Roll D&D 5e saving throw. Use when resisting spells, traps, or effects. Results appear in Foundry chat. Use actor-list first to find actorId. Never both advantage and disadvantage (module 8.13+).
| Name | Required | Description | Default |
|---|---|---|---|
| ability | Yes | Ability code (str, dex, con, int, wis, cha) | |
| actorId | Yes | Actor ID (from actor-list/actor-filter) | |
| advantage | No | ||
| disadvantage | No |
Changes observed during successful MCP inspections.
Input schema / properties / ability / descriptionPrevious value: -"Ability code: str=Strength, dex=Dexterity, con=Constitution, int=Intelligence, wis=Wisdom, cha=Charisma"New value: +"Ability code (str, dex, con, int, wis, cha)"Input schema / properties / advantageAdded value: +{
+ "type": "boolean"
+}Input schema / properties / disadvantageAdded value: +{
+ "type": "boolean"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is not read-only and not idempotent, but the description adds real value beyond them: the output destination ('Results appear in Foundry chat') and a validation constraint ('Never both advantage and disadvantage (module 8.13+)'). The prerequisite on actorId also flags a required lookup step. It stops short of describing what a save result contains or any failure modes.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four short, front-loaded sentences with zero filler: purpose, usage context, output location, prerequisite, constraint. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description usefully tells the agent where results surface (Foundry chat), covers the actorId prerequisite, and flags the advantage/disadvantage conflict. Complete enough to invoke correctly, though it leaves the mechanics of advantage/disadvantage and any error behavior unstated.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% – actorId and ability are documented in the schema, while the advantage/disadvantage booleans are bare. The description compensates with the mutual-exclusivity rule for those two flags, which is genuine semantic information, but it still doesn't explain what setting advantage=true actually does. Adequate but not full compensation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Roll D&D 5e saving throw') that cleanly separates it from the sibling roll tools (dnd5e-roll-ability, dnd5e-roll-skill, dnd5e-roll-attack, dnd5e-roll-damage). An agent can pick it out without opening any schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives a clear usage context ('Use when resisting spells, traps, or effects') and a prerequisite ('Use actor-list first to find actorId'). It does not explicitly name the alternative tools or state when not to use it, but the resource is narrow enough that no exclusion is really needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.