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

Annotations already declare readOnlyHint, openWorldHint=false and idempotentHint, so the safety/determinism sentences largely restate structured data. The genuine addition is the operational limits (64 KB input, 1 s per call, 1 MB result) and the ambiguity rule for «1.250»-style digits, which the agent cannot infer from 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 core mapping and examples, then layered as when / not-for / effects / limits, and every section is short. It loses a point only because the side-effects and determinism sentences duplicate the annotation block and the ES/EN doubling makes the payload denser than strictly necessary.

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, return format needs no explanation, and the description still covers the ambiguous-input hazard, scale convention, exclusions, and size/time limits. Nothing an agent needs in order to invoke it 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 baseline is 3; the description earns above that by explaining *why* decimal_separator exists — one separator followed by three digits is ambiguous without it — and by noting accents are optional and «menos» is understood, none of which the schema spells out.

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 precise verb+resource (converts Spanish number words or digits to a number) and backs it with concrete input→output examples («tres mil cuatrocientos veintiuno» → 3421) plus the long-scale convention. It is clearly distinguishable from the inverse sibling es-number-to-words and from co-cop-parse.

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 routing is provided: «Cuándo: hay que tratar texto, números o fechas en español según las reglas escritas» and an explicit exclusion «No para: convertir textos de dinero en estilo colombiano (co-cop-parse)». The agent has both the positive condition and a named alternative to fall back on.

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