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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, yet the description still adds real information: no network access, no stored state, deterministic output, and concrete limits (64 KB JSON input, 1 s per call, 1 MB result). Those limits and the determinism guarantee are exactly the operational facts an agent needs and cannot get from 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 action, then labelled sections (When / Not for / Side effects / Deterministic / Limits), so scanning is easy. It is however duplicated verbatim across Spanish and English, roughly doubling length for a two-parameter tool, even if every individual sentence carries 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 an output schema present and rich annotations, the description needs only the operational envelope — and it supplies it: accepted input forms, RFC variant, determinism, absence of side effects, and size/time ceilings. Nothing an agent needs in order to call this 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 enum values and default are already documented; the description adds only that text is interpreted as UTF-8. The EN text says 'hex/base64 bytes' as valid input while the schema enum permits only utf8 and hex, which mildly misleads about what 'data' may contain.

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 (encode text/bytes to standard Base64, RFC 4648 §4, with padding) and immediately names the sibling it is not (base64-decode), plus the URL-safe variant is implicitly excluded by 'Base64 estándar'. An agent can distinguish it from base64url-encode and base64-decode 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' and 'No para' clauses with a named alternative (base64-decode), which is stronger than most definitions. The one flaw is the 'o desde ella' / 'to or from this encoding' phrasing, which suggests decoding is also in scope and sits awkwardly against the explicit 'No para: decodificar Base64' exclusion.

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