Roll attack with a weapon/spell. Use actor-get FIRST to find itemId. For full attack sequence (roll + damage if hit), consider dnd5e-item-use instead. Never both advantage and disadvantage (module 8.13+).
| Name | Required | Description | Default |
|---|---|---|---|
| itemId | Yes | Item ID of weapon/spell (from actor-get items list) | |
| actorId | Yes | Actor ID making the attack | |
| advantage | No | ||
| disadvantage | No |
Changes observed during successful MCP inspections.
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 declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the description needn't restate it. It adds real behavioral context: a versioned rule ("Never both advantage and disadvantage (module 8.13+)") and the actor-get prerequisite. It stops short of saying the result is posted to chat or how a hit/failure resolves, keeping it below 5.
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 tightly written sentences, each carrying a distinct piece of information, with the core action front-loaded ahead of prerequisites and alternatives. 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?
With no output schema and annotations covering safety, the description supplies prerequisites, alternative routing, and the adv/disadv constraint. It omits the return shape (e.g. success/failure, chat output) and the meaning of the version guard, so it is strong but not airtight for a 4-param tool.
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 only 50% – itemId and actorId are self-documented, but advantage/disadvantage carry no schema descriptions. The description partially compensates by stating they are mutually exclusive ("Never both..."), but adds no semantics for when to set either or the 8.13+ caveat's effect on them.
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?
"Roll attack with a weapon/spell" states a specific verb and resource, and the actorId/itemId framing makes the target unambiguous. It also explicitly distinguishes itself from dnd5e-item-use, so an agent can separate the two roll tools 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?
Names the prerequisite ("Use actor-get FIRST to find itemId"), the alternative and the condition that selects it ("For full attack sequence... consider dnd5e-item-use instead"), plus a hard constraint (never both advantage and disadvantage). when/when-not/alternatives are all present.
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.