Skip to main content
Glama

Caribooks (QuickBooks Online)

search attachables

search_attachables
Read-only

Search attachment records (files and notes pinned to QuickBooks records). Each result names the file and the records it is attached to. Search results do not include a TempDownloadUri download link.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
companyNoWhich connected QuickBooks company to use (name, realm id, or connection id). Optional when only one company is connected.
criteriaNoCriteria accepts: an array of {field, value, operator} objects (operators: =, <, >, <=, >=, LIKE with % wildcards, IN), a simple {Field: value} object, or {criteria: [...], asc|desc: "Field", limit, offset, count}. Filters are ANDed; QuickBooks has no OR, cannot filter on Line fields, and only filters top-level fields (TxnDate, DocNumber, CustomerRef, VendorRef, Balance, TotalAmt, DueDate, MetaData.LastUpdatedTime, ...). Field names and values are case-sensitive as QuickBooks stores them. Government identifiers, birth dates and card-processing details are not available through these tools. One call returns one page of at most 1000 records, and a large page is truncated to fit the answer: narrow with filters or walk it with limit and offset rather than asking for everything. Omit to return the first page of all attachable records.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already indicate readOnly and non-destructive behavior, so the bar is lower. The description adds valuable behavioral context: it discloses that results only name the file and associated records and explicitly excludes a download link. The criteria parameter description further documents pagination behavior (page size 1000, truncation) which supplements the safety profile from annotations.

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 main description is two tightly written sentences that immediately state the purpose, the content of results, and a key limitation. No unnecessary words, and the important behavioral note about the missing download link is included without clutter.

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?

There is no output schema, so the description must explain what is returned—it does so by stating that each result names the file and its attached records, and that no download link is included. Combined with the detailed schema for the criteria parameter (filters, sorting, pagination), an agent has enough context to call the tool correctly, though it stops short of fully describing the result structure beyond that.

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

Parameters3/5

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

Schema description coverage is 100% and the criteria parameter has a rich description covering formats, operators, limitations, and pagination. The main tool description does not add any parameter-specific semantics beyond what the schema already provides, so the baseline of 3 is appropriate.

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 uses a specific verb ('search') and a clear resource ('attachment records (files and notes pinned to QuickBooks records)'). It states exactly what the tool does and what results contain, and explicitly notes that results lack a TempDownloadUri link, distinguishing it from other attachment tools like get_attachable.

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

Usage Guidelines3/5

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

The description implies usage for searching attachment records but does not explicitly name alternatives or state when not to use it. The mention that results lack a download link hints that this tool is not for downloading, but it doesn't direct the agent to get_attachable or other tools. Guidance is present but only implied.

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