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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed-world profile, so the safety surface is covered. The description adds genuinely new behavior: uncovered inputs are reported rather than numerically guessed, rules are pinned to 2026 with a last-updated stamp, and results come back as page-language rows plus raw engine outputs, sources and a disclaimer.

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?

Purpose and scope are front-loaded in the first sentence, with provenance (rules year, last updated, page URL) and return format following. Every sentence carries information, though the trailing 'Inputs marked Only used when' note is somewhat meta and the metadata sentence is borderline 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?

No output schema exists, and the description compensates by describing the return payload (result rows, raw engine outputs, sources with lastChecked dates, disclaimer). Combined with 100% schema coverage across all 7 parameters and annotations covering the safety profile, an agent has what it needs to call the tool correctly.

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% with bounds, defaults and enum glosses, so the baseline is 3. The description adds value beyond the schema by flagging that 'Only used when' inputs are conditional and by restating the key gating combination (monthly salary + third calendar year), helping the agent reason about the conditional parameter set.

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/resource pair with jurisdiction and year: 'Statutory annual leave days in Greece for 2026 ... and the gross leave allowance for monthly-salaried employees in at least their third calendar year'. The scope qualifiers (5-/6-day week, seniority increments, third calendar year) let an agent distinguish it from the close siblings latvia_vacation_pay and malta_vacation_leave without opening any schema.

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?

'Uncovered cases are reported instead of given a number' plus the explicit limitation to monthly-salaried employees in their third calendar year tells the agent when the tool will and won't produce a value. It does not, however, route the agent to alternatives for those uncovered cases or name any sibling tool, so it stops short of a 5.

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