Skip to main content
Glama

Create connection

create_connection

Creates one steel connection by rule at a steel bar (connection.member) and answers with the effect report; dry_run previews it with its checks, nothing written. One IfcElementAssembly in the storey of the member: an IfcPlate with one hole per bolt, IfcMechanicalFastener bolts and an IfcFastener weld as marked envelopes, joined to member and support by IfcRelConnectsWithRealizingElements. Every size is named; nothing is taken for you. Members are never changed: holes in the support or web are named in connection.holes_not_drilled.try. The bars themselves: create_elements. New revision, effect report. A call that succeeds is not a job that's done.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "connection": "<connection>"
    },
    "name": "create_connection"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoYour note, stored with the new revision
dry_runNoPreview: the planned effect and its checks, nothing written
connectionYesOne IfcElementAssembly: IfcPlate with holes, bolts, weld, joined by IfcRelConnectsWithRealizingElements; spacing checked to EN 1993-1-8 Tab. 3.3
request_idNoYour id for this call: a repeat answers the first result and writes nothing

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false): it enumerates the exact IFC entities produced, that a new revision and effect report result, that members and support geometry are never modified, and that dry_run writes nothing. The line 'A call that succeeds is not a job that's done' further warns that success does not imply the result is verified.

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?

Front-loaded with purpose and behavior, dense but nearly every sentence carries information. A few fragments are cryptic rather than precise, notably 'A call that succeeds is not a job that's done' and 'New revision, effect report', which cost clarity relative to their length.

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 a deep nested tool with no output schema and thin annotations, the description covers what gets created, what is left untouched, and what a dry_run returns. It stops short of describing what the effect report or its checks contain, so an agent still has to infer what to inspect after the call.

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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: 'Every size is named; nothing is taken for you' signals that no dimensions default, and 'holes in the support or web are named in connection.holes_not_drilled.try' explains the reporting path for undrilled holes. The reference to connection.holes_not_drilled.try is not a schema property, which weakens its usefulness slightly.

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 with scope: 'Creates one steel connection by rule at a steel bar'. It also names the sibling boundary explicitly ('The bars themselves: create_elements'), so an agent can separate this from element creation without reading either schema.

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 clear conditions: use this for the connection itself, use create_elements for the bars, and use dry_run to preview. It does not state explicit exclusions beyond that or describe prerequisites such as what the member/support must already be, but the routing guidance is unambiguous.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources