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

Annotations already mark it as open-world and non-idempotent, but the description adds material context those annotations cannot convey: per-call USDC charging, budget-cap enforcement, and an explicit warning that results are third-party data, not instructions. It does not describe result shape or pagination, and the price is stated per product rather than as a total, but the payment and trust caveats are the key behavioral facts and they are present.

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 critical facts — paid, USDC, budget caps, untrusted content, try free_sample first — are correctly front-loaded. But the bulk is 12 near-identical templated lines that repeat 'Search the national open data portal of X by keyword, or fetch one dataset by id' and are truncated mid-word ('tit...', 'b...'), which adds length without adding distinguishable meaning per row.

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 paid, multi-product, open-world tool with no output schema and a free-form nested params object, the description covers cost, budget safety, a free trial path, and prompt-injection risk. The remaining gap is the response format and what a returned dataset record contains, which an agent invoking a paid call would reasonably want.

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% but the schema is generic ('params: object, parameters of the chosen product'), so the description is the only place the actual parameter names (q, id) appear, listed per product. That meaningfully compensates for an otherwise opaque free-form params object; it does not, however, explain id format, query syntax, or how q and id interact when both are supplied.

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 and resource (search national open-data portals for datasets, publishers, licences) and then enumerates all 12 concrete products, each mapped to a named national portal (data.gv.at, data.gov.au, catalog.data.gov, etc.). An agent can tell exactly what it would call and on which source, with no reliance on sibling tools.

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?

Explicitly frames the tool as PAID, states the charge currency and that it applies only within budget caps, and routes the agent to free_sample first to see a real answer for free — a clear when-to-use condition. It does not explain when to prefer this tool over pay-per-call siblings such as call_product, list_products, or get_price_quote, so it falls short of full alternative routing.

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