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

Annotations already declare readOnly, idempotent, and closed-world, so safety is covered. The description adds real behavioral detail beyond that: it computes IBAN check digits and, where the country has them, national check digits such as the French RIB key or Italian CIN — explaining why check_digits is sometimes supplied and sometimes derived.

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?

Three tight sentences: purpose first, then the non-obvious check-digit behavior, then the pointer to iban_format. No filler and the most surprising detail (national check digits) is placed prominently.

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 computation tool with no output schema, it explains enough about what is derived versus supplied for an agent to call it correctly. It does not cover failure behavior (invalid account length, wrong code for country) or the shape of the returned IBAN, which would complete the picture.

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 only 40%, so the description must carry weight, and it does: it maps bank_code/branch_code/account_number to 'national bank details' and clarifies that check_digits are supplied only where they are not computed. It still leaves country-format expectations to iban_format rather than restating them.

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 ('Build an IBAN from national bank details') and names the component inputs, so it is clearly distinguishable from validate_ibans or generate_test_ibans. It does not explicitly say it does not validate, but the construction framing is unambiguous.

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?

Points the agent at iban_format to discover which parts a given country requires, which is exactly the prerequisite knowledge needed before calling. No explicit when-not-to-use or a contrast with validate_ibans, so it stops short of full routing guidance.

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