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

readOnlyHint=true already signals a safe read, but the description adds real context: the log is immutable, the response is JSON:API shaped, and payloads may reference PII. That PII and immutability detail is the kind of disclosure annotations do not provide. It stops short of noting rate limits or default page sizes.

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?

Four tight sentences front-loaded with purpose, then pagination mechanics, return shape, and the REST equivalent. Nothing is padding; each sentence carries distinct information.

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, the description usefully discloses the JSON:API { data, links } return shape and the PII caveat, plus the pagination model. An agent has everything needed to call and consume this correctly.

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 100%, so the three pagination params are already documented, including the links.next/links.prev relationship. The description reinforces how page_after/page_before map to the response cursor links, which is mildly additive but largely repeats the schema, so the baseline 3 holds.

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 and resource ('List audit-trail events') and defines the scope with a parenthetical (immutable log of actions — inquiry/account/case state changes). This reads clearly against the singular sibling persona_get_event by implying a collection listing.

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 explains how to paginate but never states when to reach for this list versus persona_get_event or the other list_* siblings. Usage is only implied by the tool's obvious listing nature, leaving no explicit selection criteria.

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