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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description discloses important behavioral traits: scan caps at 5000/account with a truncated flag, and potential provider_incident block that may affect data completeness. These are not indicated by annotations and add significant transparency.

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 description is somewhat lengthy but front-loaded with the core purpose. Every sentence adds value, covering parameters, behavior, and output. However, it could be more structured (e.g., bullet points) for quicker scanning. Still, it is efficient and not verbose.

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?

Without an output schema, the description thoroughly explains return values: total entradas, saídas, saldo_liquido, monthly evolution (por_mes), top_despesas/top_recebimentos, per-account breakdown. It also covers error conditions (provider incident, truncation). For a 9-parameter tool with no output schema, this is remarkably complete.

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?

With 0% schema description coverage, the description fully compensates by explaining all 9 parameters in detail. It specifies that 'item' can be connector_id, connector_name, or item_id; 'from'/'to' are ISO dates; 'granularity' defaults to 'monthly' (compact summary) vs 'raw' (consolidated transactions); 'detail' options (rich, raw) add merchant info or full object; 'type' filters BANK/CREDIT; 'top_n' is implied in top_despesas/top_recebimentos; 'item_ids' for bulk. This adds significant meaning beyond the schema.

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 clearly states the tool's purpose: 'Consolidated cash-flow analysis for a whole bank CONNECTION over a period, in ONE call.' It distinguishes from siblings by explicitly noting that it resolves accounts internally, so the user does not need to call openfinance_list_accounts first. The verb and resource are specific and well-defined.

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 provides explicit guidance on when to use this tool: for 'análise anual/mensal', 'fluxo de caixa', 'entradas e saídas', 'maiores gastos/recebimentos'. It also advises when to use alternatives (e.g., set granularity to 'raw' for itemized rows, or combine with detail options). It explains parameter usage (omit item for all banks, ISO dates, etc.) and trade-offs (raw is heavier).

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