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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered; the description adds no behavioral context beyond the annotation. It says nothing about whether the batch is atomic (do all ops fail if one fails), what happens on duplicate idempotency keys, whether deletions are recoverable, or any rate/latency limits — all material for a destructive multi-op writer. It does not contradict the annotations, but it fails to enrich them.

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?

A single front-loaded sentence with no filler or redundancy, which is good structurally. However, for a nine-variant, destructive batch tool, one sentence is undersized rather than tight — there is no waste but also almost no payload.

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?

Given a 0%-covered schema with nine distinct nested operation shapes, no output schema, and destructive semantics, the description should carry substantial weight — batch semantics, idempotency, failure handling, scope per workspace. One sentence covering six of nine change types leaves the agent without enough to invoke this safely.

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% across three top-level parameters and nine nested op variants, so the schema provides names and constraints but no meaning. The description gestures at change categories that loosely map to some op names, but leaves workspace, idempotency_key, quantity vs adjust_by exclusivity, location, allow_backorder/manage_inventory, and the create vs upsert distinction entirely unexplained. It compensates only partially for a very large coverage gap.

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 verb plus a list of mutable resources (prices, inventory, status, details, variants, organization), so the general purpose is readable. But it never says this is a batched multi-operation dispatcher driven by the 'ops' array, and it omits create_product, delete_variant and upsert_shipping_option even though the schema supports them. It also does nothing to distinguish itself from the sibling commerce_draft_apply — the live-vs-draft distinction has to be inferred from the name.

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?

There is no statement of when to use this versus commerce_draft_apply or commerce_get, both of which appear in the sibling list. For a destructive tool that has a draft counterpart, the absence of any 'preview in draft first' guidance or prerequisite (workspace resolution, confirmation) is a real gap.

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