FFT Companion

Find where an item comes from

find_item_sources

Reverse lookup: every way to obtain a piece of equipment or a consumable — which outfitter unlocks it and after which battle, which monsters poach into it, and which treasure tiles hold it. This is indexed backwards from the game data and is not readable from the item record alone. Free while this deployment runs unmetered.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`itemId`	Yes	Equipment or consumable id, e.g. 'excalibur'.
`version`	Yes	Which release to read. psx = original PlayStation, wotl = War of the Lions, ic = The Ivalice Chronicles. Data differs meaningfully between them.

TDQS

A4.4/5.0

Behavior4/5

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

No annotations are provided, so the description carries full weight. It discloses that the data is indexed backwards from game data and that the tool is free while unmetered. For a read-only lookup tool, this is adequate behavioral context.

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?

Three sentences, front-loaded with the purpose. Every sentence adds essential information: action, scope, technical detail, and status. No unnecessary words.

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?

Given the tool has 2 required params and no output schema, the description sufficiently explains the purpose and parameters. It lacks details on return format, but for a reverse lookup tool the description is mostly complete.

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%, but the description adds value by providing examples (e.g., 'excalibur') and expanding on the version enum with clear explanations of each option and noting data differences between versions.

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 "Reverse lookup" and clearly states the resource: every way to obtain an item. It lists specific sources (outfitter, monsters, treasure tiles), distinguishing it from sibling tools like get_monster or query_equipment.

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 explains this tool is for reverse lookup and is not readable from the item record alone, implying when to use it. However, it does not explicitly state when not to use it or mention alternatives, though the context is clear.

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

All FFT Companion tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation5/5

Each tool targets a distinct resource/action: compare_versions diffs releases, find_item_sources is a reverse-lookup, get_job/get_monster provide deep entity records, get_records is generic batch retrieval, query_equipment filters the equipment table, search resolves names to IDs, and list_versions describes the dataset. The descriptions explicitly call out when one tool should be used instead of another, so an agent should be able to pick correctly.

Naming Consistency4/5

Most tools follow a clear lower_snake_case verb_noun pattern (get_job, get_monster, get_records, list_versions, compare_versions, find_item_sources, query_equipment). The only deviation is the bare verb search, and the retrieval verbs vary (get/find/query/list) rather than being uniform, but the pattern is still predictable.

Tool Count5/5

Eight tools is a well-scoped size for a read-only game-data companion: a global search entry point, version metadata, generic batch retrieval, two deep-dive entity tools, an equipment filter, an item-source reverse lookup, and a cross-version comparator. No tool feels redundant, and every tool has a clear use case.

Completeness3/5

The server covers the main reference workflows well: discovery via search, batch retrieval via get_records, deep job/monster records, equipment shopping, item sourcing, and version comparison. However, there is no way to enumerate or filter non-equipment entity kinds (abilities, jobs, monsters, bosses, locations, consumables) without already knowing names/IDs, and compare_versions cannot identify which entities changed across versions. Those are notable gaps for a comprehensive companion server.

Resources

Need Help?