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

Annotations cover the safety profile (readOnly=false, destructive=false, openWorld=true), so the bar is lower; the description still adds real context beyond them by disclosing the external recipient, the per-call confirmation default and how to disable it, the required API-key/app access, and the returned send time. It stops short of mentioning rate limits or the effect of repeated resends, so not a full 5.

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 core action and efficient overall, but there is mild redundancy: the title sentence and 'Resends one unpaid invoice to its customer' restate each other, and the confirmation behavior is stated twice ('By default you confirm each call' and 'confirm with the user before each call'). Trimming one of these would make it tighter.

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 one-parameter action tool with no output schema, the description covers purpose, side effects on an external person, confirmation behavior, auth requirements, and the return value (send time). Nothing critical to correct invocation is missing, though rate-limit or idempotency notes would round it out.

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 100% and the single parameter already documents 'Invoice ID from list_invoices.', so the schema carries the load. The description adds no format, source, or validation detail for invoice_id, making the baseline 3 correct.

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 (resend) plus resource (unpaid invoice) and recipient (its customer), and anchors it to a recognizable UI action ('the same as Resend in the Actions menu of the Invoice Dashboard'). An agent can distinguish it from siblings like bookingkoala_list_invoices or bookingkoala_refund_charge without opening any schema.

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?

Constrains the tool to 'one unpaid invoice' and reinforces the human-in-the-loop condition ('Reaches other people: confirm with the user before each call'). It does not name a competing sibling or state when-not-to-use, but the applicability condition is clear.

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