send_invoiceGet one of the signed-in person’s invoices ready to email, with its PDF, to the client address on it from their business name. It opens a card showing exactly what the client will receive (who it goes to, the lines and the total) with a Send button. Nothing is emailed until the person presses Send on that card.
| Name | Required | Description | Default |
|---|---|---|---|
| invoiceId | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, but they cannot convey the confirm-before-send safeguard. The description adds real behavioral context: it opens a non-destructive confirmation card and no email is dispatched until the user presses Send, which resolves what would otherwise look like a write tool.
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 tight sentences, front-loaded with the action, then the card contents, then the no-email safeguard. Nothing is redundant, though the parenthetical listing of card fields is slightly enumerative.
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 and only 0%-covered params, the description carries most of the burden and does so adequately: it explains the effect (card preview) and the safety guarantee (nothing sent until confirmation). It stops short of describing the tool's return value or the eventual send path.
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% and the single invoiceId is only described as a UUID pattern. The description compensates partially by scoping it to 'one of the signed-in person's invoices', implying an ownership constraint, but it adds no guidance on obtaining or validating the id.
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 action: fetching one of the signed-in user's invoices and surfacing it as a preview card with PDF, recipient, lines and total. That is concrete, but the very close sibling send_invoice_from_card is never named, so the agent must infer the preview-vs-send split rather than being told.
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 statement that nothing is emailed until the user presses Send implies this is the pre-send preview step, which is useful implied usage. However there is no explicit when-to-use/when-not against send_invoice_from_card, create_invoice, or list_invoices, so the agent gets context only by inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.