Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

diagnose_navmesh

Read-onlyIdempotent

Diagnose Unreal navmesh issues by reporting nav bounds, Recast tiles, invoker generation, and volume validity, then returning an actionable fix list.

Instructions

One-call navmesh diagnosis: reports every ANavMeshBoundsVolume (brush validity + world extent — detects the EMPTY brush = 0 bounds that yields 0 tiles), inclusion/total nav bounds, bWholeWorldNavigable, invoker-only generation + registered invokers, the RecastNavMesh MaxTiles / built (active) tile count / RuntimeGeneration, and is_spatially_loaded per volume, plus an actionable diagnosis list. Read-only.

Returns: { world, has_authority, nav_system_present, whole_world_navigable, generate_only_around_invokers, supported_agent_count, nav_data_count, is_navigation_dirty, nav_bounds_volume_count, nav_bounds_volumes:[{actor_name, actor_label, is_spatially_loaded, brush_present, brush_empty, bounds_valid, bounds_extent:{x,y,z}, brush_poly_count, note}], registered_nav_bounds_count, total_nav_bounds:{valid, min:{x,y,z}, max:{x,y,z}, extent:{x,y,z}}, invoker_component_count, invoker_location_count, invoker_seed_bounds_count, recast_navmesh_present, recast:{name, runtime_generation, supports_runtime_generation, max_tiles, active_tile_count, tile_size_uu, is_spatially_loaded}, diagnosis:[string], success, world_name, world_package, world_type, net_mode, pie_instance }. On a CLIENT world (has_authority=false) the heuristics are suppressed and diagnosis says so first: a client with no nav system / no RecastNavMesh is EXPECTED, and rebuild_navigation is NEVER recommended from there.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
worldNoOptional world selector: absent/'editor' (default) | 'server' (**the one you want in PIE**: the navmesh is SERVER-AUTHORITATIVE, so only the authoritative world has a nav system and a RecastNavMesh) | 'pie' (ambiguous: PlayWorld, else the first PIE context -- may well land on the CLIENT) | 'client' | 'pie:N' | 'game' (alias of 'pie').

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, and non-destructive behavior, but the description adds substantial context beyond them. It details client-world behavior where heuristics are suppressed and absence of nav data is expected, lists the full diagnostic return shape, and clarifies that rebuild_navigation is never recommended from a client. This is rich behavioral disclosure with no contradictions.

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?

The description is long due to the detailed 'Returns' block, but it is front-loaded with the purpose and structured for a tool that lacks an output schema. The return-field list is justified because it compensates for the absent output schema, though there is minor redundancy with the read-only annotation.

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?

Given the complexity of navmesh diagnosis, the single optional parameter, rich annotations, and no output schema, the description is complete. It specifies the return shape, client-world caveats, and actionable diagnosis output, leaving little ambiguity for an agent invoking the tool.

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%, and the single 'world' parameter already has detailed semantics in the schema, including editor/server/pie/client distinctions. The description body reinforces client-world implications but does not add new parameter syntax or meaning beyond what the schema provides. Baseline 3 is appropriate when the schema fully documents parameters.

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: 'One-call navmesh diagnosis' and then enumerates exactly what is reported. It clearly distinguishes this read-only diagnostic from the sibling rebuild_navigation by explicitly stating rebuild_navigation is never recommended from a client world. An agent can identify the tool's function without opening 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?

The description provides clear context for use: it explains the PIE/server world selection and warns that on a CLIENT world the heuristics are suppressed and rebuild_navigation should not be used. However, it does not explicitly compare this tool with other diagnostic siblings like get_navigation_data or get_navigation_info, leaving some selection guidance to inference.

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