Skip to main content
Glama
Australian Accounting MCP

Australian Accounting MCP

Reconcile lodged BAS figures with the ledger

reconcile_bas
Read-onlyIdempotent

Compare lodged BAS labels G1, G2, G3, G10, G11, 1A and 1B with ledger lines by period to flag matches, differences, unreported labels, and negative totals on a cash or accruals basis.

Instructions

Compare lodged G1, G2, G3, G10, G11, 1A and 1B with the ledger, per period.

gst-review attributes each line to a period by payment date on the cash basis, or the earlier of invoice and payment on accruals (GST Act ss 29-5 and 29-10), rounds ledger totals down to whole dollars and gives each label a status: matches, differs (with the difference and its lines), not_reported or negative_ledger. Lodged figures are whole non-negative dollars. Amounts are AUD decimal strings; gross includes GST and both are negative for a credit note. A line in a period that it cannot place on a label refuses the call; kept_out lists excluded lines and timing lists lines invoiced in a period but attributed elsewhere. Does not decide whether a difference needs a revised BAS, whether a code is right or which basis applies. Retain not_decided and warnings. Local review aid, not advice or a BAS.

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>",
      "periods": "<periods>",
      "basis": "<basis>"
    },
    "name": "reconcile_bas"
  }
}

Input Schema

NameRequiredDescriptionDefault
basisYesThe GST accounting basis the operator established for the entity.
linesYesLedger sale and purchase lines, up to 2000, with GST codes and dates.
periodsYesNon-overlapping tax periods, each with its lodged figures if lodged.
bas_codesNoCode table mapping each GST code to its BAS category; omit for the engine's common Xero and MYOB AU codes.
g1_includes_gstNoWhether the lodged G labels include GST, as chosen at G1.

Output Schema

NameRequiredDescriptionDefault
okYesThe review ran; this does not mean compliance or a known verdict.
basisYes
engineYesDelegated distribution that produced this result.
reviewYes
unpaidYesSupplied line ids, in input order.
periodsYes
sourcesYes
warningsYesRetain when presenting the result.
disclaimerYes
facts_usedYesBasis, G1 choice, codes, rounding.
not_lodgedYesPeriods with lines but no figures.
not_decidedYesRetain when presenting the result.
engine_versionYesInstalled version of that engine.
source_checkedYesDate in YYYY-MM-DD form.
no_ledger_linesYesLodged periods with no lines.
outside_periodsYesSupplied line ids, in input order.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.23

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the readOnly/idempotent annotations: it discloses the period-attribution rules for cash vs accruals with legislative references, that ledger totals are rounded down, the four possible label statuses, that unplaceable lines refuse the call, and that kept_out/timing/not_decided/warnings must be retained. This is exactly the call-shaping detail annotations cannot carry.

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 comparison and dense but largely load-bearing throughout; every clause covers behavior (basis rules, statuses, refusal, retained fields). Minor cost: it is a single packed block with awkward mid-sentence line breaks that make it harder to scan than a short bulleted status list would be.

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

Completeness5/5

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

For a read-only reconciliation with five parameters, an output schema, and non-trivial accounting rules, the definition covers the preconditions (lodged vs not lodged periods), the outcome vocabulary, and the failure mode. An agent has enough to decide whether to call it and how to interpret a refusal.

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 real semantic weight: what 'basis' means operationally (payment date vs earlier of invoice and payment), that amounts are AUD decimal strings and negative on credit notes, and that gst_code values are resolved through bas_codes or a default table. That is meaning beyond the field descriptions.

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 — 'Compare lodged G1, G2, G3, G10, G11, 1A and 1B with the ledger, per period' — and names the exact labels reconciled. An agent can distinguish this from sibling tools like review_gst_coding, which judges code correctness rather than comparing lodged figures to ledger totals.

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 scope ('per period') and explicit exclusions: it does not decide whether a difference needs a revised BAS, whether a code is right, or which basis applies — which routes code-checking work elsewhere. It stops short of naming the alternative tool, so the agent must infer the destination from the sibling list.

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