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 largely restates these ("solo lectura, sin red, sin estado guardado", determinism). The genuinely additive facts are the 12-significant-digit precision and the hard limits (64 KB input, 1 s per call, 1 MB result), which the agent cannot get from annotations or schema.

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?

Each language block is tightly front-loaded with labeled sections (Cuándo / No para / Efectos secundarios / Determinista / Límites), so scanning is fast. The cost is that the entire block is duplicated in Spanish and English, roughly doubling length for the same information; justified only if the bilingual audience is real.

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 pure-function conversion tool with an output schema present, everything an agent needs is covered: units, default behavior when `to` is omitted, precision, determinism, and resource limits. 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 description coverage is 100% and each of the three parameters is documented there, including the unit list for `from` and "omit for all" for `to`. The description adds the same unit enumeration and the default-all behavior, so it is essentially redundant at the parameter level — baseline 3.

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 ("Convierte densidad entre unidades") and enumerates the supported units, so the agent knows exactly what magnitude is being transformed. It also disambiguates from the large family of convert-* siblings by naming convert-mass as the one it is not. No schema access needed to identify it.

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 / When" condition (a quantity must be converted with exact definitional factors) and an explicit "No para / Not for" exclusion routing mass conversions to convert-mass. The "sin 'to' devuelve todas" note also tells the agent the behavior of the optional-parameter branch.

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