commonly got wrong'). This gives a clear trigger for use, but it does not name alternative tools or state when NOT to use it (e.g., non-resident or non-Federal-Decree scenarios).

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