Skip to main content
Glama
Sign In

moddl

by site.moddl
OverviewDiscussionsAdmin

Edit grid

edit_grid
Destructive

Edits the axes of IfcGrids (guid, guids or the set of find_elements class IfcGrid): rename, move, add or remove one axis, set a spacing or append, the same edit on each named grid. Points are grid m [x,y] in the grid's own frame, as create_elements grid names them. 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. A FootPrint sharing the axis curves follows; one with own curves is rebuilt (footprint_rebuilt). A grid congruent with a named one but not named stays as it is, listed in coincident_not_named: name it to edit it too. The report's grid_edit: each grid before and after, read back.

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": "edit_grid"
  }
}

Input Schema

NameRequiredDescriptionDefault
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
editNoOne operation: rename {tag|ord, new_tag}; move {tag|ord, by} or {tag|ord, from, to}; add {tag, from_tag, by} or {tag, from, to}; remove {tag|ord}; set_spacing {tag|ord, spacing}; append {tag, spacing}
guidNoOne element (GlobalId)
noteNoYour note, stored with the new revision
guidsNoThese elements (GlobalIds)
dry_runNoPreview: the planned effect and a plan_id, nothing written
on_axisNomove, set_spacing: elements of the grid storey on an old axis (axis line or hull centre, 1 mm; judged at their body points) are named in on_axis and need the plan_id (expect_beyond) that moves them along; stay moves the axes alone
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
revisionNoWith edit.ord: the revision you read the order in
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

A4.2/5.0
Behavior4/5

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

Beyond the destructive and non-idempotent annotations, the description discloses substantial behavior: a new revision is created, an effect report is returned, plans are required for beyond-target effects, footprints either follow or are rebuilt, and unnamed coincident grids remain unchanged. It also mentions cloning, rejection, and carried effects, though these terms are not fully explained. This is strong behavioral context, but the dense and sometimes undefined terminology keeps it from being fully transparent.

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 length is justified by a 12-parameter destructive tool, and most sentences carry real rules rather than filler. However, the structure is a dense run-on of telegraphic fragments, including undefined terms like "cloned, carried" and the cryptic sentence "A call that succeeds is not a job that's done." Better front-loading and bullet-like structure would improve readability.

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 complex nested-schema tool with no output schema, the description covers the important workflow: dry_run produces a plan_id, expect_beyond governs beyond-target effects, and the report includes n_changed, rejected, cloned, carried, and grid_edit before/after. It does not fully describe every possible output field or error condition, but it gives enough context for an agent to call the tool correctly and interpret the main return values.

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 beyond the schema: points are in the grid's own frame in metres, targets must be guids or a set rather than a filter, and plan_id executes an all-or-nothing plan that holds target and fields. It also clarifies that a set writes exactly what was seen and rejects changed elements individually. These additions are useful even though much parameter detail is duplicated in the already-rich 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: "Edits the axes of IfcGrids," then enumerates the exact operations (rename, move, add, remove, set_spacing, append). This clearly separates it from siblings such as move_elements, edit_alignment, or edit_mesh because the scope is explicitly IfcGrid axis editing.

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 clear targeting rules: use guid, guids, or a set from find_elements/get_selection, "never a filter," and it explains the dry_run/plan_id workflow with PLAN_REQUIRED. It also states that unnamed congruent grids are left unchanged and must be named to edit. It does not explicitly compare when to choose this tool over sibling editing tools, so it falls short of full alternatives guidance.

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

All moddl toolsInspect
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