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

Annotations already indicate readOnlyHint=false, destructiveHint=false, idempotentHint=false, so the agent knows this is a non-read, non-destructive, non-idempotent action. The description adds that results appear in Foundry chat, which is useful behavioral context. However, it doesn't disclose details like whether the roll is whispered, whether modifiers can be applied, or whether the actor must be a PC/NPC. The description adds some value beyond annotations but not rich 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each earning its place: the first states the action and system, the second routes to the correct alternative for a different system, and the third states the output location. No fluff, no repetition of schema details, and the key scoping information is front-loaded.

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 single-parameter roll tool with no output schema, the description is nearly complete: it identifies the system, the skill, the target actor, the output channel, and the alternative for other systems. The only minor gap is that it doesn't mention whether the roll is public or private, or whether any additional options (like advantage/disadvantage) are supported, but these are not essential for a basic call.

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 description coverage is 100%: the only parameter, actorId, is described as 'Actor ID (from actor-list/actor-filter)'. The description adds the context that the actor is the target of the Perception check, but it doesn't add meaning beyond what the schema already provides. Baseline 3 is appropriate when the schema fully documents the parameter.

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?

The description states a specific verb ('Roll'), a specific resource ('Perception check for an actor'), and the game system context (D&D 5e). It also explicitly distinguishes itself from the sibling dnd5e-roll-skill by noting it is the same with skill prc, and from pf2e-roll-perception for Pathfinder 2e. This makes the tool's purpose unambiguous and differentiates it from closely related siblings.

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?

The description explicitly says when to use this tool ('D&D 5e worlds') and when not to ('In Pathfinder 2e worlds use pf2e-roll-perception instead'). It also references the equivalent generic skill roll tool (dnd5e-roll-skill), giving the agent clear routing guidance. This is explicit when/when-not guidance with named alternatives.

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