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

Annotations already cover read-only, closed-world and idempotency, but the description adds operational facts those annotations do not: no network access, no stored state, deterministic output, and concrete limits (64 KB JSON input, 1 s per call, 1 MB result). The offline guarantee is especially actionable for an agent deciding whether a call can be batched locally.

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 core verb and checks, then cleanly segmented by labelled clauses (When / Not for / Side effects / Deterministic / Limits). The whole block is duplicated in Spanish and English, which doubles length without adding information, though each single-language version is tight.

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?

An output schema exists, so return shape needn't be spelled out, yet the description still previews the returned formats and BBAN. Combined with the disclosed limits and the read-only/deterministic guarantees, an agent has everything needed to call this correctly and interpret failures.

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%, with type, required flag, maxLength 64 and a spaced example already present; the description's 'up to 64 chars' merely restates maxLength. Budget-like figures (64 KB input) add marginal context but nothing about IBAN formatting tolerance (spaces, lowercase) that the schema doesn't already say.

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 ('Validates an IBAN') and enumerates exactly what is checked: country code, country-specific length (~80 countries), allowed characters and ISO 7064 mod-97 checksum, plus what is returned (electronic/print formats and BBAN). It explicitly distinguishes itself from swift-bic-validate, so an agent can separate the two without opening either schema.

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 an explicit trigger ('When: an identifier's format and check digit have to be verified offline before it is used') and an explicit exclusion with the alternative named ('Not for: checking SWIFT/BIC code syntax (swift-bic-validate)'). Both the when and the when-not are stated rather than implied.

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