wave-mcp-server

Email Wave invoice to client

wave_send_invoice

Destructive

Email an approved invoice after previewing recipients and totals; confirm to send, as it reaches a real client and cannot be unsent.

Instructions

Have Wave EMAIL an approved invoice to the given addresses. This reaches a real client and cannot be unsent. The preview shows recipients, subject, totals and tax, and whether a recipient matches the customer's email on file. This is a two-step tool: the first call (confirm omitted) returns a preview and a fingerprint and changes nothing. Show the preview to the user. Only after they agree, call again with confirm: true and the fingerprint.

Input Schema

TableJSON Schema

Name	Required	Description
`to`	Yes	Recipient email addresses
`confirm`	No	Leave false to get a preview (nothing happens). Set true only after the user has seen the preview and agreed, and pass the preview's fingerprint.
`message`	No	Email body text (default: Wave's standard message)
`subject`	No	Email subject (default: Wave's standard subject)
`cc_myself`	No	Send a copy to the Wave account owner (default false)
`attach_pdf`	No	Attach the invoice PDF (default true)
`invoice_id`	Yes	Invoice ID exactly as returned by Wave (an opaque string)
`fingerprint`	No	The fingerprint returned by the preview call; required with confirm: true

Output Schema

TableJSON Schema

Name	Required	Description	Default
`status`	Yes
`invoice`	No
`message`	Yes
`preview`	No
`fingerprint`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 15, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already flag destructive/openWorld/non-idempotent, and the description adds the consequences in plain terms: it reaches a real client and cannot be unsent, and it enumerates what the preview surfaces (recipients, subject, totals, tax, customer-email match).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The irreversibility warning is front-loaded, followed by preview contents and then the two-step mechanics. Every sentence carries distinct, actionable information with no repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value documentation is not needed, and the description supplies the operational context (preview contents, fingerprint handshake, confirmation gate) that makes a destructive, irreversible email tool safe to invoke.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema by tying confirm and fingerprint together into a two-step safety gate and explaining what the preview returns before confirmation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Have Wave EMAIL an approved invoice to the given addresses'), and the scope ('approved invoice') separates it from siblings like wave_mark_invoice_sent or wave_create_invoice.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Lays out an explicit when/when-not protocol: first call with confirm omitted returns a preview and changes nothing, show it to the user, and only then call again with confirm: true plus the fingerprint. The agent knows exactly which call to make at which point.

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

Deploy Server