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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: in-memory processing with no storage, API key plan requirements (Growth+), a 5,000-character free-tier limit, request accounting (one per IBAN), and the important behavioral fact that text with no IBANs returns an empty list rather than an error.

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, front-loaded with purpose, then use cases, then return shape, then operational constraints. Every sentence carries distinct, actionable information with no padding.

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?

With no output schema, the description compensates by naming the return fields (count, valid_count, invalid_count, results) and the entry shape. Combined with the plan/auth notes and error-free empty-result behavior, an agent has everything needed to call and interpret the tool.

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 100% and there is only one parameter, so the schema already documents it (baseline 3). The description adds genuine meaning about the parameter's expected content and quirks — emails, invoices, pasted PDFs, chat messages, and IBANs split by spaces — which helps an agent prepare input correctly.

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?

Starts with a specific verb+resource: 'Scan a free-form block of text and pull out every candidate IBAN, then validate each one.' It clearly distinguishes extraction-and-validate from siblings validate_iban and validate_bulk_ibans, which take known IBANs rather than discovering them.

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?

Explicitly frames itself as 'the first step when the account number is buried in prose' and routes follow-up work: 'pass the extracted IBANs to validate_bulk_ibans only if you need to re-check them separately.' Names both the when and the alternative.

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