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

Annotations already carry readOnly/destructive/idempotence hints, so the description only needs to add behavior beyond safety. It does so by clarifying that the tool deliberately omits WHOIS/ownership data and by describing the splitting operation. It does not discuss invalid-hostname behavior, but that gap is minor for a read-only shape 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?

One sentence, front-loaded with the operation and immediately followed by the scope limitation. No filler or repetition of schema content.

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 simple read-only label-splitting tool, the description covers the core behavior and the output concept (labels) despite no output schema. It leaves edge-case behavior unspecified, but the schema's per-parameter discard notes and the low complexity make this acceptable.

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 already describes all properties, including 'host' as 'Public hostname', so the description adds little parameter-level meaning. It aligns 'hostname' with the host parameter but does not explicitly state which property to populate or that other fields are ignored.

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 names a specific verb ('Split'), a concrete resource ('a hostname'), and the product ('labels'), while the qualifier 'without WHOIS or ownership data' sets the scope boundary. This distinguishes it from sibling shape/URL tools without opening the schema.

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 description implies usage for pure label extraction by stating what it does not include (WHOIS/ownership data), but it does not state when to choose this tool over alternatives or name a sibling tool. The when-not is present only by implication.

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