Roll raw D&D 5e ability check (no skill proficiency). Use for contested checks or when no skill applies. Results appear in Foundry chat. 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 cover the safety profile (readOnly, idempotent, destructive all false), so the bar is lower; the description still adds value by disclosing that results appear in Foundry chat and by stating the mutual-exclusion rule 'Never both advantage and disadvantage'. It does not mention permissions or what a failure/loss looks like, but the added constraints are meaningful.
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?
Three short sentences, each earning its place, with purpose stated first, routing second, and the behavioral constraint last. No filler.
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?
For a 4-param roll tool with no output schema, the description covers purpose, routing, chat output, and the advantage/disadvantage rule. Remaining gaps (permissions, whether a target must be selected) are minor for a read-only dice roll.
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, but advantage/disadvantage have no descriptions in the schema. The description partially compensates by constraining how advantage and disadvantage interact ('Never both'), which is exactly the rule an agent would otherwise get wrong.
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+resource ('Roll raw D&D 5e ability check') with a scope qualifier ('no skill proficiency') that cleanly distinguishes it from the sibling dnd5e-roll-skill. An agent can pick the right roll tool without opening either 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 explicit usage conditions ('contested checks or when no skill applies'), which is real routing guidance rather than implied. It stops short of naming the alternative tool (dnd5e-roll-skill) directly, so it's clear but not fully explicit about exclusions.
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.