Documentation
record_pending_expenses
record_pending_expenses MCP tool reference, parameters, return type, and safety hints.
What it does
Records pending expenses in the local Clovis ledger.
(account_id: string, transactions: Array<Record<string, unknown>>, counterpart_id?: string | null, asset_id?: string | null, batch_label?: string | null, tags?: Record<string, unknown> | null, dry_run?: boolean, skip_dedup?: boolean) => Record<string, unknown>Can write, but supports dry-run. Ask the agent to preview the result before committing changes.
When to use it
Use this section to decide whether the tool fits the user request before calling it.
Before calling
Agents should gather these facts or confirmations first.
Have exact values for required inputs: account_id, transactions.
Start with dry_run=true, show the preview, then ask before applying the change.
State the intended ledger change in plain language before calling the tool.
Parameters
Required inputs are marked clearly. Optional inputs can usually be omitted unless the workflow needs them.
account_idrequiredLedger account id or resolvable account reference.
transactionsrequiredInput used by this tool.
counterpart_idoptionalIdentifier from the local Clovis ledger.
Default: nullasset_idoptionalAsset or currency id used by the ledger.
Default: nullbatch_labeloptionalHuman label attached to the generated batch.
Default: nulltagsoptionalMetadata tags to attach.
Default: nulldry_runoptionalPreview the result without committing changes.
Default: trueskip_dedupoptionalSkips duplicate detection. Use only when the user has already reviewed the rows.
Default: falseAgent call shape
Use the exact tool name and pass arguments as structured JSON through the MCP client.
record_pending_expenses
Copy this shape into agent instructions, evals, or MCP client tests.
{
"tool": "record_pending_expenses",
"arguments": {
"account_id": "<account_id>",
"transactions": [],
"dry_run": true
}
}