Update variant

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

With no annotations provided, the description fully carries the behavioral disclosure burden and does so thoroughly: null rejection before any call, the media list being replaced wholesale, the one-video-per-variant rule with its image prerequisite, wholesale replacement of stocks and characteristics, and even an upstream schema documentation bug. These are exactly the kind of non-obvious side effects an agent needs to avoid destructive calls.

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?

The description is dense but front-loads the core purpose and then organizes caveats in a logical order. A few later details, particularly the get_operation_schema correction, are slightly verbose but each sentence adds essential safety-relevant information; no filler is present.

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 no annotations, no output schema, and a nested variant object, the description covers the failure-prone aspects comprehensively: validation behavior, list-replacement semantics, video limits, empty-list semantics, and the authoritative schema source. It leaves no obvious gap that would lead an agent to make an incorrect call.

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?

The input schema only labels 'id' and describes 'variant' as a merge-patch record, but the description adds critical operational semantics: null values are rejected, media/stocks/characteristics replace entire lists, video constraints, and the need to rebuild lists from a fresh get_variant. It also corrects a schema-level prose trap for stocks, giving the agent more than 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?

States a specific verb and resource ('Update an existing variant') and grounds it in a concrete mechanism ('via JSON Merge Patch'), distinguishing it from create_variant, get_variant, and bulk_update_prices. The scope is unambiguous even without the title.

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?

Gives explicit when-to-use guidance ('send only the fields to change') and names the relevant alternative for a specific case ('to clear a price, use bulk_update_prices'). It also tells the agent to rebuild replacement lists from get_variant, which effectively routes to the correct read-before-write workflow.

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