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

Annotations already declare read-only, idempotent, closed-world, non-destructive, so safety is covered; the description instead adds the substantive behavior — it enumerates the per-regime payload (official name, target group, benefit, duration, application steps, limits and risks, legal norm with link, date checked). That tells the agent what a hit actually contains, which no annotation conveys. It does not mention result ordering or the default/maximum result count, which the schema carries separately.

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 sentences, front-loaded with the domain and scope, then the return contract. Dense but every clause carries information; the long return-field list is the only place it sprawls, and that sprawl is functional.

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 no output schema, the description usefully compensates by enumerating returned fields, and the 100%-covered input schema covers parameters. The notable gap is an internal inconsistency: it claims '21 countries' while the countries enum lists 27 ISO codes, which could mislead an agent about coverage. Result-count defaults and pagination are also left to the schema.

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%, including enum glosses for status and examples for query, so the schema does the heavy lifting. The description only restates the filter facets ('country, kind, status and free text') and adds the country-set scope; it adds no syntax or semantics for limit, version, or multi-value OR/AND behavior. 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?

The description names the exact resource: special and preferential tax regimes for individuals (newcomers, employees, self-employed, investors, pensioners) across a fixed set of countries, plus the filterable facets. That is specific enough to separate it from siblings like tax_burden or check_residency, which concern general liability and residency rather than regime catalogues. The verb is only implied ('search' lives in the name/title), so it stops short of a 5.

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 by the phrasing 'Filter by country, kind, status and free text' — an agent can infer this is the lookup for regime details. There is no explicit statement of when to use this versus exit_tax_check or check_residency, and no exclusions or prerequisites. Adequate but leaves routing to inference.

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