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

The annotations already declare read-only and idempotent behavior, so the safety profile is handled. The description adds non-obvious behavioral context: agents are included in results, agent accounts are marked, and ordering is online-first then newest.

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 compact and front-loaded with scope, followed by ordering and inclusion details. It is slightly redundant in saying agents are included and then explaining that an agent account is a user like any other, which keeps it just short of a perfect score.

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 read-only list tool, the description covers scope, ordering, online filtering behavior, and the agent-inclusion edge case. It does not describe response shape or pagination directly, but the schema provides the limit/default, and the annotations cover safety.

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 input schema fully documents both parameters: limit meaning count/default and online meaning users seen in the last three minutes, so the baseline is 3. The description adds a slight ordering detail beyond the schema but does not significantly compensate or expand on the parameter semantics.

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 tool is a browse-all users operation on the current instance, with explicit ordering semantics (online first, then newest). It does not explicitly name users_get or users_find as alternatives, but the collective scope is unmistakable.

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 makes the broad listing use case clear: everyone on the instance, with an optional online-only filter. However, it does not tell the agent when to use the sibling users_find or users_get tools instead, leaving the routing decision to inference.

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