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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint false, openWorldHint false), so the description's added value is the disclosure that results are deliberately withheld in ambiguous cases and that the tool returns result rows, raw engine outputs, sources with lastChecked dates, and a disclaimer. It also explains the "Only used when" gating convention for conditional inputs, which is genuine behavioral context not present in annotations. It stops short of describing pagination/limits, but little is at stake for a deterministic read-only calculator.

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?

Front-loaded with purpose and statutory scope, then progressively narrower detail (withheld results, year/version stamp, page URL, return shape, conditional-input convention). Dense but each clause carries operational information; the versioning sentence is arguably the weakest, yet it is useful for a jurisdiction- and year-specific calculator.

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, 8-enum, interlocking calculator with no output schema, the description covers what the tool computes, when it declines to produce a number, and what the response contains. The conditional dependency structure is acknowledged rather than fully mapped, but the schema descriptions (at 100% coverage) carry that load, leaving the definition adequately complete.

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 the 23 parameters including 8 enums are already fully documented, giving a baseline of 3. The description earns one extra point by explaining the cross-field conditional contract — inputs labelled "Only used when" apply only in that branch — which is the one piece of semantics an agent cannot infer from the flat schema alone. It does not restate individual field meanings, which is correct.

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 (Slovak personal income tax on property rental income for 2026) and pins the statutory basis (§ 6(3) of the Income Tax Act). It enumerates the exact computations covered — €500 exemption, proportional expenses, tax base, 19/25/30/35 % bands, filing obligation — which clearly separates it from the other country/benefit calculators in the sibling list.

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?

Sets clear context: rules year 2026, last updated date, and the boundary condition that no tax amount is returned while other income or expense verification is unknown. It does not explicitly route the agent between this and siblings such as list_calculators, but the domain is narrow enough that the applicable scenario is unambiguous.

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