Skip to main content
Glama

Split element

split_element

Splits one element (guid) into two. Along its axis: a pipe or duct segment, beam, column, member or pile of one extrusion, without openings, fills or parts. Through its profile: a wall or slab of one vertical extrusion (rectangle or straight-edged outline), cut by a vertical plane; the wall perpendicular to its axis (at, distance_m) or at a plan line, a slab at a plan line. Part A keeps GlobalId, placement and start (a slab: the side left of the line); part B is created after the gap with type, material (layer usage), system and storey, its own psets, no quantities. An opening goes with the part it lies in, with its fill; one across the cut refuses the call (opening_on_split). A wall joint at the end moves to B. Ports beyond the cut go to B with their links (GlobalIds kept); both new ends get a port, linked at gap 0, free otherwise. Quantities of A are invalidated, stale length values named. New revision, effect report (n_changed, rejected, cloned, carried). A call that succeeds is not a job that's done. Target: guid, guids or a set from find_elements/get_selection, never a filter. Beyond the named: PLAN_REQUIRED, run its plan_id with expect_beyond.

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": "split_element"
  }
}

Input Schema

NameRequiredDescriptionDefault
atNoThe cut, a point on the axis; beside it by more than 0.1 mm is refused, never projected
gapNoFree length between the parts, default 0 (a chamber or fitting fills it)
setNoA set id from find_elements or get_selection: writes exactly the elements seen there, nothing that matches later. An element changed since reading is rejected alone; the others are written
guidNoOne element (GlobalId)
lineNoOr, wall or slab: the cut as plan line [[x,y],[x,y]] m; crossing the outline more than once is refused
noteNoYour note, stored with the new revision
guidsNoThese elements (GlobalIds)
dry_runNoPreview: the planned effect and a plan_id, nothing written
plan_idNoExecute exactly the plan a dry_run returned, all or nothing; the plan holds target and fields. Plans that clone the same shared object (type, material) run one after the other: plan the second after the first ran, else PLAN_CHANGED
distance_mNoOr the cut as distance from the axis start (end of part A)
request_idNoYour id for this call: a repeat answers the first result and writes nothing
expect_countNoWith set: how many elements the set holds - guards against a mixed-up set id
expect_beyondNoWith plan_id: how many elements the plan reaches beyond those named (n_beyond of PLAN_REQUIRED or the dry_run)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

With annotations only declaring the mutation/safety profile, the description carries a great deal: part A keeps GlobalId and placement, part B is rebuilt with type/material/system/storey and its own psets but no quantities, quantities of A are invalidated, ports beyond the cut migrate with their links, and a new revision with an effect report (n_changed, rejected, cloned, carried) is produced. Refusal behavior and cross-part openings are spelled out, which is exactly the context annotations cannot supply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded with a clean opening sentence, but the body degrades into long run-on fragments with heavy domain jargon ("through its profile", "layer usage", "psets") and an odd aphorism, "A call that succeeds is not a job that's done." Information density is high, yet readability and scannability suffer.

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 13-parameter mutation tool with no output schema, the description covers the return values (the effect report fields), the revision side-effect, plan/dry_run escalation, idempotency via request_id, and the failure modes. An agent has enough to plan and invoke the call without further reference.

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 schema already documents every parameter; the description still adds conditional meaning the schema cannot, namely that walls use a perpendicular cut given either by "at" or distance_m (or a plan line) while slabs use a plan line. It also clarifies the gap-0 port-link behavior and that expect_beyond belongs with plan_id, though it leaves the four target parameters overlapping somewhat unexplained.

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?

"Splits one element (guid) into two" gives a precise verb and resource, then immediately scopes which element geometries qualify: pipe/duct/beam/column/member/pile along the axis, wall/slab through the profile. This is clearly distinguishable from siblings like merge_elements, clip_elements or extend_element.

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 target-selection rules ("guid, guids or a set from find_elements/get_selection, never a filter") and the escalation path when a target is beyond the named ones (PLAN_REQUIRED, then run its plan_id with expect_beyond). It also defines refusal conditions (opening_on_split, line crossing the outline twice). It never explicitly names an alternative tool or says when not to split, which keeps it off a 5.

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