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

The annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the description's job is to add context, and it does: results derive from statutory rates of the Polish tax year, they are not advice, and the response should be accompanied by inputs and assumptions. It does not discuss edge cases such as the accident-insurance rate above 9 insured or rounding, but the disclaimer and provenance statements are substantive additions.

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 opening 'Use for the cost of an employee to the employer' is restated by 'Total monthly cost to the employer...', and the disclaimer sentences sit mid-paragraph rather than up front. The component enumeration is informative but dense; trimming the duplicated purpose statement would sharpen it.

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 an output schema present, return values need no explanation, and the description covers scope, contract types, statutory basis, year defaulting, and the not-advice caveat. For a four-parameter statutory calculator this is close to sufficient; only edge-case behavior (accident rate thresholds, year-specific rate changes) is left unstated.

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 that by expanding the opaque enum values (uop = umowa o pracę, zlecenie = umowa zlecenie) and identifying PPK as optional, which the schema only encodes as a default-false boolean. It also ties monthly_gross to employer cost rather than net pay, clarifying what the number means.

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 names a specific resource (total monthly cost to the employer of an umowa o pracę or umowa zlecenie in Poland) and enumerates the cost components: pension/disability contributions, accident insurance, FP, FGŚP, optional PPK, plus employee take-home. It is clearly a cost calculator rather than a net-income or contribution calculator, though it does not explicitly name the neighbouring calc_net_income / calc_zus_contributions to mark the boundary.

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?

'Use for the cost of an employee to the employer' plus 'Give the inputs and the assumptions with the result' tells the agent the scenario and how to present output, which is real but implicit guidance. There is no explicit when-not condition and no named alternative for a user who wants only net pay or only ZUS contributions, so routing must be inferred from the component list.

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