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

Annotations already declare read-only/idempotent, but the description adds substantial extra context: hand-curated provenance with authority page and check date, the `confidence: "secondary"` marker for unfetchable official pages, the ABSENT-never-zero convention, federal-floor handling, and the mandatory not-legal-advice preamble in every response.

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?

Dense but front-loaded and almost every clause carries decision-relevant information. It is a single long paragraph, which slightly hurts scannability, but there is little genuine filler.

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 5-param, output-schema-backed reference tool, the description covers selection modes, defaults, absence semantics, provenance and confidence, and disclaimers. Nothing an agent needs to invoke it correctly is missing.

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 already 100%, so baseline is 3, but the description adds real meaning the schema does not: singular vs plural country semantics, that annual leave days are never converted from their `basis`, that `noticeNote` rises with tenure, and how `excluded` is populated for countries with no figure.

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 resource (statutory employment floors across 41 countries) and enumerates the exact figures returned: annual leave with `basis`, employer/employee notice weeks, probation ceiling, weekly-hours ceiling. This clearly separates it from siblings like compare_working_time, compare_public_holidays and compare_contract.

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?

Explains the three invocation modes precisely — `country` for one entry, `countries` for a side-by-side, neither for a metric ranking with `sort` and `excluded` — plus the default metric. It also notes the scope limit ('Statutory floors only — contracts and collective agreements usually give more'), which effectively excludes contract-level questions, though it does not name a sibling to redirect to.

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