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 clearly discloses that this is a calculation tool producing a breakdown (income tax, ACC, KiwiSaver, student loan, IETC, net pay) and specifies the ACC capped amount and KiwiSaver minimum rate. It also implicitly signals mutability through parameter defaults. It does not disclose whether it is synchronous or handles edge cases like zero income, but the calculation scope is well covered.

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 well-structured with a clear summary, a breakdown of what is returned, usage guidance, exclusions, and parameter documentation. Every sentence earns its place. The use of 'DO NOT use for' is front-loaded and effective.

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 there is no output schema, the description compensates by listing the full breakdown returned (income tax, ACC, KiwiSaver, student loan, IETC, net take-home pay annual/fortnightly/weekly). It covers the main decision-relevant context: tax year, exclusions, and parameter ranges. It is complete enough for an agent to select and invoke the tool 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?

Schema description coverage is 0%, so the description must compensate for the schema's bare property titles. It does: it explains annual_income (gross annual salary in NZD, 0 to 10,000,000), kiwisaver_rate (valid values and default), has_student_loan (repaying a NZ student loan), and claim_ietc (eligible for IETC). It adds meaning that the schema lacks, though it could have been even more explicit about the default behavior of claim_ietc since it defaults to true.

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 and resource: 'Calculate New Zealand take-home pay (PAYE) for the 2026/27 tax year'. It clearly distinguishes itself from sibling calculators like nz_net_to_gross_calculator, nz_secondary_tax_calculator, and nz_kiwisaver_calculator by scoping to PAYE take-home pay for the 2026/27 tax year and listing what it returns.

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 explicitly states 'Use for ANY NZ tax question about: salary, take-home pay, net income, PAYE, KiwiSaver impact, student loan deductions, or IETC eligibility' and explicitly lists exclusions: 'DO NOT use for: self-employed/contractor income, secondary tax codes, non-NZ residents, redundancy lump sums, or pre-April-2026 income.' This gives an agent clear routing guidance relative to sibling tools.

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