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

With no annotations, the description carries the full burden of behavioral disclosure. It does disclose one meaningful boundary: the tool does not retrieve WHOIS or ownership data, implying a local parsing operation. However, it does not state whether it mutates anything, how it handles invalid hostnames, or what exactly the returned labels look like.

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 a single short sentence with no filler and the key operation is front-loaded. It could arguably go further to clarify parameter usage, but as a concise definition it is appropriately sized and easy to parse.

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 input schema is quite rich, including ref, url, city, feed, json, path, and host, but each parameter already has a description explaining whether it is discarded. The description itself describes the output concept ('labels') but does not specify the exact return structure or edge-case behavior, leaving minor gaps.

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 covers all eight parameters with descriptive text, so the baseline is 3 even though the description itself mentions no parameters. The description does not add meaning beyond the schema, such as explicitly mapping 'hostname' to the host parameter, but the schema's 'Public hostname' description is sufficient.

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 uses a specific verb and resource: 'Split a hostname into labels.' The negative clause, 'without WHOIS or ownership data,' adds clear scope and distinguishes this from any lookup-style or ownership-bearing domain tools. This is more than a vague restatement of the tool name.

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?

There is no explicit guidance about when to use this tool versus alternatives such as github-repo-shape, jira-key-shape, or normalize-url. The phrase 'without WHOIS or ownership data' hints at what it avoids, but it does not name any alternative or condition under which the agent should prefer another tool.

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