MIDAS CIVIL NX tools (MIDAS IT Europe)

Remove loads, supports or load cases

civil_remove_loads

Destructive

Takes loads out of the model without touching other load cases: CIVIL NX keeps every case's beam loads, nodal loads, pressures and temperatures of an element or node in ONE row, so a plain delete would take the other cases with it — this tool rewrites each row with the items that stay. loads [{ case, on | at (optional selection; default everywhere), kinds (optional: nodal, udl, pressure, temperature, gradient, selfWeight) }] removes that case's loads; deleteCases [names] removes the cases' loads and then the load cases themselves; supports { at }, springs { at }, releases { on } remove those at the selected nodes / elements. Selections as in civil_loads_supports. Previews what goes (counts per kind, rows touched, combinations that would lose a case); apply: true with confirmPlanHash. civil_write_tables_undo puts everything back, load cases included.

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_remove_loads"
  }
}

Input Schema

Name	Required	Description
`apply`	No
`loads`	No
`units`	No	Length unit of selection coordinates.
`springs`	No
`releases`	No
`supports`	No
`deleteCases`	No	Load cases to delete, with all their loads.
`confirmPlanHash`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 29, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already flag destructive/not-idempotent, but the description adds genuinely non-obvious mechanics: that each row contains all cases' loads so a plain delete would destroy sibling cases, that the tool rewrites rows keeping survivors, and that the preview reports counts per kind, rows touched, and combinations that would lose a case. It also discloses that undo restores the load cases themselves.

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?

The critical rationale (why a plain delete is unsafe) is front-loaded before the parameter shapes, and the preview/apply contract closes it out. It is a single densely packed block with em-dash clauses, however, so the mode-per-target mapping is harder to scan than a structured list would be.

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?

For an 8-parameter destructive tool with nested selection objects and no output schema, the description covers the destructive semantics, the preview/confirm gate, and reversal. It omits whether at least one of loads/deleteCases/supports is required, and does not describe what the final applied response contains.

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?

With only 25% schema coverage, the description carries the load: it explains the per-target shapes (loads with case/on|at/kinds, deleteCases with names, supports/springs at, releases on) and the 'default everywhere' behaviour of the selection object. Gaps remain — units, apply defaulting to false, and the fact that confirmPlanHash comes from the preview are only implied.

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 names the exact resources removed (loads, load cases, supports, springs, releases) and the scope constraint (only the targeted case's rows are rewritten, other cases preserved). It explicitly distinguishes itself from a naive delete by explaining the CIVIL NX one-row-per-element storage model, which no sibling name alone would reveal.

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 states the dry-run/apply workflow ('Previews what goes...; apply: true with confirmPlanHash') and points to civil_write_tables_undo for reversal, plus 'Selections as in civil_loads_supports' for selection semantics. It stops short of saying which shape (loads vs deleteCases vs supports) to choose when an agent wants a given outcome, and gives no explicit when-not guidance.

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?