MIDAS CIVIL NX tools (MIDAS IT Europe)

Undo a civil_write_tables run

civil_write_tables_undo

Destructive

Puts every row a civil_write_tables run touched back as it was before the run: deletes rows it created, restores rows it changed or deleted (a merging table's row is replaced whole). Works on a run that stopped part-way too. Warns where a row changed after the run. What CIVIL NX deleted along with a row (elements on a deleted node, loads on a deleted element) is not part of the run and does not come back. Default: the latest run not yet undone. Previews unless apply: true.

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": "civil_write_tables_undo"
  }
}

Input Schema

Name	Required	Description	Default
`apply`	No
`runId`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 28, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Far exceeds the annotations: it details exactly what gets destroyed and recreated, that a merging table's row is replaced whole, that post-run edits trigger a warning, and that CIVIL NX cascading deletions (elements on deleted nodes, loads on deleted elements) are not restored. These are non-obvious side effects an agent cannot infer from destructiveHint alone.

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?

Five tight sentences, front-loaded with the core effect, followed by scope caveats and then the apply/runId defaults. Every sentence is load-bearing and no restatement of the name occurs.

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?

For a destructive mutation tool with no output schema and undescribed params, the description supplies what an agent needs: reversibility semantics, partial-run handling, post-run edit warnings, unrecoverable cascades, and safe-preview default. Nothing material is missing.

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 description coverage is 0%, so the description carries the burden. It defines apply's behavior (previews unless true) and explains runId's default (latest run not yet undone), which is the most important semantic. It adds no format detail for runId itself, but the operational meaning of both params is covered.

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 (undo) plus the exact resource (a civil_write_tables run) and immediately enumerates the concrete effects: deleting created rows and restoring changed or deleted ones. This is unambiguous against siblings like civil_write_tables or civil_read_table.

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?

Clearly explains when this applies (any run, including one that stopped part-way) and the critical default that it previews unless apply: true. It doesn't name alternatives or explicitly say when not to use it, but the preview/apply distinction gives the agent enough to decide safely.

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

All MIDAS CIVIL NX tools (MIDAS IT Europe) 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?