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

With no annotations provided, the description carries the full behavioral burden. It discloses the exact algorithm ('RF and the two digits move to the end, letters become 10–35, remainder must be 1'), the validation-vs-generation decision, the length constraint, and the error behavior ('bad checksum is rejected with 400'). This is exceptionally transparent about how the tool behaves beyond a generic validate-or-generate summary.

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 sentences, each earning its place: the core verb, the SEPA context, the algorithm, and the rejection policy. The text is front-loaded with the main purpose and then layered with increasingly specific behavioral detail without fluff or repetition of structural metadata.

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?

The description is complete enough for an agent to understand input forms, behavior, and a meaningful error condition. The only notable gap is that for a dual-mode tool with no output schema, the exact successful return value is not explicitly stated (i.e., what a validity check returns vs. what a generated reference looks like). Still, given the algorithmic thoroughness and clear single parameter, the omission is minor.

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 parameter itself is well-described ('ISO 11649 RF creditor reference, or a 1–21 character payload to encode'), giving 100% coverage. The description adds practical semantics by explaining that the reference-or-payload distinction is determined by the RF+two-digit prefix, and describes the encoding transformation. It does not fully describe output content, but for a single input parameter the meaning is strongly reinforced.

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 precise verb-resource pair: 'Validates or generates an ISO 11649 RF creditor reference', making the tool's scope unmistakable. It also distinguishes the tool from siblings like iban_validate by naming a specific standard (ISO 11649) and adding the mod-97 checksum mechanism. This is more than enough for an agent to know exactly what the tool does.

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 description gives clear context: SEPA credit transfers carry RF references, and it explicitly states when validation versus generation occurs: 'If the input already starts with RF and two digits it is validated; otherwise a 1–21 character alphanumeric payload is encoded.' It does not name alternative tools, but the mode switch is so explicit that an agent knows exactly which input type to pass.

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