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

Annotations already declare readOnlyHint=true, so the safety profile is covered; the description reinforces this and adds substantive value by disclosing the shape of each returned record (amount, created_at, manual status, linked registration). It does not describe pagination behavior, but that is documented in the schema.

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?

Two sentences with zero padding: the returned-fields summary comes first, followed by the read-only constraint and the underlying endpoint. Everything is front-loaded and every clause earns its place.

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, describing the fields returned is exactly what the description should supply, and pagination plus slugs are fully covered by the schema. Minor gap: it doesn't mention paging defaults or result ordering, which an agent might want when iterating.

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% with four well-documented parameters (event_slug, account_slug, page, page_size), so the schema carries the semantic load. The description adds no parameter-level detail, making the baseline 3 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?

States a specific verb and resource ('List the refunds recorded for an event') and enumerates the returned fields (amount, created_at, manual flag, registration), which is more than a restatement of the name. No sibling tool handles refunds, so the scope is unambiguous among the listed tools.

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?

Gives clear context for when the tool applies (retrieving refunds for an event) and adds a useful negative boundary: 'this server never issues refunds.' It stops short of naming an alternative for issuing refunds or stating prerequisites, so it isn't a full when/when-not pair.

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