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

readOnlyHint=true is consistent with a pure read tool. Beyond the annotation, the description discloses the return shape in useful detail — aggregated totals plus per-invoice paid and outstanding amounts — which matters because there is no output schema. It does not state whether cancelled/draft invoices are included in the totals, which for a financial statement is the one thing left uncovered.

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?

Front-loaded with the payload (totals + invoice list), then the optional period constraint, then two short clarifiers. Four sentences, no filler; "Pure facts, no advice" is slightly meta but cheaply prevents the agent from expecting advisory output.

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?

For a read-only, 3-parameter tool with no output schema, the return contents are described adequately. However, key inclusion rules that determine whether the numbers can be trusted (draft/cancelled/rectified invoices, currency, date basis for 'collected') are absent, which is a meaningful gap for a statement tool used near reconciliation tasks.

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 schema already documents desde/hasta format (YYYY-MM-DD, inclusive, omit for whole history) at 67% coverage. The description adds meaning beyond that by clarifying the period filters on issue date specifically rather than payment date — a real semantic distinction — and that leaving it out yields the full history. customer_id remains undocumented in both places.

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?

Names a specific resource (customer account statement) and enumerates exactly what it returns: total invoiced, collected, outstanding balance plus the invoice list, with per-line paid/outstanding. This separates it functionally from plain get_invoice/list_invoices (aggregate roll-up per customer), though it never names a sibling to route against.

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?

"Optionally limited to a period by issue date" and "Pure facts, no advice" imply the usage context (period-scoped reconciliation view, no recommendations), but there is no explicit when-to-use-this-vs list_invoices/get_customer guidance and no stated prerequisites such as whether the customer must exist or have finalized invoices.

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