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 context beyond them: the email contains a Pay Now link and the invoice PDF, it goes to the customer's address, and it 'Can't be undone,' which confirms the irreversibility in user terms. It stops short of saying what the response returns or which connected mailbox sends it.

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 what the tool does, then the prerequisite/confirmation gate, then the irreversibility warning in four words. No filler or restated field names.

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 one-parameter irreversible mutation with no output schema, the description covers purpose, contents of the email, the confirmation workflow, and irreversibility. The notable remaining gap is the return value and any account/permission requirements for the sending mailbox.

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 0% on a single uuid invoice_id, so the description has to carry the burden. It does meaningfully: 'one invoice' scopes the parameter to a single invoice, and the instruction to call find_invoices first tells the agent where the id comes from and that a human-visible number/amount/email check should precede use.

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 description names a specific verb and resource ('Email one invoice to its customer') and pins down the exact artifact sent ('the same email as the Invoices page Send button (Pay Now link and PDF)'). It implicitly separates itself from send_estimate/send_pay_link/send_text by scoping to a single invoice email, though it never names those siblings explicitly.

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 gives an explicit prerequisite chain ('First call find_invoices and tell the owner the invoice number, amount and email it goes to') and a hard gating condition ('Only call after the owner says send'). That is a clear when-to-call and when-not-to-call rule an agent can follow without inference.

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