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

With no annotations provided, the description carries the full burden. It discloses the effect (removes bans, restores sign-in), the return value (updated user summaries and total count), and the token cost. Missing details like permissions or error cases, but it remains transparent about the core behavior.

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 concise, organized, and front-loaded. The first sentence states the core action, the second provides usage guidance, and the third covers return value and cost. No wasted words.

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?

The tool has an output schema, so return values need not be described, yet they are briefly mentioned. It covers the prerequisite, instance selection, required parameters, return summary, and token cost. For a simple two-parameter tool, this is complete and well-rounded.

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%, so baseline is 3. The description adds valuable context beyond the schema by explaining that 'clerk_instance_id' comes from 'clerk.get_connected_accounts' and can be omitted for the default account, which is not evident from the schema alone.

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 opens with a specific verb and resource: 'Remove bans from one or more Clerk users, restoring their ability to sign in.' This clearly distinguishes it from the sibling tool 'ban_users' and plainly states the purpose.

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?

Provides concrete usage guidance: 'Call clerk.get_connected_accounts first' and explains how to target a specific connection or use the default account. It does not explicitly contrast with alternatives, but the close sibling is obvious and the prerequisite is clearly stated.

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