cashflow_forecast

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

Annotations already declare readOnlyHint=true, so the safety profile is covered elsewhere. The description does add genuine behavior: it names which data sources feed the projection (open invoices, recurring invoices, tax deadlines on 30 June / 30 November, fixed expenses) and states that the result flags months with negative balances. It stops short of disclosing assumptions (e.g. how overdue items and revenue_estimate feed the model, currency, or whether values are cumulative).

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?

Two dense sentences with no filler; the core scope (month-by-month projection and its inputs) is front-loaded, followed by the computed outputs. Slightly long clauses, but every element earns its place.

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 seven optional parameters, no output schema, and non-trivial financial modelling, the description covers what is computed and what the result means well enough to call the tool correctly. The remaining gap is the shape of the return (monthly rows? totals? currency?) and the model's assumptions, which an agent would have to discover from the response.

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 coverage is high (86%), so the parameters are largely self-documenting and the baseline of 3 applies. The description corroborates a few of them implicitly — fixed expenses maps to monthly_expenses, amounts to set aside map to tax_fund, expected receipts map to revenue_estimate — but adds no syntax, units, or interaction rules (e.g. how include_overdue changes the first month) 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?

A specific verb ("Previsione") applied to a specific resource (cash flow month by month), plus an enumeration of the inputs it combines (open invoices, recurring invoices, tax deadlines, fixed expenses) and the derived output (how much to set aside, negative-balance months). An agent can tell this is a projection tool rather than a raw report, though it never names the closest siblings (receivables_report, recurring_expenses_report, tax_estimate) to sharpen the distinction.

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?

Uses the description content to imply when the tool applies, but gives no explicit when-to-use or when-not-to-use guidance and does not point to alternatives for narrower needs (e.g. receivables_report for collections only, tax_estimate for tax accrual only). With many adjacent reporting/report tools in the sibling list, an explicit routing sentence is the missing piece.

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