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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint. The description significantly expands on these with critical behavioral details: a 5000-transaction-per-account cap flagged by truncated:true, a provider_incident block warning of incomplete data during provider outages, and detailed output structure (e.g., 'por_mes', 'top_despesas'). There is no contradiction with annotations, and the description adds substantial transparency beyond what annotations convey.

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 front-loaded with the key benefit and structured logically: purpose, parameter details, use cases, then behavioral notes. However, it is quite verbose, with some repetition (e.g., repeated mention of no need to call list_accounts). The length is justified by the tool's complexity, but trimming unnecessary phrases could improve conciseness without losing clarity.

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?

Given the tool's 9 parameters, no required fields, and absence of output schema, the description provides a complete understanding of the tool's behavior. It covers input parameter semantics, output structure (including the compact vs raw returns, per-account breakdown, and incident flags), usage boundaries (5000 cap, bulk support), and error/edge cases (provider incidents). The description compensates fully for the lack of an output schema.

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?

Despite 0% schema description coverage, the description thoroughly explains every parameter: item (accepts connector_id, connector_name, item_id), from/to (ISO dates), granularity (default 'monthly' vs 'raw'), detail (compact/rich/raw with specific output differences), type (BANK or CREDIT), top_n (implied in 'largest N'), item_ids (batch execution). The semantic meaning is fully conveyed, enabling correct use without schema descriptions.

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 that the tool provides 'consolidated cash-flow analysis for a whole bank connection over a period, in ONE call'. It explicitly distinguishes from siblings by noting that it resolves accounts internally, eliminating the need to call openfinance_list_accounts first. The specific use cases and output structure are detailed, making the purpose unambiguous.

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 strong usage guidance by listing concrete scenarios like 'análise anual/mensal', 'fluxo de caixa', and explains when to use different granularity and detail options. It also mentions bulk support and the ability to omit the item parameter to analyze all linked banks. While it does not explicitly state when NOT to use this tool, the context of sibling tools and the detailed parameter descriptions offer clear direction. A slightly more explicit exclusion would improve the score.

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