Skip to main content
Glama
Australian Accounting MCP

Australian Accounting MCP

Review GST coding of bank lines

review_gst_coding
Read-onlyIdempotent

Reviews GST coding on bank lines, assigns a review state with reasons, and flags registration or inter-entity mismatches for local accounting checks.

Instructions

Give each bank line one review state, with a reason, from gst-review.

States, checked in order: unknown_gst_code, gst_differs_from_registration (GST charged or claimed outside the entity's registration, or claimed from a supplier recorded as not registered), between_entities (an opposite amount in another entity within the window), coded, suggested, nothing_suggested. Amounts are AUD decimal strings, negative for money out; dates are YYYY-MM-DD. Registration dates are the operator's facts: a null registered_from means not registered, so never send it for an unknown date. Does not decide whether an entity had to register, how a supply is classified, what a transfer is or whether a suggestion is right. Retain not_decided and warnings. Local review aid, not advice; no network, writes or lodgements.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "lines": "<lines>",
      "registrations": "<registrations>"
    },
    "name": "review_gst_coding"
  }
}

Input Schema

NameRequiredDescriptionDefault
linesYesCoded bank lines, up to 1000. Every entity needs a registrations entry.
gst_codesNoCode table mapping each GST code to its treatment; omit for the engine's common Xero and MYOB AU codes.
registrationsYesOne entry per entity: its established GST registration dates.
match_window_daysNoDays either side to pair opposite amounts between entities.

Output Schema

NameRequiredDescriptionDefault
okYesThe review ran; this does not mean compliance or a known verdict.
linesYes
countsYesLines per state, every state listed.
engineYesDelegated distribution that produced this result.
reviewYes
sourcesYes
warningsYesRetain when presenting the result.
disclaimerYes
facts_usedYesRegistrations, window and codes.
not_decidedYesRetain when presenting the result.
engine_versionYesInstalled version of that engine.
source_checkedYesDate in YYYY-MM-DD form.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.23

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, and the description reinforces this with 'no network, writes or lodgements'. It adds genuinely non-obvious behavior: registration dates are operator facts, a null registered_from means not registered and must never be sent for an unknown date, and not_decided plus warnings must be retained. It does not describe output shape, but an output schema exists.

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?

Front-loaded with the core action and the state list, then caveats, then scope limits. Dense but every clause carries information; the amount/date format sentences are the only near-redundant material against the schema.

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 annotations, a full output schema and 100% parameter coverage, the description supplies what structured fields cannot: state ordering, the null-registration rule, and the boundary of what the tool will not decide. Only the optional gst_codes table and match_window_days behavior are left entirely to the schema, which is acceptable.

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 the schema already documents lines, registrations, gst_codes and match_window_days. The description's notes on AUD decimal strings, negative-for-money-out, YYYY-MM-DD dates and null registration semantics largely restate what the schema already says, adding little beyond the baseline.

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: assign one review state, with a reason, to each bank line. It then enumerates the exact state vocabulary in check order, which lets an agent distinguish this from siblings like reconcile_bas or review_div7a_loan without opening a schema.

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?

Gives clear operating context (per-line review states, ordered evaluation) and explicit scope exclusions: it does not decide registration obligations, supply classification, transfer treatment, or suggestion correctness. It does not name an alternative tool to use for those adjacent questions, so it stops short of full when/when-not/alternative routing.

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