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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses key behavior: heuristic detection based on repeated merchants, combination with fixed registered accounts, classification by amount stability, limitation to connected accounts, and a fixed 6-month window with no date filtering. This is substantial transparency about how the tool actually behaves.

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 longer than average but every sentence carries distinct value: purpose, user intents, scope, algorithm, classification, exclusions, and time window. It is front-loaded with the main purpose and contains no filler.

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?

The description covers purpose, when-to-use, exclusions, and algorithm, which is strong for a read-only detection tool. However, there is no output schema and no explanation of return shape, and several input parameters remain undocumented, so an agent may still struggle to invoke it fully correctly in all cases.

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?

The input schema has 0% description coverage, so the description must compensate, but it only hints at parameters. 'Sem datas, últimos 6 meses' implies start_date/end_date are ignored, and 'mesmo estabelecimento repetido em vários meses' vaguely suggests min_occurrences, but account, end_date, and include_recurrences are not meaningfully explained.

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 and resource: 'Detecta ASSINATURAS e serviços recorrentes' and gives concrete examples such as Netflix, Spotify, and rent. It also explicitly differentiates the tool from the sibling find_installments, making its scope unmistakable.

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 lists direct user intents ('minhas assinaturas', 'o que pago todo mês', 'o que posso cancelar') and states the operational context (Open Finance connected accounts/cards). It also provides an explicit when-not-to-use rule and names the alternative: 'NÃO inclui parcelamentos (use find_installments)'.

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