upbank-mcp

by uiux-me

Overview Schema Source Related Servers Discussions Admin

Python

Remote

List Transactions

list_transactions

Retrieve Up Bank transactions newest first, with optional filters for account, status, date range, category, or tag.

Instructions

List transactions, newest first, optionally filtered by account, status, date range, category or tag.

Input Schema

TableJSON Schema

Name	Required	Description
`tag`	No	Tag id (its label), e.g. `Holiday`.
`since`	No	Inclusive lower bound on createdAt. Accepts YYYY-MM-DD or a full RFC-3339 timestamp; bare dates are read as Australia/Sydney time.
`until`	No	Inclusive upper bound on createdAt, same formats as since.
`cursor`	No	A `next_cursor` or `prev_cursor` from a previous call to this tool. When set, all other arguments are ignored.
`status`	No	Only transactions with this status.
`category`	No	Category id slug, e.g. `restaurants-and-cafes`. Parent ids match their children.
`page_size`	No	Number of records per page (1-100).
`account_id`	No	Restrict to one account. Omit to search across all accounts.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 11, 2026

TDQS

A3.6/5.0

Behavior3/5

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

With no annotations, the description must carry the behavioral load, and it does disclose one real trait beyond the schema: results come back newest first. It does not mention pagination behavior, default page size, or that filters combine, so the disclosure is partial.

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?

A single front-loaded sentence with zero filler; the verb, ordering and filter dimensions all arrive before any clause ends. Nothing could be trimmed without losing information.

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?

An output schema exists, so return values need no prose, and all 8 optional parameters are covered by the schema. The only minor gap is that pagination/aggregate behavior isn't mentioned in the description, though the cursor parameter documents it.

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%, so date formats, cursor semantics, enum values and page-size bounds are already fully documented. The description's filter list (account, status, date range, category, tag) adds no meaning beyond what the schema provides, so the baseline 3 applies.

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

Purpose4/5

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

States a specific verb and resource plus ordering ('List transactions, newest first') and enumerates the filterable dimensions. An agent can distinguish it from get_transaction by the plural scope, though no sibling is named explicitly.

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 word 'optionally' implies this is the browse-all entry point and filters are narrowing, which gives implied usage. There is no explicit when-to-use versus get_transaction or the tagging/categorizing siblings, and no stated exclusions.

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