Skip to main content
Glama
Beeswax Shares MCP Server

Beeswax Shares MCP Server

by steamau

Record a balance-sheet item

record_balance_item

Records balance-sheet line items the ledger cannot derive at financial year end, such as loans, receivables, ATO/GST accounts or bonds. Rejected if the year is closed or lodged.

Instructions

Record a balance-sheet line the ledger can't derive, as at a financial year's end — a receivable, an LRBA/loan balance still owed, an ATO account, GST, a creditor or a rent bond. Amounts are POSITIVE magnitudes on the stated side (a $118,991.97 loan owed is side "liability", kind "borrowings", amount 118991.97). Use kind "borrowings" ONLY for money borrowed (it lands at ATO item 16 V); every other liability is kind "other" (16 Y). Rejected if the financial year is already closed or lodged.

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": {
      "fund_id": "<fund_id>",
      "financial_year": "<financial_year>",
      "side": "<side>",
      "label": "<label>",
      "amount": "<amount>"
    },
    "name": "record_balance_item"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoLiability box: "borrowings" (16 V) or "other" (16 Y, the default)
sideYesBalance-sheet side
labelYesLine description, e.g. "NAB LRBA loan 19-412-5863"
amountYesAmount in AUD as a positive magnitude on the stated side
fund_idYesFund ID (discover via whoami or list_funds)
positionNoDisplay order within the side
reasoningNoWhy you are making this change — recorded on the audit log entry for this write
external_refNoYour stable ID for this write (e.g. a statement line or document reference). Repeating a call with the same external_ref replays the first result instead of writing twice.
financial_yearYesFinancial year — the label "2023-24" or its numeric id (from list_financial_years)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.8.1

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds real behavioral context beyond that — the write precondition that it is rejected if the financial year is already closed or lodged, and the downstream consequence that values land in specific ATO return boxes (16 V vs 16 Y). It does not say what is returned or whether the created line is subsequently editable.

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?

Three sentences, front-loaded with what the tool records and followed by the two rules that most often cause errors (sign convention and kind selection). Some of the kind/side wording duplicates schema descriptions, but the repetition is scoped to the highest-risk decision and stays under a few lines.

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 a 9-parameter mutation with no output schema, the definition covers purpose, sign convention, the enum decision rule, and rejection conditions, which is enough to invoke it correctly. It is slightly thin on what a successful call produces and how to correct a line afterwards, given siblings like update_balance_item and delete_balance_item exist.

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 genuine meaning beyond the schema: the positive-magnitude convention is illustrated with a worked example ("a $118,991.97 loan owed is side 'liability', kind 'borrowings', amount 118991.97") and the borrowings-vs-other rule is stated as an exclusion rather than a mere enum listing.

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 ("Record a balance-sheet line") and immediately scopes it to items "the ledger can't derive" at financial year end, with concrete examples (receivable, LRBA/loan, ATO account, GST, creditor, rent bond). This distinguishes it from derived-position siblings like record_statement_balance or create_bank_account without ambiguity.

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 strong conditional guidance: line only for items the ledger cannot derive, at a financial year's end, and "Use kind 'borrowings' ONLY for money borrowed... every other liability is kind 'other'". It also states the operation is rejected when the year is closed or lodged. It does not explicitly name sibling alternatives such as update_balance_item for correcting an existing line, which keeps it short of a 5.

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

Deploy Server

Other Tools