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

Annotations already declare destructiveHint=true, so the write profile is covered. The description goes beyond them by disclosing the authorization scope and the concrete 409 conflict behavior with a quote_ids payload, which is genuinely useful failure semantics for a bulk delete.

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?

Two tight sentences with no waste; the deletion scope is front-loaded and the failure contract follows immediately.

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 need no explanation, and annotations cover the destructive profile. Auth scope plus the 409 quote conflict round out what an agent needs to call it safely; only alternative-routing guidance is absent.

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 0%, so the description must carry the parameter burden. It names the identifier ('by sku') and the plural form implies batch input, but adds nothing about the 1-500 item bounds or accepted sku format beyond what the schema already encodes structurally.

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?

Specific verb+resource+identifier: 'Delete products by sku'. This cleanly distinguishes it from sibling shop.merchant.catalog_upsert (mutate-or-create) and shop.catalog.get/search (reads), so an agent can select it without opening the 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?

States the required scope (catalog:write) and the exact refusal condition (open quote holding a sku → 409 with quote_ids), which tells the agent when the call will fail. It stops short of naming alternatives such as deactivate or upsert, so no explicit when-not/alternative routing.

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