NZ Data API

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

Annotations already indicate a safe, closed read operation, and the description adds important behavioral context: it is a paid x402 tool costing $0.001 USDC on Base, an unpaid call returns PaymentRequired, and retry requires _meta["x402/payment"]. This is exactly the kind of operational detail an agent needs before invoking it.

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 a compact single paragraph that front-loads the purpose, then explains the payment requirement, then gives an example. Every sentence carries useful information for an agent deciding whether and how to call the tool.

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 read-only calculator with full schema coverage and annotations, the invocation details are essentially complete. The main missing piece is that no output schema exists and the description does not say what the return value looks like, though this is a minor gap for a straightforward GST calculation.

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 schema already documents both parameters. The description still adds value by clarifying that mode accepts 'exclusive or inclusive' and by showing a complete argument object, although it does not explain the amount format or rounding behavior beyond the schema example.

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 exactly what the tool computes: NZ GST at 15%, with exclusive or inclusive modes. This is specific enough to distinguish it from the sibling validation and working-day tools without opening any 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?

The description implies the tool is used for GST calculation and shows example arguments, but it does not explicitly say when to use it versus alternatives or when not to use it. Since the sibling tools serve unrelated validation/date purposes, the gap is mild but still present.

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?

Annotations only declare readOnlyHint=true and openWorldHint=false, so the description carries real weight by disclosing the paywall: $0.002 USDC on Base per call via x402, the PaymentRequired failure mode for unpaid calls, and the exact retry mechanism (_meta["x402/payment"]). That is exactly the kind of auth/cost context an agent needs and cannot get from the schema.

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 dense sentences, front-loaded with the resource and scope before the payment mechanics. Nothing is padded and 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?

No output schema exists, so the description would ideally hint at the return shape (holiday names/dates). It also leaves the zero-required-parameter behavior unexplained — whether omitting year returns all years or a default year is unclear. Adequate but with clear gaps for a tool whose result format is undocumented.

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%, though the schema entries are thin ('e.g. 2026', 'e.g. auckland'). The description's example args reinforce the expected format (lowercase region slug) but add no meaning beyond what the schema already conveys, 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?

States a specific resource (NZ public holidays) with an explicit scope (2022-2030), naming the distinguishing coverage (Matariki, Mondayisation, optional regional anniversary day). This clearly separates it from siblings like nz_working_days and nz_working_days_add, which compute workday counts rather than list holidays.

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 by the year/region example args, and the payment retry instruction is genuinely actionable operational guidance. However, it never states when to pick this over nz_working_days or nz_working_days_add, and there are no exclusions or prerequisites beyond payment.

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?

Annotations only cover readOnly and openWorld, so the description carries real behavioral weight: it discloses the paid model ($0.001 USDC on Base via x402), the failure mode (unpaid call returns PaymentRequired), and the exact remedy (retry with _meta["x402/payment"]). That is exactly the non-obvious operational context an agent needs before invoking.

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?

Purpose is front-loaded, followed by payment mechanics and an example arg. Every sentence earns its place, though the trailing example args string partially duplicates the schema's example field.

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 single-parameter tool with no output schema, the description supplies the missing pieces: it hints at the return content (validation result, normalised number, bank code) and fully explains the payment flow. Adequate and slightly above minimum for this complexity level.

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 baseline is 3, but the description goes further by decoding the expected format as BB-bbbb-AAAAAAA-SSS and supplying a concrete example arg, which clarifies what a valid input looks like beyond the schema's bare 'e.g.' sample.

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 (validate) and resource (NZ bank account number check digit), and enumerates the actual operations: check-digit validation via IRD algorithms A-G/X, normalisation to BB-bbbb-AAAAAAA-SSS, and bank-code identification. This clearly separates it from siblings like nz_validate_ird and nz_validate_nzbn, which validate different identifier types.

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 narrowly scoped purpose makes usage strongly implied (feed it a bank account number to validate it), but there is no explicit when-to-use statement, no prerequisites, and no direct routing against sibling validators such as nz_validate_ird. Guidance is inferred rather than stated.

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?

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description goes beyond them by disclosing the x402 payment requirement, the exact price, and the concrete recovery path (_meta["x402/payment"]) after a PaymentRequired response. That is meaningful behavioral context; what is missing is what the tool returns for a valid vs. invalid number.

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 purpose, followed by payment mechanics and a worked example in a compact single paragraph. The example duplicates the schema's own example, which is the only wasted element.

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, so the description should describe the return value (boolean? check-digit detail? error shape for malformed input) and it does not. Payment behavior is covered well, but the result semantics an agent needs to interpret the call are absent.

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 schema already carries the example '49091850', so the description's example args duplicate rather than extend the schema. With one fully documented parameter, 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?

States a specific verb ('Validate') plus a precise resource ('NZ IRD/GST number check digit'), and the resource type cleanly distinguishes it from siblings like nz_validate_bank, nz_validate_nzbn, and nz_validate_phone. An agent can route to it without opening any 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?

Usage is implied by the name and the single 'number' argument, and the description does surface a genuinely useful operational fact (cost per call, payment failure behavior). However, it never states when to prefer this over a sibling validator or what happens for non-IRD inputs, so guidance remains implicit rather than explicit.

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?

Adds substantial context beyond the annotations: explicit per-call cost ($0.001 USDC on Base via x402) and the failure/retry behavior on an unpaid call. Annotations only cover the read-only, closed-world profile. It stops short of describing the response shape (valid/invalid, extracted check digit), which the absence of an output schema leaves undocumented.

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 compact sentences, front-loaded with the purpose before cost and payment mechanics. Every sentence carries distinct information: what it validates, what it costs and how to pay, and a callable example.

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 single-parameter read-only validator this covers purpose, pricing, and the payment retry path, which is the hard part. The main remaining gap is return-value semantics (what 'valid' looks like, and whether the check-digit derivation is exposed), which matters because there is no output schema.

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?

One parameter with 100% schema description coverage, so the schema already documents `number`. The description's example args duplicate the schema's example value (9429041535134) rather than adding constraints such as accepted length, formatting tolerance, or whether the check digit is required to be present.

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 (Validate) and resource (NZBN), plus the actual mechanism (check digit), which is exactly what an agent needs to distinguish it from nz_validate_bank, nz_validate_ird and nz_validate_phone. The parenthetical 'GTIN-13' is a slightly loose framing of the 13-digit format but does not obscure intent.

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?

No explicit when-to-use or when-not-to-use guidance relative to the sibling validators; selection is implied by the resource name. It does give clear operational guidance for the payment path (unpaid call returns PaymentRequired, retry with _meta["x402/payment"]), which is genuinely useful but is about invocation mechanics rather than tool choice.

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?

Annotations only cover readOnlyHint and openWorldHint; the description goes further by disclosing the paid model ($0.001 USDC on Base via x402), the PaymentRequired response on unpaid calls, and the _meta["x402/payment"] retry path. That is real behavioural detail an agent needs and cannot get from the annotations. It omits what happens on a malformed or non-NZ number, keeping it out of 5 territory.

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 tight sentences with no filler, and the core purpose is front-loaded before the payment mechanics. The inline example is slightly redundant against the schema's own example, which is the only minor waste.

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, the description still conveys the return shape (E.164 plus type) and the payment/retry protocol, which is the highest-risk unknown for this tool. What's missing is failure behaviour for invalid input, but for a one-parameter validator this is close to complete.

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% and the single parameter already carries the same example format shown in the description ("021 123 4567"), so the example adds essentially no new meaning beyond the schema. Baseline 3 is appropriate when the schema does all the work.

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 pair (validate, normalise), the resource (NZ phone number), and the output format (E.164 with type). This cleanly separates it from the sibling validators for bank, IRD, and NZBN, so an agent can route 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?

The purpose implies the usage context, and the description explains payment/retry behaviour, but it never states when to pick this over the sibling validators or what an invalid number yields. Usage is inferable rather than explicit.

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?

Annotations only declare readOnlyHint=true and openWorldHint=false, so the payment disclosure ($0.002 USDC on Base, x402 flow, PaymentRequired on unpaid calls, retry via _meta[x402/payment]) is real added behavior the agent could not otherwise know. It falls short of 5 only because the actual return value (a count? a breakdown?) is never described.

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?

Purpose is front-loaded in the first clause, then exclusions, presets, payment mechanics, and example args in descending order of importance. It is a single dense run-on with heavy parenthetical nesting, 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 4-param read tool with an output-less schema and thin annotations, the description covers purpose, exclusions, preset vocabulary, payment/auth flow, and a worked example. The one real omission is what the tool returns, which no output schema exists to cover.

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% but the schema descriptions are near-content-free ('e.g. 2026-10-01', 'e.g. none'), so the description does the real work: it enumerates the preset values (oia|lgoima|building_act|rta) that the schema omits entirely and shows a concrete argument set. It loses a point for leaving the 'region' parameter 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?

States a specific verb (Count), resource (NZ working days), and scope (between two dates inclusive, excluding weekends and public holidays). The scope of exclusion plus the day-count semantics distinguish it cleanly from the sibling nz_working_days_add (which shifts a date) and nz_holidays without needing either 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?

Usage is implied rather than stated: the agent can infer 'use this to count, not to shift dates,' and the x402/payment retry instruction is genuinely useful invocation guidance. However, no sibling is named and there is no explicit when-not (e.g. when to prefer nz_working_days_add or nz_holidays).

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?

Annotations only declare readOnlyHint and openWorldHint=false; the description adds substantial behavior the annotations cannot convey: the tool is paid ($0.002 USDC on Base per call), an unpaid call returns PaymentRequired, and the recovery path is _meta['x402/payment']. This is exactly the kind of auth/cost context that lets an agent invoke correctly on the first try.

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 use case, followed by the payment note and an example. Efficient overall, though the example args duplicate the schema's own examples and add little.

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 small pure-computation tool with readOnlyHint=true and no output schema, the description covers purpose, cost, and failure handling. The one gap is the return value (presumably a resulting date), which the description never states and which no output schema supplies.

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 baseline is 3. The schema descriptions are thin ('e.g. 20'), and the description's example args restate the same values without clarifying formats, valid preset names, or whether days is a string vs number beyond what the schema shows.

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+resource: 'Add N NZ working days to a date', plus a concrete use case (OIA 20 working-day deadline). It is clearly distinct from validation siblings, but it never contrasts itself with nz_working_days, which is the closest relative and could plausibly be confused with it.

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 OIA deadline example implies the intended context, and the payment note tells the agent what to do when a call fails (retry with _meta['x402/payment']). However, there is no explicit when-to-use guidance versus nz_working_days, and no statement of prerequisites such as whether a wallet/payment credential is needed up front.

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