Skip to main content
Glama
Australian Accounting MCP

Australian Accounting MCP

Report bundled data periods and sources

get_data_freshness
Read-onlyIdempotent

Check recorded effective periods, engine version, source URLs and review dates for each bundled ATO dataset. Optionally test a named date against those periods before you rely on the figures.

Instructions

Report what the installed release records about each bundled dataset.

For the ATO benchmarks, Division 7A rates, Payday Super GIC quarters, business-day calendar and SG parameters, each worksheet's rates, the lodgment program, the GST review rules and the reviewed ATO records: the effective periods recorded, the installed engine version, source URLs and retrieval and review dates, with UNKNOWN where the engine records none. With as_at, each dataset says whether that date falls inside a recorded period. currency is always NOT_ESTABLISHED: a cached uvx release can be older than the latest, and official figures can change after a source was checked. Retain the statement. Pass tool to report only the datasets that tool reads. Reads no network and predicts no next change.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_data_freshness"
  }
}

Input Schema

NameRequiredDescriptionDefault
toolNoOptional: report only the datasets this tool reads.
as_atNoOptional YYYY-MM-DD date the user names, tested against each dataset's recorded periods. Do not infer today.

Output Schema

NameRequiredDescriptionDefault
okYesThe report ran.
toolYesThe tool filter supplied, or null.
as_atYesThe as_at supplied, or null.
serverYesInstalled server distribution and version, or UNKNOWN. A cached release can be older than the latest.
currencyYesThis tool never establishes that data is current.
datasetsYes
statementYesLimits to retain when presenting the result.
not_listedYesTools whose data is not bundled.
live_lookupYes
bundled_dataYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.23

TDQS

A3.9/5.0
Behavior4/5

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

Beyond the annotations it discloses genuinely useful behavior: no network access, no prediction of next change, UNKNOWN where the engine records nothing, and a mandatory caveat that currency is always NOT_ESTABLISHED because a cached uvx release can lag the latest figures. That last point is real context the annotations cannot convey. It does not spell out output shape details, but the tool is a pure read with an output schema, so the gap is small.

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 purpose, then a dataset enumeration and a caveat block; each sentence does work. The second sentence's long colon-list of datasets is dense and slightly sprawling, which costs it the top score, but nothing is redundant.

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 provenance tool with a full output schema and both parameters documented, this covers everything an agent needs: what is reported, the UNKNOWN sentinel, the as_at period test, the permanent NOT_ESTABLISHED currency caveat, and the requirement to retain that caveat in downstream answers. No network access and no forecasting are explicitly ruled out.

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 description coverage is 100%, so baseline is 3, and the description earns above that: it explains that 'tool' narrows the report to the datasets that tool actually reads, and that 'as_at' makes each dataset report whether that date falls inside a recorded period. The date-semantics sentence adds a little beyond the schema's 'tested against each dataset's recorded periods,' but not a great deal.

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?

Opens with a specific verb+resource: 'Report what the installed release records about each bundled dataset,' then enumerates the dataset families (ATO benchmarks, Division 7A rates, Payday Super GIC quarters, business-day calendar, SG parameters, etc.). This clearly separates it from sibling tools that return the data itself, though it never names a sibling to contrast with 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?

It implies when to call by saying what the output is for ('Retain the statement,' 'Pass tool to report only the datasets that tool reads') and by scoping results per-tool, which is real usage guidance. But there is no explicit when-to-use/when-not-to-use framing such as 'call this before quoting a rate' or a named alternative, so the agent must infer the trigger.

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