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

Annotations already declare readOnly, idempotent and non-destructive, so the safety bar is low; the description still adds useful trust context by noting the ID number is 'not stored' and by pinning down defaults (tables method, monthly period, today's pay date, monthly-equivalent conversion). It does not state determinism or rate-table vintage caveats explicitly beyond 'the right tax year'.

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 outputs and scope, then a compact enumeration of the statutory features handled. The second sentence is a dense list but every item maps to real parameters, so nothing is padding; a slightly tighter grouping of the tax-credit and allowance features would make it easier to scan.

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, read-only calculation tool with no output schema, the description names the computed outputs (PAYE, UIF employee/employer, SDL, net pay) and the scope constraints, which is close to sufficient. The remaining gap is that the exact response fields and any rounding/table-version disclosure are left implicit.

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; the description earns above baseline by tying parameters to substantive statutory mechanics the schema only gestures at — the s11F cap, the 80%/20% travel allowance split, the annual-payment method for bonuses, and age rebates and medical credits. It does not resolve ambiguities such as how salary plus overtime plus bonus interact when period is weekly.

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-resource-scope: it computes PAYE, UIF (employee and employer, with ceiling), SDL and net pay for exactly one employee and one pay period. That scope line alone separates it from siblings like sa_tax_rates (rate lookup) and sa_vat_calculate (indirect tax) without needing their schemas.

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 single-employee/single-period scope implies when to use it, and the mention of 'the right tax year' hints at the pay_date/tax_year choice, but no explicit when-not or alternative is named, and no sibling is referenced for related tasks such as validating an ID number or looking up rates.

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