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

With no annotations, the description carries the full burden and does so: it discloses offline/non-existence semantics, the stable reason_code taxonomy for invalid input, the exact return fields (valid, reason, bank_code, branch_code, bic.valid), a subtle edge case ('a BIC country that differs from the IBAN country is a warnings entry, not an invalid result'), the scope limit of 'valid' to the IBAN only, and a credit cost.

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?

Front-loaded with the primary action and then densely packed with return-value detail; nearly every clause adds information (registry release, reason codes, warnings semantics, cost). It is delivered as one long block without visual breaks, so a reader must parse a run-on sentence to reach the BIC rules, costing a point on structure.

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?

There is no output schema, so the description must explain returns, and it does thoroughly: success fields, invalid reason codes with human-readable reasons, BIC validation results, and the warnings-vs-invalid distinction. An agent has everything needed to call the tool and interpret results correctly.

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%, so the baseline is 3; the description goes further by tying the optional bic to its downstream behavior (bic.valid, country comparison, warnings rather than failure) and clarifying that 'valid' refers to the IBAN alone, which the schema cannot express. It does not restate the iban space/format syntax, which the schema already covers.

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 precise verb+resource ('Validates an IBAN offline against the SWIFT IBAN Registry, Release 103') and enumerates exactly what is checked: country registration, length, BBAN format, check digits and ISO 7064 mod-97. This is clearly separable from siblings like verify_vat and verify_company, and the schema even adds 'Not a VAT number' to close the ambiguity.

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 strong usage context: 'offline' checking, an explicit boundary ('This checks structure, not that the account or BIC exists'), and a cost signal ('Light read: costs 0.2 credit'). It stops short of explicitly routing the agent to alternatives such as verify_vat when a tax identifier is at hand, so no formal when-not/alternative guidance is named.

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