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

With no annotations, the description carries the full behavioral burden and does so thoroughly: it discloses representative-office selection, office_note, the coarse sanctions FLAG limitation, country-name normalization, and the pricing implications of BIC choice. It is unusually transparent about the 'BIC identifies an office, not a brand' trap and provides worked examples. No contradiction with annotations because none 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 description is long, but every block carries operational weight: coverage scope, sanctions caveat, BIC-office pricing rule, and usage examples. It is front-loaded with the search statement and uses capitalization sparingly for a genuinely critical warning. Still, the BIC-identification section could be tightened without losing value.

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 tool with an output schema already explaining return shape, the description covers the remaining agent-critical context: entity classes searched, coarse vs full sanctions distinction, parameter formats, office-vs-brand behavior, and examples. The limit omission is minor because the schema provides a default and the output schema bounds what is returned.

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?

The schema provides only property names and defaults with 0% description coverage, so the description must compensate. It richly explains query (name, BIC, city, non-SWIFT entities) and country (ISO or full English name, auto-resolution), but says nothing about limit or its default meaning. This is a small but real gap, so 4 rather than 5.

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 opens with a specific verb-resource pair: 'Search banks and financial institutions by name, SWIFT/BIC code, or country.' It also differentiates itself from neighboring tools by explicitly pointing to SSI tools for settlement instructions and sanctions_screen for compliance verdicts, so an agent can select it correctly without opening schemas.

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?

It provides concrete when-to-use guidance: use for bank/institution lookup across SWIFT and non-SWIFT entities; use dedicated SSI tools for correspondent/settlement; use sanctions_screen for a full compliance verdict. It also gives decision rules for city/BIC disambiguation, telling the agent to include a city when named and to ask which BIC otherwise. This is explicit and actionable routing.

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