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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them: it discloses the four summed lines, why rent is excluded from the basket (double-counting caveat), that VAT is already embedded and never added, and the tax model assumptions (tax-resident, single filer, no deductions, special regimes like IFICI reported separately). This is exactly the extra behavioral context annotations cannot convey.

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 the core purpose, then method. The prose is dense and largely earns its place through the double-counting and tax-assumption caveats, though a few clauses (e.g., the VAT parenthetical) are verbose enough to slow scanning.

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 four parameters, no output schema, and a comparative calculation, the description supplies enough methodological grounding to call it safely. It stops short of describing the returned row/ranking structure, which is the one remaining gap given there is no output schema to cover it.

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 sort, income, country, and maxPctOfIncome are fully documented in the schema itself (including the 'remaining' vs 'share' enum semantics). The description adds no parameter-level syntax or constraints beyond what the schema provides, so the baseline 3 applies.

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 ('what a month actually costs in each of 41 countries on a stated income, and what is left over') with clear scope. It is immediately distinguishable from siblings like compare_housing, compare_food_cost, or compare_tax_burden, which each cover only one of the four lines this tool sums.

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 implied by 'Estimates for comparison — not a quote and not tax advice' and by the methodological framing, but no explicit when-to-use/when-not guidance or named alternatives are given. An agent can infer intent but must guess whether compare_effective_tax or compare_tax_burden is the better pick for tax-only questions.

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