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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint=false, but the description goes further: no side effects, no network, no stored state, deterministic output, plus concrete limits (64 KB input, 1 s per call, 1 MB result). Those limits and the determinism guarantee are operationally useful facts not present in the annotations.

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 definition, then clearly labelled blocks (Cuándo / No para / Efectos / Determinista / Límites), so scanning is easy. It loses a point because the full English text duplicates the Spanish verbatim and the trailing '[EN completo: inputSchema.description]' pointer adds no decision-relevant 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?

An output schema exists, so return shape need not be described, and the description still names the two returned values. Combined with the safety profile from annotations, the determinism guarantee and the input/size limits, an agent has everything needed to call it correctly.

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; the description earns an extra point because it tells the agent that `value` may be either delay-seconds or an HTTP-date and that `now` is the reference instant for the absolute retry time, which the terse schema descriptions ('Retry-After header value', 'Current instant ISO 8601') do not convey.

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 (parse an HTTP Retry-After value) and the exact output semantics (seconds to wait plus absolute retry time, relative to `now`). It also names what it is not (backoff-schedule), so an agent can distinguish it from the nearest sibling 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?

Explicit 'Cuándo' clause scopes usage to exact, repeatable bookkeeping steps in an agent loop, and the 'No para' clause rules out backoff-delay computation while naming the sibling `backoff-schedule` as the alternative. Both the inclusion and exclusion conditions are spelled out.

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