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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint), the description reveals important behaviors: internal fan-out of accounts, default compact summary, raw granularity option, capping at 5000/account with truncation flag, and potential provider_incident block affecting data completeness. It also notes that reconnecting does not fix provider issues. No contradiction with 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?

The description is lengthy (nearly 400 words) but well-structured and front-loaded with the core benefit. Each sentence adds value given the tool's complexity (9 parameters, multiple enums, warnings). Slightly verbose due to repetition (e.g., 'fluxo de caixa' phrase), but still appropriate for the information density.

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?

Despite no output schema, the description thoroughly describes return values: total entradas/saídas/saldo_liquido, monthly evolution, top expenses, per-account breakdown, and for raw granularity, consolidated transactions with optional enrichment. It covers truncation and provider incidents. With 9 parameters and no output schema, this is a complete and informative description.

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 each parameter: 'item' accepts connector_id, connector_name, or item_id; omitting it analyzes all banks; 'from'/'to' are ISO dates; 'granularity' values and their output types; 'detail' options (compact, rich, raw) and what they enrich; 'type' filters BANK/CREDIT; and 'item_ids' for bulk. This adds essential meaning beyond the raw 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 provides consolidated cash-flow analysis for a bank connection over a period, resolving accounts internally and fanning out transactions. It distinguishes from siblings by explicitly noting that users do not need to call openfinance_list_accounts first. The verb 'list' and resource 'transactions_by_item' are well contextualized.

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 when-to-use guidance, such as using this tool instead of separate account listing calls, and specifying use cases like 'análise anual/mensal', 'fluxo de caixa'. It explains when to choose granularity ('monthly' vs 'raw') and detail ('rich' vs 'raw'), and warns about truncation at 5000/account and provider incidents. It also covers the option to omit 'item' for all linked banks.

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