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

Annotations already carry the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the description adds substantial behavior beyond them: the one-file-per-day ingestion pattern, the 5h next-day availability rule, the default trailing one-day lag, the 92-day cap, and payment-method scope including Pix na maquininha. None of this is inferable from the schema or annotations, and nothing contradicts the 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?

Four dense sentences, each earning its place: purpose and dashboard equivalence, groupings and output metrics, payment-method scope, and operational constraints. The core purpose is front-loaded and there is no filler or repetition of schema content.

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's enumeration of returned metrics (quantidade, valor bruto, valor líquido, cancelado, chargebacks) adequately covers the return contract, and the freshness/limit rules cover invocation timing. The main omissions are the undocumented account parameter and the unspecified date input format; otherwise the description is complete for a moderate-complexity read-only summary tool.

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 0%, so the description carries full documentation burden. It compensates for agrupar_por by listing all valid grouping values, for the date pair by stating the 92-day maximum and the yesterday default, and for incluir_pix by mentioning Pix coverage on the machine. Gaps remain: the account parameter is never explained and no date format is specified for data_inicio/data_fim.

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 opens with a specific verb-resource pair — 'Totais consolidados das vendas Stone no período' — and identifies itself as equivalent to the dashboard's Resumo de vendas. It enumerates exact grouping dimensions (forma de pagamento, bandeira, dia, status, captura, terminal) and output metrics (quantidade, valor bruto, valor líquido, cancelado, chargebacks), which clearly distinguishes it from siblings like stone_vendas_listar, stone_vendas_pix, and stone_vendas_cancelamentos.

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 provides clear context: this is the consolidated-summary counterpart of the panel's sales summary, and it gives concrete constraints that govern when results are valid — the daily file is only ready after 5h of the next day, the default window ends yesterday, and the maximum is 92 days per call. It does not explicitly name sibling alternatives or state when not to use it, which keeps it at a 4 rather than a 5.

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