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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the agent already knows it is a non-destructive but non-read-only operation. The description adds two useful facts beyond the annotations: the sample is 'gratuita' (free, implying no credit consumption) and it does not persist alerts. It still leaves open whether the call consumes quota or what side effect justifies readOnlyHint=false, so it does not reach the higher bar.

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?

A single tight sentence with the key facts (free sample, inputs, no alert creation) front-loaded and zero filler. It is efficient, though it is arguably too terse for a tool with a four-key nested filter object.

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 preview tool with no output schema, the description conveys the input modes and the crucial negative constraint that no alerts are created, which is the main thing an agent must know. It omits credit/quota and return-shape details, but with 100% schema coverage and no output schema the remaining gap is modest.

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%, including the nested filtros object and the CNPJ term-suggestion behavior ('até 8 famílias'), so the schema does the heavy lifting. The description merely restates that the sample is driven by 'termos/filtros' or CNPJ, adding no syntax or precedence detail beyond the schema, 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?

Names a concrete resource and mode ('Amostra gratuita de compras') and distinguishes itself from the alert-creation siblings by explicitly stating 'Não cria alertas', which separates it from criar_alerta/editar_alerta in the sibling list. The one-sentence form is clear, though it does not name the alternative tool by name.

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 phrase 'Não cria alertas' gives an implicit when-not signal and 'Amostra gratuita' implies a preview/trial use case before committing to an alert. However, no explicit condition or named alternative (criar_alerta, alerta_por_cnpj) is provided, so the agent must infer when to prefer this tool.

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