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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds genuine behavioral rules — the 1%+1% split, the rand ceiling on UIF, and the payroll threshold that nullifies SDL. It omits how the cap is applied per employee per month and mentions nothing about rounding or what the result contains, keeping it below 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?

One dense sentence, front-loaded with the tool's purpose, with the parentheticals carrying the rates and thresholds that an agent actually needs. No filler, no repetition of the title or schema.

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 only two parameters, full schema coverage, and read-only annotations, the description covers input semantics and computation rules well. The remaining gap is output shape — with no output schema, the agent is not told whether the response lists UIF employee/employer and SDL amounts per employee.

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 adds real meaning beyond the schema by explaining why annual_payroll_estimate exists (the SDL exemption test) and that remuneration is per-employee with a statutory cap applied. It stops short of clarifying whether the array is processed independently per element or aggregated.

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 (calculates) and two named resources (UIF and SDL) with the exact rates, the R17,712 cap and the R500,000 exemption threshold, so scope is unambiguous. It is clearly separable from all siblings, which cover dates, leave, wages, overtime and holidays rather than statutory contributions.

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 usage context (monthly payroll contributions for one or more employees) but never states when to call this versus alternatives or what to do when only a subset of employees is relevant. There are no exclusions, preconditions, or routing hints — the agent must infer that this is the payroll-contribution calculator.

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