Skip to main content
Glama

audit_asset_references

Destructive

Audit a project folder to detect orphaned assets and broken references without loading them, returning a summary and report path.

Instructions

Project-wide reference audit under folder_path: assets with zero referencers ("orphans") and dependencies pointing at a package no longer on disk ("broken"). Metadata-only through the AssetRegistry -- it never LOADS the assets, so it scales to a large project without spiking memory. It returns only a summary plus a report path; read the detail back with read_mcp_audit_file. For one asset rather than a sweep, use get_asset_referencers / get_asset_dependencies; for unused assets only, find_unused_assets.

Returns: { path: string, summary: { asset_count: int, orphan_count: int, broken_reference_count: int, dependency_type: string } }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
recursiveNoRecurse into subfolders. Defaults to true.
folder_pathNoContent-relative folder to scan. Defaults to "/Game".
max_resultsNoCap on assets processed (1-100000). Defaults to 5000.
dependency_typeNo"hard"|"soft"|"all" (case-insensitive), default "all". Scopes BOTH the referencer check (orphan detection) and the dependency check (broken-reference detection) to that dependency kind. Use "hard" to find only the broken references that actually break loading -- a broken SOFT reference (TSoftObjectPtr/FSoftObjectPath) does not. "all" applies no Hard/Soft requirement at all.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Adds real context beyond annotations: metadata-only via AssetRegistry, never loads assets, scales without memory spikes, and returns only a summary + report path so the agent knows a second read is required. It implicitly discloses a disk write ('a report path'), but never reconciles with the destructiveHint=true annotation — an agent could read 'metadata-only, never LOADS the assets' as a harmless scan and be surprised by the flagged destructive profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

Front-loads purpose, then behavior, then alternatives, then the return shape — four tight sentences with no filler. The returns block is compact and every clause carries information.

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 complex project-wide audit with four optional params and no output schema, the description supplies the return contract inline ({ path, summary: {...} }) and the two-phase workflow (report then read_mcp_audit_file), so nothing an agent needs to call it 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 schema already fully documents recursive, folder_path, max_results, and dependency_type (including the hard/soft semantics). The description only restates folder_path scope and adds no syntax or format beyond the schema, so the baseline 3 applies.

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+resource+scope (project-wide reference audit under folder_path finding orphans and broken references) and names the sibling tools it is not (get_asset_referencers, get_asset_dependencies, find_unused_assets). An agent can distinguish it from every neighboring asset-query tool without opening a 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 routing: 'For one asset rather than a sweep, use get_asset_referencers / get_asset_dependencies; for unused assets only, find_unused_assets,' plus the follow-up step 'read the detail back with read_mcp_audit_file.' When-to-use, when-not-to-use, and the alternative tools are all named.

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