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

No annotations are provided, so the description carries the full burden of disclosing behavior. It only says it splits a hostname and that WHOIS/ownership data is not included; it does not explain the return format, whether any network access is involved, or how the other schema parameters interact with the operation. There is no disclosure of side effects, error cases, or the behavior when multiple parameters are supplied.

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, compact sentence that is front-loaded with the core action ('split a hostname into labels') plus a clarifying negative scope ('without WHOIS or ownership data'). There is no filler or repetition, and each clause earns its place. The issue is in what is omitted, not what is included.

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?

Given the high complexity (9 optional parameters, no annotations, no output schema), this description is far from complete. It describes a use case for `host` only, never mentions what the actual return shape is, and leaves `ref`, `URL`, `city`, `json`, `path`, `query`, and `zone` parameters completely unacknowledged. An agent would be able to guess a reasonable use case for a hostname but would be lost for the other 8 inputs, and even for the host case there is no clarity on the split output order.

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 the baseline is 3. The description hints at the `host` parameter through 'hostname', but it adds no extra semantics for the 8 other parameters, nor does it clarify how the splitting operation relates to them. It does not go above the minimum because it offers no meaning beyond the schema.

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 does state a specific verb and resource: 'split a hostname into labels' and the 'without WHOIS or ownership data' qualifier distinguishes it from lookup-style tools. However, the input schema exposes 9 entirely different parameters (ref, JSON, zone, city, query, path, etc.) and the description only addresses the `host` parameter, so it leaves the tool's overall scope ambiguous and misleadingly narrow.

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 a partial usage boundary: the phrase 'without WHOIS or ownership data' implies this tool is for lexical splitting, not domain intelligence. But the description does not name any sibling tool, offer a when-to-use / when-not-to-use contrast, or explain why `domain-shape` is preferable to `github-repo-shape`, `jira-key-shape`, or `normalize-url`.

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