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 adds the underlying endpoint (GET /users) and the shape of returned records, but says nothing about pagination, result size, or rate limits — modest added context, not rich behavioral disclosure.

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?

Compact and front-loaded: the resource comes first, then the practical hint, then the endpoint. Slightly elliptical phrasing (a bare noun phrase plus fragment) but nothing wasted.

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 read-only list tool with full schema coverage and no output schema, the description covers what entities are returned, their fields, and how to reuse the id downstream. Only pagination/result-limit behavior is unaddressed, which is a minor gap.

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%, so type, with_roles and with_invited are fully documented in the schema — baseline 3 applies. The description's "or customer groups" restates the type enum rather than adding filtering syntax or defaults beyond 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?

Names the resource precisely (agents/admins/collaborators or customer groups) and enumerates the returned fields, so an agent knows what comes back. It omits an explicit verb and does not name the nearest sibling, supportbee_get_user, which is the single-record counterpart — so sibling discrimination is only implied.

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?

"Use the id as assigned_user or user_id" tells the agent why the result matters (feeding IDs into assignment calls), which implies a usage context. However there is no explicit when-to-use statement and no comparison against supportbee_get_user for fetching a single user.

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