Skip to main content
Glama
Australian Accounting MCP

Australian Accounting MCP

Look up a reviewed ATO rate for a date

get_reviewed_rate
Read-onlyIdempotent

Returns one reviewed ATO rate or threshold for a specific date, plus its source URL and verbatim quote, and refuses out-of-range dates so you never rely on a nearby year.

Instructions

Return one reviewed ATO rate or threshold for a date, with its source and quote.

Reads a bundled copy of reviewed records, each holding the figure, its unit and period, the ATO page, when that page was captured and a verbatim quote containing the figure, with no folder to configure. The records cover 2025-26 and 2026-27 only. status is FOUND only when as_at falls in those years and in the named record's own period. Otherwise status is REFUSED, the reason says so and no figure is returned: a date outside those years, even for an open-ended record; a date outside the record's period, with covering_ids naming any record of the same figure that holds that date; a record with no recorded period; or an unknown id. Never answer a refusal with a nearby year. An open-ended record stays FOUND for a date after it was last read, with after_last_read true and after_last_read_note saying that it was last read on that date and does not show the figure still applied on as_at. A record is a point-in-time copy, not a live lookup, and takes no account of an entity's facts: retain source_url, quote, notes and the statement, and confirm the figure at the source. Use search_tax_rates for a configured legislation corpus and the reviewed engines for a calculation. 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": {
      "record_id": "<record_id>",
      "as_at": "<as_at>"
    },
    "name": "get_reviewed_rate"
  }
}

Input Schema

NameRequiredDescriptionDefault
as_atYesThe YYYY-MM-DD date the figure is needed for. Do not infer today.
record_idYesRecord id, such as 'concessional-cap-2026-27' or 'gst-registration-threshold'. An unknown id is refused with every id in known_ids.

Output Schema

NameRequiredDescriptionDefault
okYesThe lookup ran; see status for its outcome.
as_atYesDate in YYYY-MM-DD form.
reasonYesThe refusal in words; null when FOUND.
recordYesThe record when FOUND, otherwise null.
statusYesREFUSED carries no figure; never fill the gap with a nearby year.
refusalYesWhy no figure came back, or null when FOUND.
currencyYesA record never establishes that a figure is current.
known_idsYesEvery record id; supplied for an unknown id only.
record_idYes
statementYesLimits to retain when presenting the result.
covering_idsYesRecords of the same figure that do cover as_at, if any.
covered_yearsYesThe income years the bundled records cover.
record_periodYesThe period the named record holds; null when FOUND or unknown.
after_last_readYesTrue when an open-ended record is asked about a date after it was last read, so it does not show the figure still applied.
after_last_read_noteYesThat limit in words; retain it. Null when after_last_read is false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.23

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only cover safety/idempotency, and the description adds substantial behavior beyond that: coverage limited to 2025-26 and 2026-27, FOUND vs REFUSED status semantics, the enumerated refusal causes, the after_last_read flag and its note, and that no network is read. The gap is that it does not summarize the returned payload's shape or how large a quote/source block may be, though an output schema exists to cover most of that.

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 alternative routing are front-loaded, but the middle is a long run-on enumerating five refusal cases plus an after_last_read caveat, and it repeats the point-in-time warning. The content is valuable but would be far more scannable as a short list rather than dense prose.

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 two-parameter lookup with an output schema, the description covers everything an agent needs: date-window limits, refusal conditions, the after_last_read edge case, the point-in-time caveat, and the instruction to retain source_url, quote, notes and the statement. Nothing material is left to inference.

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; the description nonetheless adds meaning by tying as_at to the record's own period and the 2025-27 coverage window, and by explaining that an unknown record_id yields a refusal listing known_ids. It stops short of explaining what covering_ids in a refusal means operationally for a follow-up call.

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?

Opens with a specific verb and resource: "Return one reviewed ATO rate or threshold for a date, with its source and quote." It also names what it is not (legislation corpus via search_tax_rates, calculations via the reviewed engines), so an agent can separate it from siblings without inspecting schemas.

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

Usage Guidelines5/5

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

Explicitly routes alternatives: "Use search_tax_rates for a configured legislation corpus and the reviewed engines for a calculation." It also states a usage prohibition ("Never answer a refusal with a nearby year") and warns it is a point-in-time copy rather than a live lookup, which tells the agent when this tool's answer is insufficient.

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