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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds materially new behavior: an explicit non-lookup caveat, a per-call price ($0.001 USDC via x402 on Solana), and an equivalent HTTPS endpoint. Payment and dual-transport details are exactly the kind of context annotations cannot convey, though the return value (boolean vs. normalized string) is still undisclosed.

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?

Four tight sentences, front-loaded with the format definition before the algorithm, the scope caveat, and finally pricing/transport. No filler, though the algorithm sentence ('moves RF and the two digits to the end... mod 97-10 to be 1') is more implementation detail than an agent needs to select or call the tool.

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 single-parameter read-only check with no output schema, the description supplies format rules, separator handling, the verification algorithm, scope limits, cost and an alternative transport. The one real gap is what the call returns on success or failure (boolean, normalized reference, extracted check digits), which an agent would need to interpret results.

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 0% and the single 'value' parameter has no description or enum, so the burden falls on the description. It does compensate substantially by specifying the accepted character set, the ignored separators (spaces, hyphens, dots, commas, slashes, colons) and the 21-character body limit, but it never ties these rules explicitly to the parameter or states that the leading 'RF' is required in the input.

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 the resource precisely (ISO 11649 creditor reference) and lays out the exact grammar (RF + two check digits + up to 21 alphanumerics), so an agent knows this is a creditor-reference check tool rather than a lookup or generator. It never uses an explicit verb like 'validate' or 'verify', leaving the operation slightly implicit, but against the sibling set (iban_validate, lei_validate, isin_validate) the purpose is unmistakable.

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 line 'This does not look the creditor up' usefully scopes the tool away from any counterparty/registry lookup, which is real guidance. However, there is no explicit when-to-use clause and no named alternative (e.g. iban_validate for bank accounts, or a generator if one existed), so the agent must infer the call conditions from the format rules.

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