IQ Books by ReconcileIQ

Code everything in the session

run_coding

Run the full pipeline over every account in the session: transfers, invoice matching, this company's own history, shared merchant patterns, category and meaning-based matching, your corrections, and VAT. ★ It does not charge: the credits were taken by add_bank_transactions, so re-running is free. Run it once, after every account is in and after fetch_outstanding_invoices, because invoices can only be matched once they are loaded.

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": "run_coding"
  }
}

Input Schema

Name	Required	Description
`hold_below`	No	Confidence a line needs to post without a person (default 0.8). Below it a line is HELD until recode_transaction settles it. Raise it for unfamiliar books; lower it only when someone reads every line. It cannot go below the platform bar; the answer states the bar used.
`wait_seconds`	No	How long to wait for it to finish. Default 120.
`estimate_only`	No	Returns what the run would cost and does nothing else. Nothing is spent. Use it before the real call so the user hears the price first.
`skip_invoice_matching`	No	Only set this to go ahead deliberately without loading the outstanding invoices first, when you know none of these payments settle a bill.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 30, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false; the description adds value beyond them by explaining the billing model (credits already taken by add_bank_transactions, so re-runs are free) and the consequence of the hold threshold (lines held until recode_transaction settles them). It does not say what a run actually returns or how long the run may take relative to wait_seconds, which limits it to a strong 4.

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?

Two dense sentences, front-loaded with what the pipeline does, then the ordering rule and the cost reassurance. The ★ marker and the emoji-free but slightly ornamental tone cost a little; every clause still carries information.

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?

With no output schema, the description covers cost, ordering, mutation scope and the hold/recode loop, which is most of what an agent needs before calling. It does not describe what a successful run reports back (opens/held counts) or any dependency on start_coding_session, leaving a small gap for a four-parameter non-idempotent run tool.

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 carries detailed semantics for hold_below, wait_seconds, estimate_only and skip_invoice_matching; baseline 3 applies. The description only adds a supporting rationale for skip_invoice_matching ('invoices can only be matched once they are loaded') rather than new syntax or defaults.

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?

Names a specific verb and resource and enumerates exactly what the pipeline covers (transfers, invoice matching, company history, shared merchant patterns, category/meaning matching, corrections, VAT) for the stated scope 'every account in the session'. That scope plus the ordering clause separates it from review_coding, recode_transaction, plan_bookkeeping and commit_plan without needing to name them.

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 an explicit trigger and precondition: 'Run it once, after every account is in and after fetch_outstanding_invoices', with the reason (invoices can only be matched once loaded) and a suggested cheap pre-check via estimate_only. It also states a deliberate exception path through skip_invoice_matching, so both when-to and when-not-to are covered.

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

All IQ Books by ReconcileIQ tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?