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

Annotations only carry the safety profile (destructiveHint=true, readOnlyHint=false), and the description adds substantial context beyond them: exists-named creates are rejected per-row, updates are append-only, attribute renaming cascades but value renaming does not, rows are independent, max 500 rows, no undo/dry-run, and results do not appear in the cabinet's Recent Imports list.

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?

Purpose and the create/update distinction are front-loaded, and nearly every sentence adds distinct actionable information. It is dense and long for a tool definition, but little of it is filler, with only mild redundancy in the repeated safety/undo emphasis.

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 destructive bulk import with no output schema, the description covers preconditions, per-row failure reporting, failure isolation, limits, irreversibility, and post-call expectations. An agent has everything needed to call this correctly and 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 effectively 0% at the top level, so the description must carry the burden, and it does: it defines the difference between creates and updates, the unique-name rejection behavior, and the append-only merge semantics and cascade rules that no schema description conveys.

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?

The description opens with a specific verb and resource ('Load product attributes and their values') and clarifies scope ('the axes variants are built from'). It explicitly distinguishes itself from the sibling create_option ('For one axis use create_option') and states what it does NOT do ('This creates no products and no variants').

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 names the alternative (create_option for one axis), gives a prerequisite workflow (read get_options first, route existing names through updates), and prescribes a pre-call procedure (show a preview, state exact row count, get explicit yes). When-to-use and when-not-to-use are both explicit.

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