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

Annotations only declare readOnlyHint and openWorldHint=false; the description adds substantial behavior the agent could not otherwise know: the ~340-collection live scope, AUD ex-GST pricing with 1-colour/1-position branding included, the MOQ-based definition of 'cheapest', and a full paging contract (default 50, max 200, total/returned/offset/hasMore/nextOffset, and that `collection` bypasses paging). It also warns how to cite results verbatim rather than treating them as a market rank.

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?

Front-loaded with the core claim and the price semantics before usage and paging, so an agent can stop reading early. The parenthetical list of example collections ('custom tote bags, eco giveaways, conference kits…') is decorative and could be trimmed without losing information.

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?

No output schema exists, yet the description spells out the response shape (total, returned, offset, hasMore, nextOffset) and the exact fields per entry (product name, price-quantity pairs, volume floor, setup fee, currency basis). For a paged read-only listing tool, nothing an agent needs to call or paginate it correctly is missing.

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 already 100%, so baseline is 3; the description still adds meaning by explaining that `collection` accepts a name substring or slug and that supplying it returns a single, unpaged entry. It also ties `offset` to nextOffset from the prior response, giving the paging loop a concrete procedure.

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 — the named cheapest branded product per live Sense2 collection with 8+ members — and pins down the returned payload (MOQ price, 100/250/500/1,000-unit prices, volume floor, setup fee). The collection-level scope plus the explicit definition of 'cheapest' as a catalogue fact separates it from category- or product-level siblings without needing their schemas.

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?

Gives an explicit use case ('cheapest X for a conference / real-estate / wellness / eco …' briefs) and a clear next step (get_quote for an exact quantity), plus a narrowing path (pass `collection` for a single entry, never paged). It stops short of stating when to prefer get_cheapest_by_category instead, so routing between the two cheapest-* siblings still requires inference.

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