Find recurring charges

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world), so the description's added value is the amount semantics: BRL currency, positive = money leaving the account, and refunds/card payments/deposits reported separately as credits. That sign convention is genuinely non-obvious context. It stops short of describing result shape or how partial matches are handled.

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?

Three dense sentences, front-loaded with the detection rule before the caveat and the sign/currency note. Every clause carries information an agent cannot get from the schema or annotations.

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 does the heavy lifting on what counts as a match and how amounts are signed, which is the essential context. It omits what a returned result contains and whether near-misses are surfaced, but nothing critical to invoking the tool correctly is missing.

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 100%, so both parameters (bank, min_months) are already documented and the baseline is 3. The description reinforces the cadence semantics ('about once a month', 'in several different months') that contextualize min_months and adds the 5% amount tolerance, but adds no syntax or format detail 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?

States a specific verb and resource ('detect likely subscriptions') and then defines the exact heuristic: same merchant, amount within 5%, roughly monthly, across several months. That precision clearly separates it from siblings like spending_summary or search_transactions, which do not infer recurrence.

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 implies when the tool is appropriate (identifying subscriptions) and gives one exclusion (installment purchases are ignored), but never names an alternative sibling or states when to prefer raw transaction search instead. Usage must be inferred from the purpose.

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