Skip to main content
Glama

Move elements

move_elements

Moves elements: by a vector, by direction and distance, to a point, or until they touch a target set (until). 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. reference center/min/max reads the body hull: an element with body_gap is refused there (partial_body: origin works). An IfcOpeningElement without fill named by guid moves by a vector (by, or direction with distance) inside its host; refused where it would leave it, stop cutting through or cut another opening. A filled one moves with its fill. An IfcStructuralPointConnection, one per call, moves by a vector in the analysis model only: its members, faces and eccentricities follow (carried, structural_moved), elements stay. What is placed relative to them (fills, parts) goes along and stands in carried. Directions east/north take the project axis; with a rotated TrueNorth the call is refused with both readings. Example: {"guid":"2O2Fr$t4X7Zf8NOew3FLOH","direction":"east","distance":"50 cm"}

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": "move_elements"
  }
}

Input Schema

NameRequiredDescriptionDefault
byNoTranslation [x,y,z] in m
toNoMove the reference point here; a point of another element: get_element include snap_points
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)
hostNoOne door or window (with its opening) or one unfilled opening moves by by (or direction) into this wall, GlobalIds kept; the new host is measured (wall-like, aligned, opening inside), else refused, never chosen by moddl
noteNoYour note, stored with the new revision
guidsNoThese elements (GlobalIds)
movesNoInstead of by: one vector per element, one call; names exactly the elements of guid, guids or set
untilNoMove until touching one of the target elements; n_checked counts the candidates
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
distanceNoWith direction: metres or a text with unit
directionNoWith distance: a compass or vertical direction
referenceNoWith to: which point of the element; default origin (placement)
request_idNoYour id for this call: a repeat answers the first result and writes nothing
to_stationNoInstead of to: the placement origin onto a station point; only moves, read_as gives the rotate_elements calls to turn with the tangent and roll with the cant
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)
within_openingNoA door or window moves by a vector inside the opening it fills; the opening stays. Refused where it would stand further out of the opening than before
expect_contactsNoIntended contacts: checks.contacts splits into as_expected, missing, surprises; an omitted kind is not judged

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?

Beyond the annotations, it discloses substantial behavior: a new revision is created, an effect report is returned (n_changed, rejected, cloned, carried), dry_run produces a plan_id, plans are all-or-nothing, and specific IFC elements are refused or carried under defined conditions. It also states that direction calls can be refused under rotated TrueNorth, which is meaningful operational context not present in the annotations.

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?

The description is front-loaded with the core purpose, but it is a dense, semicolon-heavy paragraph with cryptic references such as 'PLAN_REQUIRED' and 'partial_body' that make it harder to scan. The complexity justifies length, but the structure could be clearer and a few sentences feel compressed rather than concise.

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 20-parameter mutation tool with no output schema, the description covers the important modes, target restrictions, plan workflow, report fields, and several IFC-specific edge cases and refusal conditions. An agent has enough information to choose inputs and anticipate major failure modes.

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, but the description adds cross-parameter semantics: target inputs must come from guid/guids/set and never a filter, PLAN_REQUIRED gates moves beyond the named elements, reference center/min/max reads the body hull, and body_gap elements are refused there. These are meaningful constraints beyond the individual schema descriptions.

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 opens with a specific verb and resource ('Moves elements') and enumerates the supported motion modes: vector, direction+distance, to a point, and until contact. This clearly distinguishes it from siblings such as rotate_elements or copy_elements without needing the 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?

It gives explicit targeting guidance ('guid, guids or a set from find_elements/get_selection, never a filter') and conditions such as PLAN_REQUIRED and expect_beyond. It also explains special cases for IfcOpeningElement and IfcStructuralPointConnection, though it does not explicitly compare against sibling tools beyond referencing find_elements/get_selection and rotate_elements in one note.

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