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

With no annotations provided, the description carries the full burden and delivers rich behavioral disclosure: the net_weekly vs effective_hourly_after_tax distinction (dividing by 52 vs actual hours worked), the decimal-only kiwisaver_rate with 'Passing 3 is rejected', and the 12%-above-threshold student loan repayment. These are precisely the traps an agent would otherwise stumble into. No annotation contradiction exists.

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?

Approximately 230 words organized into clear sections (purpose, use-for, Args, Returns) with the core sentence front-loaded. The four query examples overlap slightly but each earns its place as pattern-matching signal for an agent.

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 financial calculator with no annotations and no output schema, the description covers everything required for correct invocation: full parameter semantics, the output shape (gross at each frequency, every deduction, net annual/weekly, effective hourly), and the caveat about interpreting the two weekly figures. The only omission is a tax-year/rates-currency reference, which isn't needed to call 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 — and it covers all 5 parameters with meaning the schema lacks: NZD currency for hourly_rate, '40 is full time in NZ' for hours_per_week, seasonal/academic work guidance for weeks_per_year, the decimal-format rejection for kiwisaver_rate, and the 12% threshold for has_student_loan. Every parameter is semantically enriched.

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?

Opens with a specific verb+resource: 'Convert a New Zealand hourly rate into a salary, before and after tax.' The stated scope — gross and net at weekly, fortnightly, monthly and annual frequencies plus PAYE, ACC, KiwiSaver and student loan — clearly distinguishes it from single-purpose siblings like nz_paye_calculator or nz_kiwisaver_calculator.

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 'Use for:' block gives four realistic query patterns ('what is $32 an hour as a salary', 'is $75,000 better than $36 an hour'), giving an agent strong matching signals for when to invoke this tool. However, it never names an alternative or states when NOT to use it — notably it doesn't differentiate from confusable siblings like nz_net_to_gross_calculator or nz_contractor_vs_employee_calculator.

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