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

Annotations already establish readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: the calculation source (Belastingdienst tables), the 2026 tax year, and the shape of the result (monthly and annual net plus a tax breakdown). It stops short of stating assumptions such as pension contributions or other deductions being excluded.

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?

Effectively one dense sentence plus a compact example, both front-loaded with jurisdiction and capability before the example. The phrase 'as on our net salary calculator' is faintly promotional and adds little a calling agent can act on, but the definition is otherwise free of padding.

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 five parameters, full schema coverage and no output schema, the description does the one job structured data cannot: it tells the agent what comes back (monthly and annual net plus a tax breakdown) and which official tables underpin it. What remains unstated is the scope boundary of the calculation — which deductions and allowances are excluded — which an agent quoting a result to a user could reasonably want.

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 100%, so every parameter — including the enum on period and the interaction between ruling_30 and under_30_with_masters — is already documented in structured fields. The description's only added value is a concrete parameter combination in the example (gross=60000, period='yearly', ruling_30=true), which is marginal over the schema's own 'e.g. 60000 a year'.

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 and resource ('gross-to-net pay'), pins the jurisdiction and tax year (Dutch, 2026, Belastingdienst tables), and names the optional 30% ruling variant. The return content ('net per month and year plus the tax breakdown') further disambiguates it from every sibling, none of which touch payroll.

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 domain ('Dutch ... 2026') implies when the tool applies, and the worked example shows a valid invocation, but there is no explicit when-to-use/when-not-to-use statement — e.g. that it does not cover non-Dutch income, other income years, or employer-side costs. No alternative tool is named, though the sibling list contains none that overlap.

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