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

Annotations declare readOnlyHint=false, so the tool is expected to have side effects (e.g., chat posting), but the description does not elaborate on those side effects. It does add value by disclosing that isCritical/isFumble reflect critical success/failure, which is not in the schema or annotations. Since annotations already cover the mutation aspect partially, the description provides some extra context but not rich behavioral detail.

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 two short sentences with no filler. The key scope constraint 'PF2e only' is front-loaded, followed by the action and a note on criticals. Every phrase contributes to understanding the tool.

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 simple roll tool with two well-documented parameters and no output schema, the description covers the essential aspects: the system, the action, and the critical handling. It does not mention prerequisites beyond actorId, but those are implied by the schema. The description is slightly limited by not stating what happens when showInChat is false (which is the default), but the schema covers that. Overall, it is nearly complete for its simplicity.

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?

The schema already provides descriptions for both parameters: actorId is sourced from actor-list/actor-filter, and showInChat has a clear boolean meaning. The description does not add any additional parameter-specific information beyond what the schema offers. With 100% schema coverage, the baseline of 3 is appropriate; the description does not need to compensate but also does not exceed the schema.

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 verb 'Roll' and the resource 'Perception check', combined with 'PF2e only' which distinguishes it from the generic roll-perception and other system-specific roll tools. It also mentions isCritical/isFumble, which clarifies the expected output behavior. This makes it unambiguous what the 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 begins with 'PF2e only', providing a clear system context for when this tool is appropriate. However, it does not explicitly mention when to avoid it or name alternative tools like roll-perception or pf2e-roll-skill, leaving some inference to the agent. The condition is clear for PF2e perception checks, but not exhaustive.

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