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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavioral information: it returns official legal sources and a link to the web calculator, which matters because there is no output schema. It says nothing about error handling or how rates are resolved when inputs are ambiguous.

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?

The core question is front-loaded in the first clause, and the rest is dense, example-driven legal context with no filler. It is slightly long with stacked resolution citations, but each sentence carries information an agent cannot get from structured fields.

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 an 11-parameter, two-jurisdiction tool with no output schema, the description covers what is computed, under which rules, and what is returned. The remaining gap is that conditional requirements are only implied (e.g. which parameters become necessary once country=ec vs country=py), leaving the agent to infer the effective schema from per-parameter descriptions.

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 parameter is already documented with country tags and enum meanings, so the schema does the heavy lifting. The description only supplements with the underlying legal resolutions (NAC-DGERCGC26-00000009, NAC-DGERCGC20-00000061, Decreto 3107/19, Ley 6380/19), which is corroborating context rather than new parameter semantics. 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 concrete verb and resource ('calcular retenciones') and frames the exact question it answers ('Cuánto retener en una factura y cuánto pagar al proveedor'). It also scopes the two jurisdictions and names the taxes involved, which distinguishes it from siblings like calcular_iva or calcular_impuesto_renta.

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?

The description establishes clear usage context by enumerating the scenarios it covers (Ecuador renta/IVA withholding by buyer type; Paraguay local IVA retention or INR/IDU), which is effectively a when-to-use map. It does not, however, explicitly exclude alternatives or tell the agent when to prefer calcular_iva or calcular_impuesto_renta instead.

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