Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

is_point_inside_mesh

Read-onlyIdempotent

Check whether a 3D point lies inside a DynamicMeshActor's current mesh via a fresh winding-number test; results reflect latest edits without changing the mesh.

Instructions

Test whether a 3D point is inside the live dynamic mesh of a DynamicMeshActor using Fast Winding Number via UGeometryScriptLibrary_MeshSpatial::IsPointInsideMesh. Every call builds a fresh BVH and fast winding tree from the mesh as it is now (the plugin keeps none), so the answer always reflects the latest mesh edits. The mesh is not changed.

Returns: { actor_name, is_inside: bool, containment_outcome: string } -- actor_name is the dynamic mesh component's name, not the actor label.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actor_nameYesLabel or name of the target DynamicMeshActor.
query_pointNo[x, y, z] point in the mesh's local space.
max_distanceNoOptional float; it has no effect on this query, whose winding-number test uses no search distance.
winding_thresholdNoOptional float; default 0.5 (standard parity test). Higher values shrink the "inside" region.
allow_unsafe_modifiedNoOptional; maps to bAllowUnsafeModifiedQueries (default false). It has no effect: the BVH is built fresh on every call, so it always matches the mesh.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.2.2
    • changedInput schema / properties / allow_unsafe_modified / description
      Previous value: -"Optional; allow querying against a mesh modified since the BVH was built without re-syncing (maps to bAllowUnsafeModifiedQueries, default false)."New value: +"Optional; maps to bAllowUnsafeModifiedQueries (default false). It has no effect: the BVH is built fresh on every call, so it always matches the mesh."
    • changedInput schema / properties / max_distance / description
      Previous value: -"Optional float; max search distance for the spatial query (0 = unlimited)."New value: +"Optional float; it has no effect on this query, whose winding-number test uses no search distance."
  2. First observedv1.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real value beyond them: it discloses that a fresh BVH and winding tree is rebuilt on every call (a performance cost) and that the plugin retains no accelerator, explaining why results are always current. That is meaningful behavioral context the 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.

Conciseness4/5

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

Front-loaded with the core purpose, followed by mechanism, then a clearly delimited returns line. Every sentence carries information; slightly long but no filler, and the return-value detail is warranted because there is no output schema.

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?

With no output schema, the description supplies the return shape ({ actor_name, is_inside, containment_outcome }) plus a clarifying caveat about actor_name, and the 100%-covered schema handles the inputs. Combined with the annotated safety profile and the rebuild-each-call disclosure, nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds only marginal parameter meaning — it clarifies that returned actor_name is the component name rather than the actor label, but input parameter semantics (query_point local space, winding_threshold behavior, inert params) are already fully handled by 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 ('Test whether a 3D point is inside the live dynamic mesh of a DynamicMeshActor') and names the exact underlying engine call. An agent can immediately separate this containment query from surface-query siblings like find_nearest_point_on_mesh or find_nearest_ray_intersection_with_mesh.

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

Usage Guidelines3/5

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

The description explains the mechanism well (fresh BVH each call, reflects latest edits) which implies when the tool is appropriate, but it never states explicit when-to-use conditions or names an alternative sibling for the neighboring surface-distance queries. Usage is left to be inferred.

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

Deploy Server

Other Tools