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

Annotations already declare readOnlyHint=true, destructiveHint=false and idempotentHint=false, and the description is consistent with them. It adds real context beyond the annotations: prices are computed by the store and equal the product page, only one-time prices at internal/embedded tiers are returned, and a quote_id holds the price for up to 30 minutes — a retention behavior the annotations do not reveal. It stops short of describing failure modes (stale or mismatched full_cut_hash, exceeding item limits).

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 the when-to-use triggers before the input-mode detail; almost every clause carries information (use cases, modes, price provenance, licence limits, quote_id lifetime). The opening sentence is long and chain-loaded with four comma-separated use cases, which slightly slows scanning, but nothing is disposable.

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?

An output schema exists, so return values needn't be spelled out, yet the description still notes that a priced quote returns the total and may carry a quote_id. Combined with 0 required parameters and the explicit 'send items or cut, not both' rule, an agent has everything needed to construct a valid call and interpret the result.

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 100%, so the baseline is 3; the description earns above that by tying parameters to their sources — sku 'from search or fetch', and cut accompanied by 'the full_cut_hash from mogean_count' — which the schema only repeats in isolation. It also clarifies that intended_use 'never changes the price', a semantic point the schema does not state. It does not add field-level guidance for response_format or the tier/brand/state membership rules beyond the schema.

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+resource ('Get the price of a selection') and immediately enumerates the concrete cases it covers: single product cost, totals across several products, geometry add-on, and licence-tier pricing. It explicitly distinguishes itself from the nearby alternative ('instead of reading list prices from a product card') and names the two input modes (catalog items vs. one custom cut), so an agent can tell it apart from mogean_count/mogean_preview without opening a schema.

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 explicit trigger conditions ('use this whenever someone asks what data would cost...') plus the negative case (don't read list prices from a product card). It also routes around unsupported cases: subscriptions cannot be quoted ('Agents cannot quote subscriptions') and redistribution is handled on the store or by sales, with the same restriction repeated for cut licensing.

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