Resend an invoice

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

Goes well beyond the annotations (readOnly=false, destructive=true, idempotent=false, openWorld=true): it discloses that the invoice record itself is unchanged, that CC and billing addresses also receive the email, that delivery is immediate, that attach_pdf follows the invoice setting, and that some resends fail with a warning whose message is carried in the error. That is exactly the side-effect and failure information an agent needs before invoking an irreversible external send.

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?

Front-loaded with the core action, then ordered from mechanism to side effects to failure modes; every sentence carries information. It is on the dense side and repeats a few schema defaults (email default true, attach_pdf default), which is minor waste.

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 side effects, timing, and error behavior well, but says nothing about what a successful response contains. Given the tool's simplicity and the presence of annotations, this is a small residual gap rather than a blocking one.

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 each parameter already documents its default, so the description's restatement of email/sms/attach_pdf defaults adds little. The one genuine addition is that the email also reaches CC and billing addresses, but that is about effect rather than parameter meaning.

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?

States a specific verb+resource+mechanism ('Send an invoice to its customer again by email, text or both') and anchors it to the 'Resend button' behavior. It also identifies the source of the input ('an existing invoice from list_invoices'), separating it from sibling tools like send_quote and list_invoices.

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 clear context for when to use it (re-sending an already-existing invoice rather than issuing a new one) and notes that certain invoices, such as void ones, will be rejected. It does not explicitly name when to prefer a sibling tool or state exclusions beyond the void example, so it falls short of full routing guidance.

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