Foundry MCP

item-create

Create a new item directly in an actor's inventory (dnd5e data model): custom items, loot, simple gear. SRD content: item-create-from-compendium; the world Items Directory instead of an actor: world-item-create.

Input Schema

Name	Required	Description
`img`	No	Item icon path (optional)
`name`	Yes	Item name
`type`	Yes	dnd5e item type ("backpack" is accepted as the legacy name of "container")
`system`	No	D&D 5e system data.
`actorId`	Yes	Actor ID to add item to (from actor-list/actor-filter)

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 26, 2026

changedInput schema / properties / system / description

Previous value: -"D&D 5e system data: quantity, weight, price, rarity, equipped, range, damage, uses, etc."New value: +"D&D 5e system data."

Changed7 schema fields changedOct 8, 2026
- removedInput schema / properties / system / properties / damage / description
```
Removed value: -"Damage"
```
- removedInput schema / properties / system / properties / damage / properties / base / properties / types / description
```
Removed value: -"e.g. [\"slashing\"]"
```
- removedInput schema / properties / system / properties / range / description
```
Removed value: -"Weapon/spell range"
```
- changedInput schema / properties / system / properties / range / properties / long / description
```
Previous value: -"Long range (e.g. 600)"New value: +"e.g. 600"
```
- changedInput schema / properties / system / properties / range / properties / reach / description
```
Previous value: -"Melee reach in ft (default 5)"New value: +"reach ft"
```
- removedInput schema / properties / system / properties / range / properties / units / description
```
Removed value: -"ft or m"
```
- changedInput schema / properties / system / properties / range / properties / value / description
```
Previous value: -"Normal range (e.g. 150)"New value: +"e.g. 150"
```

Changed7 schema fields changedOct 8, 2026

changedInput schema / properties / system / properties / uses / additionalProperties
```
Previous value: -falseNew value: +true
```

addedInput schema / properties / system / properties / uses / properties / max / anyOf

Added value: +[
+  {
+    "type": [
+      "number",
+      "string"
+    ]
+  },
+  {
+    "type": "null"
+  }
+]

removedInput schema / properties / system / properties / uses / properties / max / type
```
Removed value: -[
-  "number",
-  "null"
-]
```
changedInput schema / properties / system / properties / uses / properties / per / description
```
Previous value: -"Recovery: \"sr\", \"lr\", \"day\", \"charges\""New value: +"dnd5e 3.x"
```

addedInput schema / properties / system / properties / uses / properties / recovery

Added value: +{
+  "description": "[{ period: \"lr\" }]",
+  "items": {
+    "additionalProperties": true,
+    "properties": {
+      "period": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "period"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedInput schema / properties / system / properties / uses / properties / spent

Added value: +{
+  "description": "dnd5e 4+: spent",
+  "minimum": 0,
+  "type": "integer"
+}

changedInput schema / properties / system / properties / uses / properties / value / description
```
Previous value: -"Remaining uses"New value: +"dnd5e 3.x"
```

First observedSep 21, 2026

TDQS

A4.2/5.0

Behavior3/5

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false), so the bar is lower. The description adds useful context that this writes directly onto an actor's inventory under the dnd5e data model, but it says nothing about what happens on repeat calls (a new duplicate item), whether the actor must exist, or what is returned.

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 short sentences with the capability front-loaded and the disambiguation clauses following. Every phrase carries information; nothing is restated from the schema or annotations.

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?

For a creation tool with a nested system object and no output schema, the description covers purpose, system applicability (dnd5e), and sibling routing well. The one remaining gap is the return value: with no output schema, an agent is not told whether the created item or its ID comes back.

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%, including the type enum with the backpack/container note and the nested system object, so the schema carries the parameter burden. The description adds only the general signal that system follows the dnd5e data model and that actorId originates from actor-list/actor-filter (already stated in the schema). 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?

The description opens with a specific verb and resource ("Create a new item directly in an actor's inventory") and immediately scopes the content type (custom items, loot, simple gear). It also names the two adjacent tools it is not (item-create-from-compendium, world-item-create), so an agent can distinguish it from siblings without opening schemas.

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 rules are given: SRD content goes to item-create-from-compendium, and placing an item in the world Items Directory goes to world-item-create. That covers the two realistic alternatives an agent would otherwise confuse with this tool, leaving little to infer.

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

All Foundry MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?