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

With no annotations, the description carries the burden. It discloses that the tool creates a domain, returns the created domain with CNAME targets, and notes a cost of 10 tokens. It does not discuss authentication requirements or failure modes, but it is transparent about the primary side effect and output.

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 four short sentences, each adding value: purpose, prerequisite/guidance, return info, and cost. No fluff or repetition of schema details.

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 4-parameter creation tool with no annotations, the description covers the prerequisite (get_connected_accounts), key parameter behavior (clerk_instance_id), return value (CNAME targets), and cost. It doesn't explain is_satellite's full implications, but the schema covers the basics, and the output schema handles return format details.

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 descriptions cover all 4 parameters, so the baseline is 3. The description adds extra meaning for clerk_instance_id by clarifying the default-account behavior, which goes beyond the schema. It also clarifies proxy_url's role in satellite domain setups.

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 'Add a custom domain to a connected Clerk instance' with a clear verb and resource. It also distinguishes itself by noting it returns CNAME targets for DNS setup, setting it apart from sibling tools like change_instance_domain or update_domain.

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?

Explicitly instructs to call clerk.get_connected_accounts first and explains how to use clerk_instance_id to target a specific connection or omit it for the default account. This provides clear context for when and how to use the tool, though it doesn't mention alternatives or exclusions.

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