Variants Update

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

Annotations already declare mutation, idempotency, and non-destructiveness; the description adds genuinely useful operational context in the required scope (write_products) and pinned API version. However, the single most important behavioral fact for a 20-param update endpoint — whether omitted fields are preserved or reset, and how additional_fields/inventory_levels interact with top-level stock — is never stated, and no output schema compensates.

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 compact lines with the action front-loaded and the endpoint, scope, and version stacked underneath — no filler. The only minor cost is that the parenthetical field list adds little over the schema.

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?

With 20 parameters, nested objects, no output schema, and openWorldHint=true, the description is thin on what comes back and on partial-update semantics. The full schema coverage and the scope/version disclosure keep it adequate, but an agent still has to guess about request body merge behavior.

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 100% and every parameter, including the nested values and inventory_levels objects, is documented inline with format hints (decimal strings, i18n objects, null = infinite). The description adds nothing beyond naming four example fields, so the baseline of 3 applies.

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 and resource ("Update one variant") and enumerates representative mutable fields, so an agent knows exactly what it touches. "One variant" implicitly signals this is the single-record counterpart to the batch siblings, but no sibling is named explicitly, keeping it short of a 5.

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?

Usage is only implied by the word "one" — an agent can infer that bulk edits belong to tiendanube_variants_batch_update and stock-only edits to tiendanube_variants_update_stock, but neither alternative nor any exclusion is stated. No guidance on when this is preferable to the batch or stock-specific variants.

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