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

With no annotations present, the description carries the burden of behavioral disclosure. It does disclose an important boundary: no WHOIS or ownership data. It does not mention normalization, network behavior, or the fact that most input schema fields are unrelated and discarded, which leaves some behavioral ambiguity for a no-annotation tool.

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, sharply front-loaded sentence with no filler. It states the action, the resource, and the limitation without redundancy.

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 broad and contains seven unrelated fields with no required marker, yet the description does not clarify that only 'host' matters or what the output shape looks like. There is also no output schema and no annotations, so a one-line description is insufficient to guarantee correct invocation. An agent inspecting the schema would have to guess which parameter is actually relevant.

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 has seven properties and all are described, so schema coverage is 100 percent and the baseline is 3. The description adds no parameter-level mapping, though 'hostname' reasonably points to the 'host' field. The unrelated extra fields make the parameter intent somewhat ambiguous, but the schema descriptions themselves are informative enough to avoid misinformation.

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 added scope clause 'without WHOIS or ownership data' clearly distinguishes this from any ownership or lookup-oriented tool. It states exactly what the tool does in one focused sentence.

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 intended use case is implied: use this when you need hostname labels rather than ownership information. However, the description never names alternatives or gives explicit conditions for choosing this over sibling tools like normalize-url, web-fetch, or the other shape tools. It provides a partial exclusion but no real routing guidance.

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