Skip to main content
Glama

Find missing files

find-missing-files
Read-onlyIdempotent

Identify missing file references in Foundry VTT world documents: images, sounds, videos, text, and fonts in fields and markup. Scans data storage and Foundry's files; wildcard paths counted, compendiums skipped.

Instructions

Find files that world documents point to but that do not exist: images, sounds, videos, text and fonts in fields and in markup, looked up in the data storage and in Foundry's own files. Wildcard paths are counted but not checked. Compendiums are not scanned.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
underNoOnly paths inside this folder
maxResultsNoAt most this many missing files are named, 1 to 1000, default 200
collectionsNoCollections to scan: scenes, actors, items, journal, playlists, tables, cards, macros, users. Default all.
maxDirectoriesNoAt most this many folders are listed, 1 to 1000, default 300

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv14.2609.4

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description adds meaningful behavioral nuance beyond those flags: wildcard paths are counted but not checked, compendiums are not scanned, and the search spans both data storage and Foundry's own files. This gives an agent expectations about coverage and false positives without contradicting the read-only safety hints.

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?

Two dense sentences with no fluff. The first sentence front-loads the action, scope, and locations; the second packs the essential caveats. Every clause adds information.

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?

The description is complete for a read-only analysis tool: it states what is searched, where, and the important coverage limits. With no output schema, it leaves the exact result shape implicit, but the maxResults/maxDirectories parameters and the verb 'find' make the return intent clear.

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 every parameter already has a clear description in the schema, so the baseline is 3. The tool description adds no parameter-level meaning beyond the schema; it neither clarifies formats nor reveals relationships between 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 uses a specific verb and resource: 'Find files that world documents point to but do not exist.' It further narrows scope by enumerating file types, lookup locations, and explicit exclusions, making it distinguishable from sibling file tools like find-file-references and browse-files without needing to open 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 gives clear context on what the tool covers (images, sounds, videos, text, fonts in fields and markup, data storage and Foundry files) and states two limitations: 'Wildcard paths are counted but not checked. Compendiums are not scanned.' It does not explicitly name sibling alternatives or state a direct when-to-use/when-not-to-use rule, so it falls just short of a 5.

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