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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description contributes the pagination trait ('paged') and the returned fields, but says nothing about authorisation, scoping to a site, page size, or how the cursor behaves beyond the schema's own wording.

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 compact clauses, front-loaded with what the tool returns followed by the filtering capability — zero padding. It is slightly too telegraphic, dropping the leading verb and an article, which costs a little readability without bloating the text.

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 five optional parameters, no required fields and no output schema, the description carries more burden than it discharges: it gives a partial return-value summary and mentions paging, but never resolves which site is being listed when id is omitted, nor how results are ordered. Adequate for a simple list endpoint, but the ambiguity against list_site_members is unresolved.

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 80%, which sets the baseline at 3. The description names three of the five parameters (plan, status, q) but adds no semantics beyond the schema, and the two it omits (id, cursor) are only obliquely hinted at by 'paged'. The enum for status is undocumented in both places.

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 states the resource and its payload clearly ('Site customers with their plans, status and expiry'), which tells an agent exactly what comes back. However it omits an explicit verb and, critically, does not differentiate itself from the near-duplicate sibling list_site_members, leaving the agent to guess which of the two list tools is intended.

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?

'Filter by plan, status, q; paged' implies how to narrow results, which is a form of usage guidance. But there is no when-to-use vs when-not, no mention of the alternatives (list_site_members, list_membership_plans), and no prerequisite such as needing a site id or selecting a site first.

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