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

Annotations already establish the safe, idempotent, closed-world read profile, so the bar is lower; the description adds real domain context beyond that — the tax year applied, the progressive-bracket method, and the tax-free allowance reduction step. It omits assumptions such as household/dependents treatment, which matters for a tax engine.

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 compact sentences, front-loaded with the calculation identity before the version qualifier and cross-reference. The return-field preview is slightly redundant given the output schema but is short and skimmable, so no sentence is wasted.

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, the description needn't fully explain returns, and it correctly leaves detail there. Method and tax-year context are supplied, but a tax calculator with only 'income' as input silently assumes a household/family situation that the description never states, which is the main residual gap.

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?

Single parameter with 100% schema description coverage, so the schema already defines 'income' as annual taxable income in euros after social security and professional expenses. The description only echoes that framing ('annual taxable base') and adds no further format, boundary, or unit nuance.

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 (Belgian personal income tax, IPP/PB) on an annual taxable base, and pins the version to income-year 2026 / tax year 2027 with the SPF method. It is clearly distinguishable from other national income-tax siblings by country, but it does not differentiate itself from close siblings such as calculate_belgian_salary or calculate_belgian_social_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?

Usage is only implied: 'on an annual taxable base' tells the agent what input shape is expected, and the closing 'See list_bundles for related finance-belgique calculators' is a navigation pointer rather than a when-to-use rule. No exclusion or alternative-selection guidance versus the other Belgian calculators.

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