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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description repeats the read-only claim but adds genuinely new behavioral facts: determinism, no network, no stored state, and hard limits (64 KB input, 1 s per call, 1 MB result) that an agent must respect to avoid failures. The safety restatement is mild redundancy rather than added value, which keeps it below a 5.

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?

Purpose and examples are front-loaded and each labeled section (Cuándo / No para / Efectos / Límites) is scannable. The bilingual duplication roughly doubles length, which is defensible for a Spanish-language tool, but the trailing "[EN completo / full EN: inputSchema.description]" pointer is a wasted meta-reference since it merely redirects elsewhere.

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 and an output shape (ISO 8601 proleptic Gregorian, weekday) is still briefly named, the two parameters are covered by the schema, and limits, determinism and the sibling exclusion are all stated. Nothing an agent needs to call this correctly or interpret the result 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 description coverage is 100%, so the baseline is 3; the description adds semantic context by explaining that hoy/mañana/ayer are resolved against "a given reference date" and that day-first order applies to 15/03/2026 and 2-digit years are 20xx. It doesn't restate the regex or maxLength constraints, but those are already fully in the schema.

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+resource ("Encuentra y convierte una fecha escrita en español") and backs it with three contrasting input examples plus the outputs (ISO 8601, weekday). It explicitly names the sibling it is not (es-number-parse), so an agent can separate it from the adjacent Spanish-language parsers 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?

Contains explicit routing: "Cuándo: hay que tratar texto, números o fechas en español según las reglas escritas del idioma y no por aproximación" and "No para: leer un número escrito en palabras o cifras en español (es-number-parse)". Both the positive trigger and the negative exclusion are present, which is the full standard.

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