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

Annotations are minimal (readOnlyHint=false, destructiveHint=false, etc.) and don't reveal much about behavior. The description adds valuable behavioral context: it explains how isCritical/isFumble flags behave with advantage/disadvantage, specifically that a 20 on the kept die marks a crit and a 20 on the discarded die does NOT count. This is non-obvious behavior that an agent would otherwise not know. It also notes the module version requirement (v8.5.0+). It doesn't describe the return format, but with no output schema, that's a minor gap.

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?

The description is compact and information-dense. It front-loads the core purpose, then provides routing guidance, then the critical behavioral detail about crit/fumble flags, and finally the version requirement. Every sentence earns its place; there's no fluff or repetition of schema content.

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 tool with full schema coverage, the description is quite complete. It covers purpose, alternatives, and a subtle behavioral edge case (crit/fumble with advantage/disadvantage). The only missing piece is the return value shape, but with no output schema and a simple dice-roll tool, an agent can reasonably infer the result. The version requirement is a nice operational detail.

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 single 'formula' parameter is fully documented in the schema with examples ('1d20+5', '2d6', '4d6kh3', '2d20kh1', '2d20kl1'). The description adds context about what the formula is used for and how crit/fumble flags interact with certain formulas, but the core parameter semantics are already in the schema. Baseline 3 is appropriate.

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 clearly states the tool's purpose: 'Roll arbitrary dice for custom checks, random tables, or DM-specified rolls.' It uses a specific verb ('roll') and resource ('arbitrary dice'), and it distinguishes itself from the many D&D 5e-specific roll tools by explicitly listing them as alternatives. This makes it easy for an agent to know exactly what this tool does and how it differs from 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 provides explicit when-to-use guidance: use this for custom/arbitrary rolls, and prefer the listed dnd5e-roll-* tools for D&D 5e mechanics. It names the alternatives (dnd5e-roll-skill, dnd5e-roll-save, dnd5e-roll-attack/damage, dnd5e-item-use) and the conditions that select them. This is exactly the kind of routing guidance an agent needs.

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