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

Adds real context beyond the annotations: determinism, no network, no stored state, and concrete operational limits (64 KB JSON input, 1 s per call, 1 MB result). The read-only/idempotent statements duplicate readOnlyHint/idempotentHint, but the limits and offline/deterministic guarantees are genuinely new information.

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 opening Spanish sentence is well front-loaded, but the description then repeats itself in a full English block and ends with a truncated dangling fragment "[EN completo / full EN: inputSchema.description]", which is noise rather than signal. The bilingual duplication roughly doubles length for the same content.

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 one required parameter, full schema coverage, rich annotations, and an existing output schema, the description covers the remaining gaps (offline, deterministic, limits, sibling exclusion). The only shortfall is the over-broad "LatAm o España" scope claim, which slightly undercuts routing accuracy.

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 single `cbu` parameter is already documented with type, maxLength, and an example. The description still adds meaning by explaining what the input is decomposed into (3-digit bank + 4-digit branch + check digit, 13-digit account + check digit) and that only validation, not normalization, occurs.

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 ("Valida una CBU/CVU argentina de 22 dígitos") and even names the internal block/check-digit structure it verifies. It explicitly rules out the sibling ar-cuit-validate, so an agent can distinguish it 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?

Provides an explicit "Cuándo" trigger (offline check of a user-supplied account/document number before storing or using it) plus a "No para" exclusion naming ar-cuit-validate. However, the stated scope "LatAm o España" is broader than the tool's actual Argentina-only CBU/CVU check, which could misroute an agent holding an IBAN, Mexican CLABE, or Spanish DNI.

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