Skip to main content
Glama

Map an account

bridge_map_account
Destructive

Say what something is called in the ledger of record: one of our accounts, or one of the person's own spending categories or statement accounts. The mapping is the accountant's answer, not a guess: ask for the code and the name exactly as their chart spells them, one at a time, and write them as they are given. Xero imports match on the code, QuickBooks on the name, so supply both where you can.

Three kinds. "derivation" is one of our fixed accounts (receivables, revenue, cash, bank fees). "category" is a word the person used when reviewing their spending — groceries, software, rent — and it needs their expense or income account. "source" is the account a statement came from, their bank or card, and it needs that account in the chart. bridge_accounts lists all three and says which are in use. The tax rate label is only needed where their import expects one. Changing a mapping never rewrites a hand-over that already went out. Effects: account mapping written.

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": {
      "account": "<account>"
    },
    "name": "bridge_map_account"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeNoTheir account code, as their chart spells it (Xero AccountCode).
kindNoWhat is being mapped. Defaults to one of our derivation accounts.
nameNoTheir account name, exactly (QuickBooks Account Name).
noteNoAnything the accountant said about it.
reasonNoWhy — part of the record.
accountYesWhich one: an account name for "derivation", the person's word for "category", the statement account label for "source".
tax_rateNoThe tax rate label their import expects on this account, if any.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare this is a destructive, non-idempotent, non-read-only write, so the description is not carrying the safety burden alone — but it still adds genuinely useful context: "Effects: account mapping written" and the non-retroactivity guarantee that remapping never rewrites an already-issued hand-over. What it does not disclose is what happens when a mapping is overwritten (does the prior mapping vanish, is history kept?) or how conflicts are surfaced, which matters for a destructiveHint=true tool.

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?

Roughly 130 words for a seven-parameter destructive write with three distinct modes is proportionate, and the per-kind breakdown is easy to scan. The opening ("Say what something is called in the ledger of record") is an oblique framing rather than a verb-first statement of the action, which weakens front-loading slightly, but no sentence is pure filler.

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 mutation tool with no output schema and full schema coverage, the description covers what it writes, the three modes, sourcing rules for code/name, the conditional tax rate, and the downstream non-effect on issued hand-overs. The remaining gap is failure behavior — what the agent should expect if the supplied code or name does not match the client's chart.

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 earns above that by explaining what the enum values mean and how the `account` parameter is interpreted differently per kind (account name for derivation, the person's own word for category, the statement label for source). It also clarifies that tax_rate is only needed where the import expects a label. The `note` and `reason` parameters get no treatment, but they are self-describing.

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 names a concrete action (write the ledger-of-record mapping for an account) and immediately decomposes it into three named kinds — derivation, category, source — each defined in plain terms. It also distinguishes itself from the sibling that reads the same data ("bridge_accounts lists all three and says which are in use"), so an agent can tell read from write without opening a 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?

It gives real operational guidance: collect code and name exactly as the client's chart spells them, one at a time, and supply both because Xero matches on code while QuickBooks matches on name. It also points to bridge_accounts for discovery. It stops short of explicit when-not-to-use conditions or a stated prerequisite that the account must already exist in the chart.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.