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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds genuinely new context: ordering (newest first, open rotation included), DLC exclusion, a one-hour cache, and the fact that searches are computed live rather than served from that cache. It does not warn about payload size or pagination behavior despite returning every skin as {url, name} per rotation.

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 purpose leads and the detail follows in a single dense paragraph; the field enumeration earns its place because no output schema exists. Minor waste: a raw HTTP path (GET /store/rotations/{rotation_id}) is cited instead of the sibling tool an agent could actually call, and the awkward line break mid-backtick fragments the id-format sentence.

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, the description correctly compensates by describing every returned field and its semantics, including null end and null name. What is missing is guidance on result volume and paging for a response that carries every skin icon per rotation, which matters for a default of 50 and a max of 200.

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%, with page, per_page and search all documented including a maxLength and an example, so the baseline is 3. The description restates the search semantics ('only the rotations that sold a matching skin') but adds no format or edge-case detail beyond the schema, and says nothing about how paging interacts with the newest-first ordering.

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 names the specific resource (past item-store rotations) and the elaboration makes the returned shape concrete: newest-first weekly rotations including the open one, with a defined id format and DLC exclusion. It implicitly separates itself from the current-store and single-rotation siblings via the word 'Past' and the pointer to full item lists, but it never names those sibling tools, so an agent must infer the distinction.

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 'search' behavior is anchored to a concrete user question ('when was X in the store?'), which tells an agent exactly which situation calls for this parameter. It also redirects to another surface for full item lists, an implicit when-not. It stops short of naming get_item_store or get_store_rotation as alternatives, so the routing decision against siblings is left to inference.

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