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

Annotations already establish the safe, idempotent, closed-world read profile, and the description still adds real behavior: only *active* items, newest-first ordering, deduplication so each source item appears once, and cursor pagination bounds. It omits edge behavior such as an unknown/invalid itemId or how a cursor is obtained, so it stops short of full disclosure.

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 sentences, front-loaded with what is listed and its scope, then ordering/pagination, then the depth control. No filler and nothing repeated from the schema except where the number itself carries meaning.

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?

There is no output schema, so return values matter, and the description conveys them: paginated source items with depth-controlled hydration and dedup. Missing are failure behavior for a bad itemId and whether inactive/draft referrers are excluded silently, which matters for a lookup an agent may rely on for integrity checks.

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?

With 0% schema description coverage the description carries the burden, and it does most of it: `depth` is explained as reference hydration (0–3, default 0), `limit` defaults and caps are restated with meaning, and `cursor` is tied to pagination. Only `itemId` is left implicit as 'the target item', and the cursor's opaque round-trip nature is unexplained.

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 (Lists), a precise resource (active items referencing the target item), and the exact mechanism (via `reference` or `multi_reference` fields). The reverse-lookup semantics clearly separate it from siblings like cms_items_list and cms_items_get without needing to name them.

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 when the tool is useful (finding what points at a given item) but never states it as guidance, gives no exclusions, and does not point to any alternative such as cms_items_get or cms_items_list. An agent must infer the selection condition from the semantics alone.

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