Beeswax Shares MCP Server

Update document

update_document

Instructions

Retitle, recategorise or relink a document — e.g. turn a liquidator's report that was uploaded as a statement into a supporting "correspondence" document linked to its financial years, the property holding and the notes_to_financial_statements compliance document. Only the fields you pass change; pass null (or [] for financial_years) to clear a link. A statement that already has extracted lines can't become supporting. Changes the document only — never the ledger. Audit-logged.

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>",
      "document_id": "<document_id>"
    },
    "name": "update_document"
  }
}

Input Schema

Name	Required	Description
`kind`	No	New kind (must fit the category; see upload_document)
`note`	No	Free-text note: what it is and why it matters (null clears)
`title`	No	New title
`fund_id`	Yes	Fund ID (discover via whoami or list_funds)
`category`	No	"statement" (extracted into lines and reconciled) or "supporting" (stored as evidence only — never extracted, no lines, never pending work). Default inferred from kind: supporting-only kinds (trust_deed, lease, valuation, correspondence, ato_notice, audit, legal, insurance, minutes, trustee_consent, actuarial_certificate, related_party_agreement) are supporting; "other" stays a statement unless you say so.
`check_key`	No	Return check it is evidence for, e.g. "large_transactions" (get_return_checks; null clears)
`permanent`	No	Not tied to a year: shows in every year's evidence index (trust deed, lease). Defaults true for trust_deed, lease, related_party_agreement and trustee_consent with no years.
`reasoning`	No	Why you are making this change — recorded on the audit log entry for this write
`holding_id`	No	Holding it relates to, e.g. the property (null clears)
`period_end`	No	Statement period end as an ISO date, e.g. "2026-05-30"
`document_id`	Yes	Document ID (from list_documents)
`counterparty`	No	Other party, e.g. "Slightly Orangey Colour Pty Ltd" (null clears)
`external_ref`	No	Your 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.
`period_start`	No	Statement period start as an ISO date, e.g. "2026-05-30"
`document_date`	No	Date on the document itself (letter, report, deed date) as an ISO date, e.g. "2026-05-30"
`balance_item_id`	No	Balance item it supports (list_balance_items; null clears)
`financial_years`	No	Financial years it is evidence for, as labels e.g. ["2024-25","2025-26"]. [] clears.
`compliance_document_type`	No	Compliance document it supports, e.g. "notes_to_financial_statements", "investment_strategy" (null clears)

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.14.0Nov 9, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is largely covered and the bar for credit is higher. The description does add real context: partial-update semantics ("only the fields you pass change"), the null/[] clearing convention, a business-rule constraint on statements with extracted lines, scope limited to the document, and audit logging. It stops short of saying whether the call is reversible or what it returns.

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

Conciseness5/5

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

The verb list and scope lead, followed by the illustrative example, then the update/clearing semantics, the constraint, and finally the ledger-scope and audit note. It is dense but every clause carries distinct information, and no sentence restates the title or the schema.

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 18-parameter mutation with no output schema, the description covers partial-update behavior, clearing, a key failure mode, mutation scope, and audit logging — enough for correct invocation. The one gap is that, absent an output schema, it never indicates what the call returns or confirms whether an update to a non-existent document errors.

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 description coverage is 100%, so the schema already documents each of the 18 parameters, including the per-field "null clears" notes and the category default inference from kind. The description reinforces the global clearing convention and the kind/category coupling but adds little field-level meaning the schema does not already carry, making the baseline 3 appropriate.

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 clause gives three specific verbs (retitle, recategorise, relink) bound to a single resource (a document), then anchors them with a concrete worked example of a reclassification. This is clearly distinguishable from siblings such as upload_document, move_document_to_account, or reconcile_document without opening any schema.

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?

The description supplies a realistic use case and a hard exclusion: a statement with extracted lines cannot become supporting, which tells the agent when this call will fail. It also scopes the tool away from ledger mutations ("never the ledger"), implicitly routing accounting changes to transaction tools, though it never names an explicit alternative sibling for those cases.

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

Deploy Server