Skip to main content
Glama
businessapi-mcp

businessapi-mcp

by JoeFu

Lodge Abn Registration

lodge_abn_registration
Idempotent

Validates and lodges Australian Business Number (ABN) applications with the ATO, starting as a dry run by default. Submit entity details, get field errors or a request ID to track.

Instructions

Apply for an Australian Business Number (ATO ABNREG). LIVE cost ≈ $25.

request mirrors https://businessapi.com.au/developers/api/abn-registrations; read bapi://docs/abn-registrations (entity types, workflow, rules) and bapi://docs/ato-codes first. Sole trader = entityType 117 / entitySubType 006; company = 051/027 (needs the ACN); partnership = 161/087|150; trust = 212/…; SMSF = 210/196. The entitlement questionnaire answers come from get_abn_entitlement_questionnaire(entity_type, entity_sub_type); activity codes from search_business_industries(keyword). TFNs are sensitive: collect them, validate (checksum is checked locally), never repeat them back to the user.

dry_run=true (default): validate and return the payload (the server adds testTransmissionIndicator from its env). dry_run=false: lodge -> {requestId, status: "received", billing: {price_cents, charged_cents}}; a duplicate in-progress application returns the existing requestId with a warning. Then wait_for_request(requestId) -> 'finished' gives info.abn. HTTP 400 = field errors keyed by path, nothing charged.

request is a JSON object. Fetch its exact schema first with get_request_schema("abn_registration") (or read resource bapi://schemas/abn_registration), build the object, then call this tool; field errors come back as a readable list.

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": {
      "request": "<request>"
    },
    "name": "lodge_abn_registration"
  }
}

Input Schema

NameRequiredDescriptionDefault
dry_runNo
requestYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations it discloses live cost (~$25), that the server injects testTransmissionIndicator from its environment, that duplicate in-progress applications return the existing requestId with a warning, that HTTP 400 causes no charge, and that TFNs must never be echoed back. These are operational facts not recoverable from readOnlyHint/openWorldHint/idempotentHint.

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 purpose, cost, and the schema-fetch prerequisite, then the dry_run/lodge flow. Dense and largely waste-free, though the entity-code shorthand ('trust = 212/…', 'SMSF = 210/196') is compressed to the point of being cryptic and the paragraph runs long.

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 high-stakes, cost-incurring, deeply nested payload tool, the description covers prerequisites, cost, dry-run semantics, the asynchronous wait_for_request follow-up, error shape (400 field errors by path), and sensitive-data handling. No output schema is needed since the description already names the returned fields (requestId, status, billing).

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?

With 0% schema coverage and a free-form nested `request` object, the description carries the burden well: it explains dry_run defaults and the validate-vs-lodge split, points at the authoritative fields via get_request_schema/bapi://schemas/abn_registration, and enumerates the entityType/entitySubType combinations. It stops short of inlining each request field, deferring to the schema lookup, which is reasonable but leaves a small gap for an agent that skips that step.

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: 'Apply for an Australian Business Number (ATO ABNREG)'. The entity-type table (sole trader 117/006, company 051/027, trust 212/…) makes clear this is the ABN lodgement path specifically, distinguishing it from lodge_company_registration and lodge_business_name_registration.

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?

Names the prerequisites and the sibling tools that feed it: get_abn_entitlement_questionnaire for questionnaire answers, search_business_industries for activity codes, and get_request_schema("abn_registration") before calling. It also states the dry_run-first workflow and the live cost, so an agent knows exactly when and how to invoke it.

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