Skip to main content
Glama
Australian Accounting MCP

Australian Accounting MCP

Get ATO lodgment program due dates

get_lodgment_due_dates
Read-onlyIdempotent

List ATO lodgement, payment and concession due dates for BAS, IAS and income tax returns, including holiday-adjusted timing and DETERMINED or UNKNOWN status.

Instructions

List lodgement, payment and concession due dates from lodgment-calendar.

Covers the ATO 2026-27 lodgment program: monthly and quarterly BAS and IAS for 2026-27 periods, and 2025-26 income tax returns for individuals, trusts, partnerships, companies (including consolidated head companies) and SMSFs, lodged by the taxpayer or a registered tax or BAS agent. Each row gives status DETERMINED or UNKNOWN, due_date after the next-business-day roll under the ATO's public holiday table, nominal_due_date, rule_id, summary, source_url, source_provision, source_checked and missing. A payment row appears only where payment is not due with the lodgement. UNKNOWN names each fact not supplied or question the ATO pages leave open; report it as UNKNOWN. Dates after 30 June 2027 stay UNKNOWN unless holidays_complete_until covers them. Retain not_decided and warnings. Not advice; lodges nothing and reads no network.

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": {
      "obligation": "<obligation>",
      "entity_type": "<entity_type>",
      "financial_year": "<financial_year>",
      "channel": "<channel>"
    },
    "name": "get_lodgment_due_dates"
  }
}

Input Schema

NameRequiredDescriptionDefault
factsNoProgram conditions as established; omit any that is not.
channelYesWho lodges. A BAS agent cannot lodge an income tax return.
obligationYesActivity statement (BAS or IAS) or income tax return.
entity_typeYesThe entity that lodges.
extra_holidaysNoPublic holidays for the whole of a state or territory that the ATO table (1 July 2026 to 30 June 2027) does not list, from an official source. Omit unless established.
financial_yearYesYYYY-YY: the year of the statement periods (2026-27 recorded), or the income year a return covers (2025-26 recorded). Other years return UNKNOWN.
reporting_cycleNoRequired for bas and ias; omit for income_tax_return. A monthly bas reports GST monthly; other monthly activity statements are ias. A quarterly instalment reported on a monthly BAS is monthly. For a consolidated head company, a quarterly ias is its PAYG instalment activity statement.
holidays_complete_untilNoYYYY-MM-DD: only when the ATO table plus extra_holidays hold every such holiday to this date. Settles dates after 30 June 2027; never guess it.

Output Schema

NameRequiredDescriptionDefault
okYesThe review ran; this does not mean compliance or a known verdict.
countsYesRows per status.
engineYesDelegated distribution that produced this result.
requestYesObligation, entity, year, channel.
calendarYes
warningsYesRetain when presenting the result.
disclaimerYes
facts_usedYesEach fact; null is not supplied.
not_decidedYesRetain when presenting the result.
obligationsYes
program_yearYesIncome or dataset year in YYYY-YY form.
engine_versionYesInstalled version of that engine.
source_checkedYesDate in YYYY-MM-DD form.
holiday_calendarYesHoliday rule, ATO table source and coverage.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.23

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered; the description adds genuinely new behavior: every fact not supplied surfaces as UNKNOWN rather than being guessed, payment rows appear only where payment is not due with the lodgement, and dates past 30 June 2027 stay UNKNOWN unless holidays_complete_until covers them. The one cost is the sentence enumerating output fields (due_date, nominal_due_date, rule_id, summary, source_url, source_provision, source_checked, missing), which restates what the output schema already carries rather than adding behavioral insight.

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

Conciseness3/5

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

The purpose and scope are front-loaded, which is good, but the description then spends a full sentence listing output column names that duplicate the output schema, and the closing 'Retain not_decided and warnings' assumes fields the reader has not been shown. It is dense rather than bloated, yet at least one sentence fails to earn its place.

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?

For an 8-parameter, enum-heavy tool with a full output schema and complete annotation coverage, the description supplies the essential contract: what is in scope, that unsupplied facts degrade to UNKNOWN, the 30 June 2027 horizon, and that the tool neither advises nor touches the network. It does not need to explain return values because an output schema exists, so the remaining gaps (no guidance on when a caller should prefer this over computing dates elsewhere) are minor.

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 coverage is 100%, so the baseline is 3 and the description must earn more. It does add one important semantic beyond the schema: omitting a fact is not neutral, it produces UNKNOWN ('UNKNOWN names each fact not supplied or question the ATO pages leave open'), which changes how the agent should populate the large facts object. Beyond that it does not elaborate on channel/entity_type/reporting_cycle interactions that the schema itself already spells out, so the added value is real but limited to a single rule.

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 opening sentence names a specific verb and resource (list lodgement, payment and concession due dates from lodgment-calendar) and the following sentences bound the scope precisely to the ATO 2026-27 program, BAS/IAS periods and 2025-26 income tax returns across the five entity types. No sibling tool covers due-date lookup, and the scope statement is detailed enough that an agent cannot confuse it with the benchmark, ruling, or calculation tools.

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?

Usage is only implied: the agent must infer from 'Covers the ATO 2026-27 lodgment program' and the required inputs that this is the tool for looking up a due date once obligation, entity, year and channel are known. There is no explicit when-to-use, when-not-to-use, or routing to an alternative (for example, what to do when the obligation falls outside the covered years). The closing 'Not advice; lodges nothing and reads no network' is behavioral framing, not usage guidance.

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