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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, and the description reinforces this with 'sin red, sin estado guardado' and a determinism guarantee. The added value is in the concrete limits (64 KB input, 1 s per call, 1 MB result), which no annotation or schema field expresses.

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 content is front-loaded and each fact is useful, but the same text is delivered twice (a full Spanish block followed by an equivalent English block) and then a third time lives in inputSchema.description, referenced by a pointer sentence. Roughly half the description is duplication, which dilutes an otherwise tight definition.

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?

For a one-parameter validator with an output schema and full annotations, nothing an agent needs is missing: accepted formats, check-digit semantics, offline/deterministic behavior, resource limits, and the sibling to use for CPF are all stated.

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 the single param is documented with an example and maxLength, so the schema carries the baseline. The description still adds real meaning: it tells the agent the alphanumeric format is accepted (letters valued as ASCII − 48) and that output is formatted as 11.222.333/0001-81, which the schema only hints at via one example.

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 un CNPJ brasileño') and immediately scopes it to the alphanumeric format from July 2026 with both mod-11 check digits. It explicitly names the sibling it is not (br-cpf-validate), so an agent can separate the two Brazilian document validators without opening a 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 explicit 'Cuándo' and 'No para' clauses plus the named alternative br-cpf-validate, which is exactly the routing information an agent needs. The trigger phrasing ('documento o número de cuenta de LatAm o España') is looser than the tool's actual scope — a CNPJ is a Brazilian company registry number, not a generic LatAm account number — which could pull in slightly wrong calls.

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