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

Annotations already declare destructiveHint=true and openWorldHint=true, so the description earns credit for adding the non-obvious approval gate ('Waits for the owner's approval') — an agent otherwise might assume the email goes out immediately. It does not say what happens if approval is denied, whether a second call resends, or how the pending state is observed.

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?

Two short sentences, zero filler, with the delivery behavior front-loaded before the approval caveat.

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?

No output schema and no return value described; more importantly, an approval-gated side effect needs to say what the caller gets back and how to check whether the invoice was actually sent. Adequate for invoking correctly, thin for understanding the outcome.

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 80%, so the baseline is 3. The description restates the `to` default (customer) and 'PDF' delivery, but adds nothing for copy_me, which is the one parameter left undocumented by the schema, and gives no syntax guidance for the address array.

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?

Specific verb (emails as PDF) plus resource (the invoice) and delivery targets ('the customer or to the addresses you give'). It does not differentiate itself from the parallel siblings send_estimate and send_change_order, which is the only reason it falls short of a 5.

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?

The invoice_id schema note ('From list_invoices or create_invoice') plus the description imply the prerequisite (an existing invoice), and the approval caveat hints at the workflow. But there is no explicit when-to-use/when-not guidance or comparison against send_estimate or send_change_order.

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