Skip to main content
Glama

search_assets_by_pattern

Read-onlyIdempotent

Search every mounted content root for assets whose name matches a substring or wildcard pattern, returning each hit's path, class, and package.

Instructions

Find assets by NAME, scanning every mounted content root (/Game, /Engine, /Water, plugin mounts, ...) and returning name, object path, class and package per hit. The broad "does anything called exist, and where?" search. It has TWO match modes and picks one automatically, reporting which in match_mode: a pattern WITHOUT */? is a case-insensitive SUBSTRING test (FString::Contains) -- pass the bare token, this is the common case; a pattern WITH * or ? is a real glob (FString::MatchesWildcard). WARNING: The glob is ANCHORED AT BOTH ENDS -- it matches the WHOLE name, not a substring -- so Grass* means "starts with Grass" and *Grass* is what reproduces substring behaviour. It only ever looks at the asset NAME, so it cannot find an asset by its folder or by a class it belongs to: use resolve_asset_by_name to check ONE exact name and get every homonym, get_assets_in_folder to enumerate a directory, get_assets_by_type for the 5 built-in type filters, and get_assets_by_tag for an Asset Registry tag.

Returns: { assets: [{ name, path, class, package, is_loaded }], count: int, total_scanned: int, scan_was_pending: bool, search_pattern: string, match_mode: "substring"|"wildcard", case_sensitive: bool, max_results: int, results_truncated: bool }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
patternNoAlias of `search_pattern` (same value, same meaning). Accepted because sibling tools spell this parameter differently; prefer `search_pattern`.
max_resultsNoCap on number of matched assets (1..50000); defaults to 1000. WARNING: Hitting the cap ABORTS the enumeration, so `total_scanned` then counts only the assets visited before the early-out, not the whole registry.
wait_for_scanNoWhen true (default), force-completes the AssetRegistry scan before enumerating so a still-loading registry cannot report total_scanned:0. Set false to skip the (possibly blocking) wait.
case_sensitiveNoWhen true, match is case-sensitive; defaults to false
search_patternNoMatched against the asset NAME. Contains no `*`/`?` -> case-insensitive substring (FString::Contains). Contains `*` or `?` -> glob (FString::MatchesWildcard), ANCHORED at both ends: `*` matches any run including empty, `?` matches 0 or 1 character (UE semantics, not exactly 1). Not a regex.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare it read-only/idempotent/non-destructive, and the description goes well beyond that: it discloses the two auto-selected match modes and which is reported, the case-insensitive substring default, the both-ends-anchored glob pitfall (Grass* vs *Grass*), scan-wait behavior, and the total_scanned truncation caveat.

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?

Purpose and routing alternatives are front-loaded in the first sentences, followed by the match-mode warning and a returns block. It is dense and mostly earns its length, but the substring/glob and anchoring details are partly duplicated between the description and the search_pattern schema entry.

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?

There is no output schema, so the description compensates by spelling out the return payload (assets with name/path/class/package/is_loaded, count, total_scanned, match_mode, results_truncated, etc.). For a 5-param search tool with rich routing, the description is complete enough to call correctly.

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 real meaning: it flags the bare-token substring case as 'the common case', explains the substring-vs-glob selection rule as a single behavior, and reinforces the anchoring semantics for wildcard input. It restates some schema detail (match modes, anchoring) rather than going far beyond it.

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 (find assets by NAME) with scope (every mounted content root) and output fields, and frames itself as the broad 'does <token> exist, and where?' search. It explicitly contrasts with four named siblings, so an agent can distinguish it without opening a sibling 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?

Gives explicit routing: use resolve_asset_by_name for one exact name, get_assets_in_folder to enumerate a directory, get_assets_by_type for the 5 built-in filters, and get_assets_by_tag for a tag. It also states the scope limit (only matches the asset NAME, not folder or class), which functions as a when-not-use rule.

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