Email invoice

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

The annotations already flag destructiveHint=true, openWorldHint=true and non-idempotence, but the description adds genuinely new context beyond them: the action is irreversible, recipients should be confirmed beforehand, and the call will fail unless emailSendEnabled is true on the business. It doesn't mention rate limits, whether sending changes the invoice status, or what happens on partial success with multiple recipients.

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?

Three short sentences, front-loaded with the action and the irreversibility warning before the prerequisite. The parenthetical "(wave_get_business emailSendEnabled)" is efficient but slightly telegraphic; no filler is present.

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, open-world send operation with no output schema, the description covers the safety narrative and one prerequisite well. However, five of seven parameters remain unexplained and the agent is not told what the tool returns or whether the invoice's sent status changes, leaving a real gap for a 7-parameter mutation.

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?

With 7 parameters and only 29% schema description coverage, the description needed to compensate and instead says nothing about `message`, `subject`, `ccMyself`, `attachPDF` (which defaults to true) or `fromAddress`. Only the recipient concept is gestured at via "real recipients"; the optional email-shaping parameters are 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?

"Email an invoice through Wave to real recipients" gives a specific verb (email) and resource (invoice), and the phrase "real recipients" distinguishes it from the nearby mark-sent-style tools that only change status. It stops short of naming the sibling alternative (e.g., wave_mark_invoice_sent) explicitly, so the differentiation is implied rather than stated.

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?

It supplies a clear precondition (email sending must be enabled for the business) and an operational instruction (confirm recipients first) that an agent can act on before calling. It does not say when to prefer this over wave_mark_invoice_sent, so the alternative-routing guidance is incomplete.

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