IQ Books by ReconcileIQ

See what the coding decided

review_coding

Read-onlyIdempotent

Read back every line in the coding session: the account and VAT code chosen, the confidence and how it was decided, plus the chart recode_transaction accepts. Lines below the confidence bar (80% unless run_coding set hold_below; the answer states it) are held until a person approves or recodes them, so start here after run_coding. A line above the bar has not been checked by anyone: read the list, not the count.

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": "review_coding"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Default 50.
`offset`	No	How many results to skip, to fetch the next page. Default 0.
`search`	No	Match against the description.
`from_job`	No	The job id run_coding returned. Shows only the lines that run touched, which is what you want straight after a run.
`held_only`	No	Only the lines that will not post as they stand. Use this first.
`include_chart`	No	Include the chart of accounts. Default true on the first page.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 30, 2026
- addedInput schema / properties / offset / description
```
Added value: +"How many results to skip, to fetch the next page. Default 0."
```
First observedOct 30, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the read-only annotations, the description discloses meaningful behavioral context: the 80% confidence threshold can be overridden by hold_below in run_coding, held lines do not post, and 'A line above the bar has not been checked by anyone: read the list, not the count.' This gives the agent important nuance about interpreting the results.

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?

The description is three dense sentences with no wasted language, front-loading the return contents and then the held-line behavior. Each sentence contributes useful information for invoking or interpreting the tool.

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?

With no output schema, the description adequately describes the returned fields and the key caveat about held versus unchecked lines. For a six-parameter read-only review tool, it gives enough context to call 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 description coverage is 100%, so all six parameters are already documented in the schema. The description does not add parameter-specific meaning beyond noting that the answer states the confidence bar and that the chart is accepted by recode_transaction, so the baseline 3 is appropriate.

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: 'Read back every line in the coding session', and enumerates the exact fields returned (account, VAT code, confidence, decision rationale, chart). It also distinguishes this review step from run_coding by saying 'start here after run_coding'.

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 clear timing guidance ('start here after run_coding') and explains that lines below the confidence bar are held until a person approves or recodes them. It does not explicitly name recode_transaction as the alternative for fixing held lines, though it references the chart recode_transaction accepts.

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?