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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the 'sin efectos secundarios' line adds nothing; the description does add real value with determinism, a 64 KB input cap, a 1 s per-call timeout and a 1 MB result cap. It stops short of saying what the output contains or how rounding interacts with the extraction mode.

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 and the when/not-for structure is easy to scan, but the body is near-duplicated in Spanish and English and ends with a meta-pointer ('[EN completo / full EN: inputSchema.description]') that is noise for an agent. The contradictory 'No para' sentence also costs space without adding usable guidance.

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?

Rich annotations, a full output schema and 100 % parameter coverage mean the description need not explain return values. What is missing is unambiguous disambiguation from vat-calculate — the stated exclusion conflicts with the tool's own stated behavior, which is the one thing an agent most needs here.

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 every property (rate enum, amount bounds, round_to_peso, amount_includes_iva) is documented in the schema. The description restates the rate set and the rounding default but adds no new semantics such as how rounding applies when extracting IVA from a gross amount, so baseline 3 applies.

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 ('Calcula el IVA colombiano') plus the supported rates (19 %, 5 %, 0 %) and the two modes (add to a base / extract from a total), with rounding to pesos. It explicitly names the sibling it is not (vat-calculate), so an agent can differentiate without opening either 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?

It has the right structure — a 'Cuándo' clause (DIAN, Ley Emiliani, COP, IVA, GMF, UVT; invoicing/payment flows) and a 'No para' clause naming vat-calculate. However, the exclusion says it is not for 'sumar o extraer un impuesto', which is exactly what the first sentence says this tool does ('suma a una base o extrae de un total con IVA'), so the routing rule is self-contradictory and may push the agent away from the correct tool.

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