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

With annotations declaring write/destructive/idempotent, the description still adds useful behavior: the update is narrowly scoped ("Nothing else on the product changes"), a read-then-confirm workflow is required, and the store tax setting determines which price field matters. It does not address failure modes or permissions, and the scoped-PATCH phrasing sits in slight tension with destructiveHint=true, though it is a clarification rather than a contradiction.

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?

Four short sentences, front-loaded with the WRITE marker, then the value format, then the scope guarantee, then the workflow. Nothing is redundant and the endpoint is appended as a trailing technical note rather than cluttering the lead.

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 mutation tool with annotations covering safety and idempotency and full schema descriptions, the description supplies the missing operational context: value format, field exclusivity, scoping, and read-before-write. The only real omission is any mention of loyalty_amount and of what the response returns, though no output schema exists to lean on.

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 baseline is 3; the description goes beyond it by explaining the either/or semantics of price_excluding_tax versus price_including_tax and that the store's tax configuration determines which the till uses. It does not mention the optional loyalty_amount parameter at all, leaving that one to the schema alone.

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?

"WRITE: set the selling price of one product (variant)" gives a specific verb, a specific resource, and an explicit scope limit (one product, price only). "Nothing else on the product changes" plus the PATCH endpoint line separates it cleanly from siblings like set_product_stock and update_customer.

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?

It states prerequisites clearly: "Read the product first and confirm the new price with the user," which tells the agent both to call get_product beforehand and to seek confirmation. It also advises setting only one of the two price fields and explains the tax-setting decides which is used. It does not explicitly name alternative tools (e.g., set_product_stock) for adjacent price/stock edits, so it stops short of full routing guidance.

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