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

Annotations only declare the generic profile (write, non-idempotent, destructive); the description adds substantive behavior: exactly which fields are copied (client, lines, tax, discount, deposit), the side effect that the estimate becomes approved, that nothing is transmitted to the client, and the duplicate-invoice rejection. That is a genuine mutation-safety disclosure beyond the annotations, and it does not contradict destructiveHint since it openly states a state change on the estimate.

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?

The description is front-loaded with the action and its output, then layers constraints and next steps in a logical order. The "nothing is sent" point is made twice (opening and closing), which is mild redundancy, though the closing mention usefully names send_invoice as the gate.

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 single-parameter conversion tool with no output schema, everything an agent needs is present: what gets produced, what side effect hits the estimate, the failure condition, and what to call next to actually deliver the invoice. No output-schema explanation is required.

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 there is only one required parameter (estimate_id, sourced from list_estimates), so the schema already does the work. The description still adds meaning by establishing that all invoice content is derived from the estimate, so the agent knows no other fields are needed and shouldn't attempt to supply them.

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?

The first sentence states a specific verb and resource ("Generate an invoice") and immediately bounds it ("with everything from the estimate"), which separates it from create_invoice and create_estimate. The Joist UI reference ("Does what Generate Invoice does in Joist") anchors the semantics of a copy-conversion rather than a fresh creation.

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?

Usage context is clear: use this to turn an existing estimate into an invoice, and the refusal case ("an estimate already invoiced is refused here") tells the agent when the call will fail. It also routes the follow-up step to send_invoice. It does not explicitly contrast with create_invoice for building an invoice from scratch, so not a full 5.

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