MIDAS CIVIL NX tools (MIDAS IT Europe)

Write the designed tendons into the model (Tendon Designer)

tendon_write

Destructive

Writes a tendon_design result into the open model with the Tendon Designer plugin's writer: the strand material and tendon property (or one already in the model), every tendon profile (TDNA) and its prestress (TDPL) in the prestress load case, one load group per tendon group, and - when a construction stage is named - each group's load group activated in its stage. With improve, the model's own tendons the design was read from are removed first (only while unchanged since). Refused when the model, the girder, or the loads the forces were read from changed, and while checks fail unless allowFailedChecks. The model is re-checked before writing, the journal is kept before the first change, and every row is read back. 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": "tendon_write"
  }
}

Input Schema

Name	Required	Description	Default
`apply`	No
`stage`	No	Activate every tendon group's load group in this construction stage.
`bonded`	No
`prefix`	No	Tendon name prefix, at most 8 characters (tendons are named <prefix>-C1R1, ...).	TD
`stages`	No	Per tendon group (its key or label from tendon_design design.groups): the construction stage it is stressed in.
`replace`	No	Remove tendons this tool wrote before on these elements with the same prefix (recorded in the ledger and unchanged since).
`designId`	No	The tendon_design result to write (default: the latest).
`loadCase`	No	Prestress load case (default PS, or the model tendons' own).
`transferLength`	No	Transfer length written to each profile (none = full force at the anchor; the design's checks take the full force either way).
`confirmPlanHash`	No
`loadGroupPrefix`	No	Each tendon group's prestress goes in a load group named this prefix plus the group's name (made if missing). Empty string = no load group (Default); stages need one.	TD PS
`strandMaterialId`	No	Strand material already in the model for a new tendon property (default: a new strand material).
`tendonPropertyId`	No	Use this tendon property already in the model (default: the model tendons' own for improve, else a new one from the design). null = a new one.
`allowFailedChecks`	No	Write a design whose checks fail. Only with the user's agreement.
`tendonPropertyName`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 8, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Far exceeds the annotations: it discloses the destructive path (removing the model's own tendons under improve, only if unchanged since read), staleness refusal rules, re-check before writing, journal kept before the first change, and read-back verification. The only ambiguity is 'improve', which appears to be a design-side option rather than an argument this tool accepts.

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?

Purpose is front-loaded and the follow-on clauses are dense with operational facts rather than filler. The single long sentence enumerating what gets written is hard to scan, but nearly every clause carries information an agent needs.

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 15-parameter destructive write tool with no output schema, it covers the essentials: default is a preview, how to commit, safety preconditions, undo path, and post-write verification. What it returns is only lightly characterized ('every row is read back'), but the operational picture is complete.

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?

Adds real meaning for several parameters beyond the 73%-covered schema: apply as the preview/write switch, stage as the construction stage for load-group activation, strandMaterialId/tendonPropertyId as 'use existing vs create new', loadCase as prestress case, and loadGroupPrefix semantics for grouping. transferLength, confirmPlanHash and tendonPropertyName get no description-level help, and 'improve' is not a schema property, so a few gaps remain.

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 ('Writes a tendon_design result into the open model with the Tendon Designer plugin's writer') and then enumerates exactly what is created (TDNA profiles, TDPL prestress, load groups, stage activation), which separates it cleanly from tendon_design and tendon_write_undo.

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?

Gives concrete conditions: preview unless apply:true, allowFailedChecks required to write a failing design, refusal when the model/girder/loads changed, and improve removing the source tendons first only while unchanged. It does not explicitly name tendon_design or tendon_write_undo as the alternative steps, so the routing is implied rather than spelled out.

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?