Métricas de venta (30 días)

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

Annotations already cover read-only and non-destructive behavior, so the description adds value by detailing the aggregation semantics: it sums all stores, can be narrowed to one account, and lists the output contents including shipping breakdown and product ranking. It does not contradict the annotations and no hidden destructive behavior is implied.

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?

Two direct sentences with no filler: scope is front-loaded, every metric in the run-on list contributes value, and the account-filter behavior is stated at the end. The all-caps 'SUMANDO TODAS' is emphatic but reinforces the key aggregation semantics.

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 no output schema, the description must explain what the tool returns, and it does: it enumerates sales counts, revenue, net after commissions, average ticket, per-store contribution, shipping-type split, and top products. The only optional parameter's effect is also described, making the definition complete enough for correct invocation.

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?

The schema already documents 'cuenta' fully, so the baseline is 3. The description adds explicit behavioral meaning: 'si le pasas una cuenta, muestra solo esa' and clarifies that omitting it means all stores, resolving the schema's slightly ambiguous 'por defecto / todas'.

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?

The description has a specific verb ('Resumen') and resource ('ventas de los últimos 30 días') and spells out the exact metrics delivered: ventas, facturado, neto, ticket promedio, aporte por tienda, envíos por tipo, and top 12 productos. It clearly distinguishes itself from generic dashboards and narrower sales tools by stating the all-stores aggregation scope.

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 implies the tool is for a 30-day sales overview across all stores and that passing a 'cuenta' filters to one store, but it never explicitly says when to prefer this tool over sibling tools like ml_ventas_geo, ml_caja, or ml_rentabilidad. No alternatives or exclusions are named.

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