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

Annotations already mark this as a non-readonly, open-world write with destructiveHint=false. The description adds meaningful context beyond them: the send flag's effect (saved draft vs client email with payment link), the per-call user confirmation requirement, and the Cotlet API key need. It does not state reversibility of a sent invoice.

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?

'Saved to send later or sent with an online payment link' appears in both the opening and third sentences, which is redundant. The purpose is front-loaded, but the repetition and the final API-key/confirmation notes pad the length without new information.

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?

With no output schema, the description covers the operation, both send modes, and the confirmation/key requirements. It does not describe the returned invoice identifier or state after creation, which is a minor gap for a write tool.

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%, so the baseline is 3. The description adds real meaning beyond the terse schema text by explaining that send=true attaches an online payment link and dispatches to the client, while send=false only saves. client_id and line_items semantics still come from the schema.

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 second sentence states a clear verb+resource: 'Creates an invoice on the client card from line items,' which distinguishes it from read siblings like thryv_list_invoices. The first sentence is an awkward fragment ('Thryv: Invoice on the client card...'), but the intent is recoverable. It does not explicitly contrast with thryv_create_estimate.

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 clearly explains the send=false vs send=true branch (save to send later vs send now with a payment link), which is the key decision an agent must make. It also mandates confirming with the user before each call. It lacks explicit direction on when to prefer create_invoice over create_estimate.

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