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

Annotations already establish a safe read-only, idempotent profile, so the bar is lower. The description adds genuine behavioral context beyond them: results include tagging method and confidence, the view is 'every provision' (complete listing), and it is language-neutral. It does not cover pagination or behavior for an unknown conceptId, but the annotation coverage makes that a minor gap.

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 with no waste: the first states the function and output content, the second provides concrete examples and the overarching use case. The key scoping ('cross-jurisdiction', 'one legal concept') is front-loaded.

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 three-parameter, one-required read-only listing tool, the description covers purpose, output contents, and the use case. There is no output schema, so description should hint at return values — it does mention tagging method and confidence — but it omits any indication of result volume limits or pagination, which matters for a tool that returns 'every provision'.

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 all three parameters are already documented, warranting baseline 3. The description's EuroVoc examples reinforce the conceptId format already present in the schema and add domain relevance, but it does not add meaning beyond what the schema provides for jurisdiction or minConfidence.

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 action and resource: retrieving every provision tagged with a EuroVoc concept, with tagging method and confidence. Concrete examples ('eurovoc:4585' VAT, 'eurovoc:4392' VAT rate) anchor the semantics. It distinguishes itself from siblings like lookup_provision (single provision) and search_legislation via the 'cross-jurisdiction' and 'language-neutral' framing.

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?

The description implies the use case — lining up EU and national law on the same subject in a language-neutral way — which gives clear context for when to call it. However, it never names an alternative or states when not to use it; notably, find_national_implementations is a sibling with apparent overlap that is not disambiguated.

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