Skip to main content
Glama

Get Reconciliation Status

get_reconciliation_status
Read-onlyIdempotent

Reconciliation per bank account: every uploaded statement with its own opening and closing balance as printed, the books' balance at its end date, the difference and whether they agree (month by month), plus the unreconciled transaction count and the newest unreconciled lines. Use it for "does the bank agree?", "what was the closing balance in March?", before quoting any reconciliation difference, when the user asks to check the books against the bank statements, or about reconciliation progress. This tool only reads: to actually reconcile ("reconcile what you can", "match the receipts", "reconcile my bank") call auto_match_receipts, which does the matching. Never say everything is reconciled without a result from this tool, get_attention or auto_match_receipts. Never say you cannot read balances off statements. Each statement row carries period_start, period_end, opening_balance, closing_balance, book_balance_at_end, difference, agrees and document_id. Pass bank_account_id to look at one account. It also lists who changed matched marks in the last 7 days, as the audit log records it (the user on the app pages, another person, Finn, a connected AI app, or not recorded), with times and counts: read that before explaining why a count moved, and never put a change down to something unknown when it is listed. Where a change is listed as not recorded, say the log does not record who made it: never call it automatic and never guess. It also gives the link to download the reconciliation report (PDF or Excel), the report to give an accountant who asks for one.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_reconciliation_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
companyNoWhich company to read, by name or id, when the account has more than one (see list_companies). Leave it out to use the only company, or the default.
bank_account_idNoLimit to one bank account (optional).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: a 7-day audit trail of who changed matched marks, the rule that 'not recorded' must be reported as unknown rather than guessed, and a downloadable PDF/Excel report link. However, it does not cover pagination or limits on the unreconciled line list, which matters for a read tool returning variable-length data.

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

Conciseness3/5

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

The core purpose and return fields are front-loaded, which is good, but the description runs long and mixes output documentation, usage triggers, guardrail imperatives ("Never say...", "never call it automatic") and report-download info into one dense block. Several sentences could be tightened without losing meaning.

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

Completeness5/5

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

There is no output schema, so the description carries the full burden of explaining return values, and it does so field by field (period_start, period_end, opening_balance, closing_balance, book_balance_at_end, difference, agrees, document_id) plus the audit-log and report-link extras. An agent has enough to call it and interpret the result correctly.

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 coverage is 100%, so both parameters are already documented, including the company fallback behavior. The description only restates the bank_account_id filter ("Pass bank_account_id to look at one account") and says nothing about the company parameter, so it adds little beyond the schema. Baseline 3 applies.

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 (reconciliation status per bank account) and enumerates exactly what is returned: per-statement opening/closing balances, book balance at end date, difference, agrees flag, unreconciled counts and newest lines. It also explicitly distinguishes itself from auto_match_receipts, which does the matching rather than the reading.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete trigger questions ("does the bank agree?", "what was the closing balance in March?") and an explicit when-not: to actually reconcile, call auto_match_receipts instead. It also names get_attention as a companion for the "everything reconciled" claim, so the agent knows the routing.

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.