Skip to main content
Glama
Sign In
Beeswax Shares MCP Server

Beeswax Shares MCP Server

by steamau
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Answer an auditor's document request

answer_auditor_request

Answer an auditor request by generating a prefilled draft letter or attaching an uploaded document, then supply field answers so trustees can finalise and sign it on the web.

Instructions

Answer an auditor request with a generated letter or an uploaded file: document_type generates (or reuses) the year's draft of an auditor-requested type — trustee_representation_letter, notes_to_financial_statements, related_party_confirmation, trustee_residency_declaration, property_valuation — prefilled, with answers for its fields; or compliance_document_id for one already prepared; or document_id for a file sent with upload_document. A generated letter is a draft: the trustees finalise and sign it on the web.

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>",
      "request_id": "<request_id>"
    },
    "name": "answer_auditor_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNo
answersNoFields for a generated letter
fund_idYesFund ID (discover via whoami or list_funds)
reasoningNoWhy you are making this change — recorded on the audit log entry for this write
request_idYes
document_idNoA fund document from upload_document
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.
document_typeNoAuditor-requested type to generate as the answer
financial_yearYesFinancial year — the label "2023-24" or its numeric id (from list_financial_years)
compliance_document_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only cover the safety profile (readOnlyHint=false, destructiveHint=false). The description adds genuinely non-obvious behavior: a generated letter is a draft that trustees finalise and sign on the web, and document_type 'generates (or reuses) the year's draft', telling the agent the call is idempotent-per-year rather than creating duplicates. It does not disclose what a call returns or what happens when request_id and fund/financial_year mismatch, but the draft/reuse semantics are the material addition.

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?

One long but tightly structured sentence front-loads the tool's action, then walks the three modes in the order an agent would evaluate them, closing with the draft-signing caveat. No filler, no restatement of the tool name, and every clause carries either a route or a behavioral fact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter write tool with a nested answers object and no output schema, the description explains input routing well but never says what comes back (document id? letter body? request status) or whether answers is expected for document_type only. The draft-finalisation note helps, but an agent still cannot predict the result of a successful call.

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?

At 70% schema coverage the baseline is 3, and the description beats it by supplying the valid values for document_type, which the schema leaves as a bare string with no enum. It also clarifies that answers prefill the generated letter's fields and distinguishes document_id (an upload) from compliance_document_id (an already prepared document). It says nothing about note, reasoning, or external_ref beyond what the schema already documents.

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 description states a specific verb and resource (answer an auditor request) and then enumerates the three input modes exactly: document_type for a generated letter, compliance_document_id for a prepared one, document_id for an uploaded file. It even lists the concrete auditor-requested types (trustee_representation_letter, related_party_confirmation, etc.), so an agent knows precisely what this tool produces.

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 'X, or Y, or Z' construction gives clear internal routing between the three answer modes and implies they are alternatives, which is exactly the decision an agent must make. It stops short of naming external alternatives (e.g. answer_audit_query, record_auditor_request) or stating when an auditor request should be answered by letter versus by upload, so no explicit exclusions are present.

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