Skip to main content
Glama

Caribooks (QuickBooks Online)

List the receipt inbox

list_receipt_inbox
Read-only

List receipts, invoices and documents uploaded through the Caribooks portal or emailed to the account's receiving address. Returns each file's upload_id, company, kind, filing status and content preview. Kinds include transaction evidence, monthly statements and reference documents. Read-only; does not create transactions or attachments. include_filed includes filed statements and references. upload_id selects a document for a full-text read; text_offset pages through long documents, and cursor pages through older files. search, from, to, min_total and max_total find documents by the words, date and total read off them, filed receipts included; each line shows the vendor, date, number, total and summary read.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoOnly documents dated on or before this day, YYYY-MM-DD.
fromNoOnly documents dated on or after this day, YYYY-MM-DD, by the date written on them.
limitNoFiles per page, newest first. Defaults to 10.
cursorNoThe next cursor from a listing. Keep the same company and include_filed when continuing.
searchNoWords every matching document contains, in its vendor, number, summary, lines bought, text, file name, sender or subject. Case and accents do not matter. Searches filed documents too.
companyNoOnly the files sorted into this connected company. Every file when left out, each line saying which company it belongs to.
max_totalNoOnly documents whose total is at most this amount.
min_totalNoOnly documents whose total is at least this amount.
upload_idNoRead this file instead of listing previews. PDFs return up to 12,000 characters with a continuation until the end.
text_offsetNoContinue reading upload_id at the text_offset returned by the previous call. Defaults to 0.
include_filedNoAlso list filed statements and references. A named file includes these automatically; filed receipts live in QuickBooks.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / from
      Added value: +{
      +  "description": "Only documents dated on or after this day, YYYY-MM-DD, by the date written on them.",
      +  "pattern": "^(\\d{4}-\\d{2}-\\d{2})?$",
      +  "type": "string"
      +}
    • addedInput schema / properties / max_total
      Added value: +{
      +  "description": "Only documents whose total is at most this amount.",
      +  "type": "number"
      +}
    • addedInput schema / properties / min_total
      Added value: +{
      +  "description": "Only documents whose total is at least this amount.",
      +  "type": "number"
      +}
    • addedInput schema / properties / search
      Added value: +{
      +  "description": "Words every matching document contains, in its vendor, number, summary, lines bought, text, file name, sender or subject. Case and accents do not matter. Searches filed documents too.",
      +  "maxLength": 200,
      +  "type": "string"
      +}
    • addedInput schema / properties / to
      Added value: +{
      +  "description": "Only documents dated on or before this day, YYYY-MM-DD.",
      +  "pattern": "^(\\d{4}-\\d{2}-\\d{2})?$",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and destructiveHint, and the description reinforces this with 'Read-only; does not create transactions or attachments.' Beyond annotations, it discloses cursor pagination, full-text continuation via upload_id/text_offset, and search behavior over filed receipts. No contradiction with the annotations is present.

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

Conciseness4/5

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

The description is dense but efficient: purpose and return values are front-loaded, and the parameter-related sentences earn their place. The semicolon-heavy style packs a lot into seven sentences, and while it could be reorganized into clearer sections, there is no redundancy or filler.

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?

With no output schema and 11 parameters, the description carries a heavy burden, and it covers the key ground: document sources, return fields, file kinds, read-only behavior, filtering, search, and pagination. It does not spell out edge cases like missing upload_id behavior, but the essential information an agent needs to invoke the tool correctly is present.

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 grouping search/from/to/min_total/max_total as a coherent filtering behavior and explaining the output line format ('vendor, date, number, total and summary read'). It also clarifies the relationship among upload_id, text_offset, and cursor, which is not obvious from the schema alone.

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 opens with a specific verb and resource: 'List receipts, invoices and documents uploaded through the Caribooks portal or emailed to the account's receiving address.' It also names what is returned (upload_id, company, kind, filing status, content preview), which makes the tool's purpose unmistakable. The inbox scope distinguishes it from the many search/get/create siblings in the surrounding tool list.

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 context: it is read-only, does not create transactions or attachments, and notes that filed receipts 'live in QuickBooks' when include_filed is used. It does not explicitly name alternative tools or state when not to use this tool, so it stops short of a 5, but the usage context is unambiguous enough for correct selection.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources