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

With no annotations, the description carries the full burden and does substantial work: snapshot date, temporal coverage, the 80-vs-97 HS2 chapter gap in 2005–2021, and the explicit prohibition 'EU-wide CN8 must not be inferred'. These are exactly the failure modes an agent would otherwise hit. It stops short of rate limits, response size, or what happens when filters are unsupported for a given view ('depends on the REST view' is left unresolved).

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?

It is a single dense run-on sentence packed with parenthetical caveats and dates ('verified 2026-10-23', exact row counts, chapter ranges) that partly crowd out the operational information. The most actionable warnings, such as the CN8 prohibition, are buried mid-string rather than front-loaded. Much of the content earns its place, but the packaging works against it.

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?

Nine parameters, no output schema, no annotations, so the description has to cover scope and caveats — and it does so thoroughly, including data-quality pointers. The remaining gap is per-query_type behavior: without an output schema, nothing tells an agent what 'heatmap' or 'balance' returns or which filters each accepts.

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 every parameter including hs2, flow, reporter, and limit is already documented, and the enum on query_type is self-describing. The description adds only marginal filter semantics ('HS2 only', EU27 reporters constraining reporter values) and notes macro_context draws on a live ECB/FRED snapshot. Crucially, it does not say which filters are valid for which query_type, which is the real semantic gap here.

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?

Opens with a specific verb and resource ('query 67.7M Eurostat COMEXT rows'), and the eight query_type values make the tool's scope concrete. It also pins the dataset boundaries (EU27 reporters, HS2 only, monthly 2005-01–2026-06). What it never does is explain what each query type actually returns, so an agent knows the tool's shape but not its outputs.

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 enum lists query types, which implies routing, but no mapping from a user question to a query_type is given and no when-not guidance appears. The only real directives are indirect: 'consult current data_quality for recent periods' and 'see data-coverage.json'. Sibling tools are unrelated domains, so there is nothing to disambiguate against, but internal routing is left to inference.

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