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

Annotations already flag destructiveHint=true and openWorldHint=true, but the description adds real behavioral detail beyond them: a preview-first two-step flow gated on strict confirm=true, client-facing email being sent, and the clarification that no funds move through the assistant. That is exactly the context an agent needs before firing a destructive operation.

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?

Four short sentences, front-loaded with the core action and immediately followed by the preview/confirm safety model. Every clause carries information; nothing is restated from the title or schema.

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 destructive, schema-rich tool with no output schema, the description covers the essential risk model (preview then confirm), the side effect (email dispatched), and the boundary (no money movement). It stops short of describing what the preview contains or how multiple currencies are surfaced, which is a minor gap.

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 75% and the schema already documents period, confirm, and booking_ids thoroughly. The description still adds meaning by framing period vs booking_ids as mutually alternative selection modes (id-based or calendar-month) and clarifying the per-currency invoice granularity that no single parameter expresses.

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 precise verb+resource and scope: create one invoice per currency for a client's sessions, by booking id or calendar month, then email it. The 'no money moves through the assistant' clause also distinguishes it in spirit from send_pay_link, so an agent can tell what this tool is without opening the 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?

Gives clear invocation context: it returns a preview first and only acts when confirm=true, and it explains the two input modes (by id or by calendar month). It does not explicitly compare itself to siblings like send_pay_link or who_owes, so no exclusion guidance is present.

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