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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), but the description adds substantive behaviour: a semi-annual publication cadence, the upstream dataset, an explicit coverage gap for five named countries, and a per-call cost of 1 credit. Those are things an agent cannot infer from annotations and directly affect whether a call is worth making.

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?

The metric, cadence, units and source are front-loaded in the first sentence, and the coverage caveat follows logically. The first sentence is dense (three concepts stacked), but every clause carries information an agent needs, and the credit note is terse.

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 read tool with no output schema, the definition covers scope, units, cadence, provider and known data gaps — enough to call it correctly and interpret empty results. It does not describe the shape of returned values (e.g. time-period labels alongside amounts), which is the only remaining gap.

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%, so the schema already defines geo, currency and n, including the NAC/PPS expansions that the description restates. The description's contribution is limited to reinforcing that EUR is the default and that values are monthly gross, while the n parameter (most recent half-years) is left entirely to the schema. Baseline 3 is appropriate.

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 a specific metric and scope: 'Statutory monthly gross minimum wage in one European country', with the unit basis (gross, monthly), cadence (January and July) and underlying source (Eurostat earn_mw_cur). An agent can distinguish this cleanly from neighbouring Eurostat siblings such as eu_unemployment_rate or eu_inflation_rate without opening the 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?

It supplies a concrete usage example ('what is the minimum wage in Germany or Spain') and a clear negative case: countries without a national statutory minimum (Italy, Austria, Denmark, Finland, Sweden) return no values, which prevents a wasted call. It stops short of naming an alternative tool for those cases, so no explicit routing is provided.

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