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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing the exact validation algorithm (mod 97), the country-length rule, the normalisation/grouping behaviour, and critically a negative guarantee that the account's existence is not verified. That limitation is the most decision-relevant trait and is not derivable from any structured field.

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 tight sentences, front-loaded with the core action and its mechanism, closing with the boundary condition. Every clause earns its place with no filler.

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 one-parameter validation tool with no output schema, the description covers mechanism and limits well, but it never hints at the result shape (e.g., a validity flag versus specific failure reasons per check). Minor gap given the tool's simplicity.

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% ('IBAN, spaces allowed.'), so the schema already carries the parameter contract. The description's mention of a 'normalised and grouped format' describes the output presentation rather than adding input syntax guidance, so baseline 3 applies.

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 (validate) and resource (IBAN) and enumerates exactly what is checked: ISO 13616 mod-97 checksum, country-registered length, and normalised/grouped format. This clearly separates it from non-overlapping siblings such as eu_vat_validate or lei_lookup.

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?

Gives clear context via 'offline' (no network lookup) and an explicit scope exclusion: 'Does not check that the account exists.' No alternative tool is named, but no sibling covers the same ground, so routing is unambiguous.

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