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

Annotations already declare readOnly/openWorld=false/idempotent, and the description still adds substantive context beyond them: no network access, no stored state, determinism ('la misma entrada da la misma salida'), an explicit semantic limit (does not confirm bank existence), and concrete operational limits (64 KB input, 1 s per call, 1 MB result). That is exactly the kind of disclosure annotations cannot carry.

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?

Content is front-loaded and labeled (Cuándo / No para / Efectos secundarios / Determinista / Límites), so an agent can scan straight to the routing cue. The ES/EN duplication doubles the token footprint without adding information, which is the only thing keeping it off a 5.

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 the description is right not to enumerate return fields, and every other decision-relevant fact for a single-input validator — offline scope, determinism, size/time limits, semantic ceiling — is present. Nothing an agent needs to call it correctly is missing.

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% so the baseline is 3, and the description goes further by decomposing the expected value into its ISO 9362 components (4-letter institution, 2-letter country, 2-char location, optional 3-char branch). That tells an agent what a well-formed input looks like, though it does not address the schema's maxLength of 16 against the 8/11-char reality.

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 ('Verifica la sintaxis de un código SWIFT/BIC (ISO 9362)') and adds the exact output behavior ('lo separa en partes'). It also draws an explicit negative boundary ('no confirma que el banco exista') and names the confusable sibling iban-validate, so an agent can distinguish it without opening any 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?

The 'Cuándo' clause gives the selecting condition (offline format/check-digit verification before using an identifier) and the 'No para' clause names the alternative tool (iban-validate) for the adjacent use case. Both when-to-use and when-not-to-use are explicit.

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