list_users

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds the genuinely non-obvious behavior that results are capped and that truncated=true means the list is incomplete. It stops short of mentioning any pagination mechanism or how to retrieve the remainder, which is the one behavioral gap.

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?

Three short sentences, front-loaded with what is returned, then routing, then the truncation caveat. No filler and every sentence carries an actionable fact.

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 one optional parameter, full schema coverage, an output schema, and safety annotations, the only thing left for prose to carry is the truncation gotcha — and it does. Nothing an agent needs to call this correctly or interpret the result is missing.

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% and the limit param already documents the server default, so the baseline is 3. The description adds meaning by tying limit to the truncation signal, telling the agent how a small limit manifests in the response — a genuine increment over the schema text.

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 Twingate users") and enumerates the fields returned (id, email, name, role, state), so the agent knows exactly what surface it gets. It also names the sibling get_user as the single-record alternative, making the distinction explicit.

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 to browse who is in the network; use get_user to look up one email" gives both the positive case and the alternative route, which is exactly the routing decision an agent needs. The caveat about truncated results further constrains how to use the output, not just when to call.

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