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 adds genuinely new behavior: invalid characters are rejected, padding is optional, whitespace is ignored, plus concrete limits (64 KB JSON input, 1 s per call, 1 MB result). That is exactly the kind of constraint an agent cannot get from the annotation block.

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 core verb and resource, then clearly labeled Cuándo / No para / Efectos / Determinista / Límites sections that each carry distinct information. Cost is the full bilingual duplication, and 'Determinista' largely repeats the idempotentHint annotation.

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 two-parameter pure function with an output schema and full annotation coverage, the description covers input tolerance, error rejection, size/time limits and side-effect freedom — everything needed to invoke it correctly. Return-value shape is correctly left to the output schema.

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 baseline is 3, but the description adds semantics the schema lacks: whitespace in the input is ignored and out-of-alphabet characters are rejected, which tells the agent how leniently to clean input before calling. It also confirms the three output encodings, though the Spanish half omits the 'base64' output option.

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: decodes standard or URL-safe Base64 into UTF-8 text, hex or base64, and explicitly names base64-encode as the thing it is not. It does not address the very close sibling base64url-decode, so the agent still has to infer when this tool versus that one applies.

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' and 'No para' pair with a named alternative (base64-encode), which most siblings lack. However the 'when' clause is muddled ('convertir bytes o texto a esta codificación, o desde ella'), describing both directions for a one-directional tool, and never mentions base64url-decode or ascii85/base32/base58 decode siblings.

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