Skip to main content
Glama
oliverames

MCP Server for Wave

by oliverames

Wave: List Invoices

wave_list_invoices
Read-onlyIdempotent

Retrieve invoices filtered by status, customer, date range, or amount due. Use UNPAID to find unpaid, or OVERDUE for past due invoices.

Instructions

List invoices, filtered by status, customer, date range, or amount due. To find unpaid invoices use status "UNPAID"; "OVERDUE" narrows that to ones past their due date.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNo1-based page number for offset pagination.
sortNoe.g. ["INVOICE_DATE_DESC"], ["AMOUNT_DUE_DESC"], ["CUSTOMER_NAME_ASC"]. Defaults to INVOICE_DATE_DESC.
statusNoDRAFT, SAVED, UNPAID, SENT, VIEWED, PARTIAL, PAID, OVERDUE, OVERPAID.
currencyNoCurrency code, e.g. "USD".
fetch_allNoWalk every page instead of returning just one. Slower, but complete.
page_sizeNoRecords per page (1-200).
source_idNoOnly invoices created from this source, such as an estimate ID.
amount_dueNoExact outstanding amount match, e.g. "250.00".
business_idNoBusiness to operate on: the base64 id from wave_list_businesses (a bare business UUID is also accepted). Defaults to the business set by wave_set_default_business. When calls may be minutes apart, pass it on every call.
customer_idNoOnly invoices for this customer.
invoice_numberNoSubstring match applied by Wave: 12 also matches 112 and 120.
modified_afterNoISO 8601 timestamp; only invoices changed after it.
modified_beforeNoISO 8601 timestamp; only invoices changed before it.
response_formatNoOutput format: "markdown" for a compact human-readable summary, "json" for the complete record.markdown
invoice_date_endNoLatest invoice date, YYYY-MM-DD.
invoice_date_startNoEarliest invoice date, YYYY-MM-DD.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.0.8
    • changedInput schema / properties / business_id / description
      Previous value: -"Business to operate on. Defaults to the session business set by wave_set_default_business."New value: +"Business to operate on: the base64 id from wave_list_businesses (a bare business UUID is also accepted). Defaults to the business set by wave_set_default_business. When calls may be minutes apart, pass it on every call."
    • addedInput schema / properties / source_id
      Added value: +{
      +  "description": "Only invoices created from this source, such as an estimate ID.",
      +  "type": "string"
      +}
  2. Changed1 schema field changedv1.0.6
    • changedInput schema / properties / invoice_number / description
      Previous value: -"Exact invoice number match."New value: +"Substring match applied by Wave: 12 also matches 112 and 120."
  3. First observedv1.0.2

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful domain context about UNPAID vs OVERDUE semantics, but does not disclose other behavioral aspects such as pagination defaulting to a single page unless fetch_all is set, or the impact of the response_format parameter. With annotations carrying the core behavior, this is an adequate but not rich transparency contribution.

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?

Two sentences, both purposeful. The first front-loads the core operation and filter capabilities; the second gives high-value status guidance. No filler, no repetition of schema details, and the structure moves from general purpose to specific filter usage.

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

Completeness4/5

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

For a tool with 16 optional parameters and no output schema, the description provides enough orienting context: it names the primary filter axes and gives concrete status usage. The schema documents each parameter thoroughly, so the description does not need to repeat them. A small gap is that pagination behavior and the effect of response_format are left to the schema, but the overall definition is sufficient for correct tool selection and invocation.

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 description coverage is 100%, so the baseline is 3, but the description adds value beyond the schema by grouping filters into categories (status, customer, date range, amount due) and by explaining the practical difference between UNPAID and OVERDUE statuses. This helps an agent reason about filter combinations without opening the schema.

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?

The description states a specific verb and resource ('List invoices') and immediately lists the main filter dimensions (status, customer, date range, amount due), clearly distinguishing this plural listing tool from the singular wave_get_invoice sibling. The resource is unambiguous and the sentence is action-oriented.

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

Usage Guidelines4/5

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

The description gives clear, actionable context on how to use the status filter: 'To find unpaid invoices use status "UNPAID"; "OVERDUE" narrows that to ones past their due date.' This is specific guidance that helps an agent select the right filter values. It does not explicitly compare to sibling tools like wave_get_invoice, but the listing intent is clear enough that no exclusion is needed.

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