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

Annotations already declare destructiveHint=true, readOnlyHint=false, and non-idempotency, so safety framing is partly covered. The description adds the human-confirmation gate, which is valuable workflow context for a bulk deletion. It still omits blast radius (does it remove every orphan on the site in one call?) and irreversibility, which matter for a destructive maintenance operation.

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?

Two sentences, zero filler, and the destructive action is stated first with the confirmation constraint second. Every sentence contributes information the agent needs.

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 destructive bulk cleanup with no output schema and no annotation detail beyond the flags, the definition should clarify scope (all orphaned variations on the given site) and whether the caller can preview affected rows. The confirmation gate is covered, but impact magnitude and result reporting are left to inference.

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?

Both parameters are fully described in the schema at 100% coverage, including site_id's requirement to call list_sites first and not to pass a URL or post ID. The description reinforces confirm=true but adds no new meaning about how site_id scopes the deletion (per-site only, or cross-site). Baseline 3 applies when the schema carries the semantics.

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?

"Delete product variations whose parent no longer exists" gives a specific verb, resource, and a discriminating condition, which in practice separates it from wc_delete_product_variation (single, known variation). It does not name that sibling, so an agent must infer the distinction from the orphan criterion alone rather than from an explicit contrast.

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 second sentence gives a clear procedural rule: only pass confirm=true after asking the user. That is real usage guidance, but it is limited to the confirmation gate; there is no statement of when to prefer this tool over manual/single-variation deletion, or of any prerequisite state (e.g., orphaned variations must exist, or a database check should run first).

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