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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real value by disclosing the two response shapes and their exact keys, which matters since there is no output schema. The "Through Royally: read-only, runs straight away" line mostly restates the annotations and adds little.

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 listing/pagination behavior is front-loaded and dense but readable. The trailing site URL and the "Through Royally" sentence are padding relative to the signal in the first two clauses.

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?

With no output schema, spelling out both return shapes is exactly the missing piece an agent needs, and all four parameters are documented. What's left unsaid is minor: whether search combines with pagination and how total_count differs from total.

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 description coverage is 100%, so page, per_page, search and site_id are already documented. The description only reinforces what happens when page is supplied (pagination envelope with totals), which the schema already states, so it lands at the baseline.

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?

States a specific verb and resource ("Get WooCommerce customers") and roughly scopes the return set via per_page. It implicitly separates itself from the WordPress-user siblings (wp_get_users) by naming WooCommerce customers, but never says so explicitly.

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 explains the two calling modes (omit page for a bare array, supply page for a paginated envelope), which is implied guidance on how to call it. It gives no when-to-use vs when-not guidance, and never points at wp_get_users or search-based alternatives.

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