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

Annotations already declare destructiveHint=true, idempotentHint=false, readOnlyHint=false and openWorldHint=true. The description adds real value beyond that by disclosing the Royally human-approval gate — nothing on the site changes until a person approves — which explains the async execution model an agent otherwise couldn't infer. It stops short of covering post-approval behavior (receipt, undo, partial failure when a term name can't be resolved).

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?

Three tight sentences, front-loaded with the action before the input-format detail and the approval caveat. The '(site: demo.royalplugins.com)' parenthetical is boilerplate that duplicates the site_id enum and could be dropped, costing it the top score.

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, human-gated mutation with no output schema, the description covers the action, accepted input forms, and the approval workflow — enough to call it correctly. The one substantive gap is that 'add or replace' never resolves whether existing terms are appended to or overwritten, which matters a lot given destructiveHint=true.

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 75%, and the description meaningfully supplements the terms parameter by mapping input forms to taxonomy kind (slugs for hierarchical like category, names for non-hierarchical like post_tag) — semantics the schema's flat anyOf(int,string) does not convey. post_id gets no explanation, though it is self-evident, and site_id is covered by its enum description.

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 first sentence gives a precise verb+resource+scope: add or replace terms on a post in any taxonomy. That clearly separates it from read-side siblings such as wp_get_post_terms and term-creation siblings such as wp_create_term. What's missing is an explicit sibling callout (e.g. 'to create a new term first, use wp_create_term'), so it lands at a clear-but-not-differentiated 4.

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?

Usage is only implied: attach/bind taxonomy terms to an existing post_id. The description does add a genuinely useful selection rule (use integer IDs, slugs for hierarchical taxonomies, names for non-hierarchical), but it never says when to prefer this over wp_update_post or wp_create_term, and gives no prerequisite checks (does the post exist, must the term pre-exist).

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