moddl

Mirror elements

mirror_elements

Mirrors elements (guid, guids or set) across a plane onto their image, in place of copy plus rotate. Openings and fills placed with them follow; a door or window turns its hand: OperationType or PartitioningType _LEFT and _RIGHT swap, at its type only where that types no element left unmirrored (read_as names each). 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. The placement stays right-handed, so each element moves (turns where its x axis is not square to the plane); a plain extrusion takes the mirrored profile, a body other than a plain extrusion is wrapped under the reflection (structure wrapped) and refuses set_dimension and extend_element: size it first, then mirror; a straight Axis about its midpoint stays. Refused: a profile set usage, a layer set across which the plane cuts, an annotation or port placed on a mirrored element. Mirror a copy: copy_elements first.

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": "mirror_elements"
  }
}

Input Schema

Name	Required	Description
`set`	No	A 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
`guid`	No	One element (GlobalId)
`note`	No	Your note, stored with the new revision
`guids`	No	These elements (GlobalIds)
`plane`	No	The mirror plane
`dry_run`	No	Preview: the planned effect and a plan_id, nothing written
`plan_id`	No	Execute 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
`request_id`	No	Your id for this call: a repeat answers the first result and writes nothing
`expect_count`	No	With set: how many elements the set holds - guards against a mixed-up set id
`expect_beyond`	No	With plan_id: how many elements the plan reaches beyond those named (n_beyond of PLAN_REQUIRED or the dry_run)
`expect_contacts`	No	Intended contacts: checks.contacts splits into as_expected, missing, surprises; an omitted kind is not judged

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations only say not read-only, not idempotent, not destructive; the description adds substantial behavior beyond that — a new revision is created, an effect report returns n_changed/rejected/cloned/carried, partially stale targets are rejected individually while others are written, and wrapped bodies refuse set_dimension and extend_element. The only real gap is return-shape detail for the effect report, which is gestured at but not structured.

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?

Nearly every clause carries information, and the core operation is front-loaded, but the telegraphic, semicolon-chained style makes several passages hard to parse — 'at its type only where that types no element left unmirrored (read_as names each)' requires re-reading. Compression has crossed into ambiguity for a 200-word description.

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 an 11-parameter, mutation-heavy geometry tool with no output schema, the description covers the geometry consequences (right-handed placement, elements rotate where their x axis is not square to the plane, plain extrusions take the mirrored profile, wrapped bodies, straight axes) plus the transactional and refusal behavior. Nothing an agent needs before calling is missing.

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 cross-parameter semantics the schema does not state: which parameters act as the target selector versus which are a filter (never a filter), and that the plan_id returned by dry_run must be executed with expect_beyond when PLAN_REQUIRED names extra elements. Individual field meanings (plane, note, request_id) are left entirely to the schema.

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 ('Mirrors elements ... across a plane onto their image') and immediately positions it against the sibling operations it replaces ('in place of copy plus rotate', 'Mirror a copy: copy_elements first'). An agent can distinguish it from copy_elements, rotate_elements, and move_elements without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit about the admissible targets ('guid, guids or a set from find_elements/get_selection, never a filter'), about the dry-run path ('PLAN_REQUIRED, run its plan_id with expect_beyond'), and about when not to use it (mirroring a copy requires copy_elements first). It also enumerates refused cases, which is guidance in the negative direction and rarer than the positive.

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

All moddl tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?