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

Annotations are mostly negative (readOnly false, openWorld false, idempotent false, destructive false), so the description carries useful extra context: the isCritical/isFumble kept-d20 rule and the note that a 20 on the discarded advantage/disadvantage die does not count, plus a minimum module version (v8.5.0+). It does not mention that rolling likely emits to chat or requires an active world/chat context, 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?

Front-loaded with the purpose and the sibling exclusion list before the finer crit/fumble and version details. It is dense and somewhat run-on in the middle clause, but every sentence carries selection-or-invocation value rather than 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 single-parameter, no-output-schema tool it covers routing, the crit/fumble interpretation and a version prerequisite, which is enough to call it correctly. It stops short of describing what a roll returns or where output lands, but with no output schema that omission is understandable.

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?

Only one parameter (formula) with 100% schema coverage and worked examples, so the schema does the heavy lifting (baseline 3). The description nonetheless adds interpretation the schema lacks: which formulas map to crit/fumble outcomes and the 'kept d20' semantics for 2d20kh1/2d20kl1, which refines how the formula argument behaves.

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 arbitrary dice') and immediately scopes it to custom checks, random tables and DM-specified rolls. It explicitly names the sibling family (dnd5e-roll-skill, dnd5e-roll-save, dnd5e-roll-attack, dnd5e-roll-damage, dnd5e-item-use) it is not meant to replace, so an agent can separate it from the D&D 5e rollers without opening a 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?

Explicit when-to-use (custom checks, random tables, DM-specified rolls) and explicit when-not (D&D 5e mechanics route to the named dnd5e-* tools). This is exactly the routing information needed among ~80 siblings, with no inference required.

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