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

Annotations mark this as a non-destructive, non-idempotent write with no open-world access; the description adds genuinely new behavior context by disclosing that it is "Free," that it doubles as a read when called empty, that updates are partial ("send only the fields to change"), and that it returns the saved look. It does not say what happens to fields omitted from a partial update or how reference-image replacement/removal interacts, which is the remaining gap for a non-idempotent write.

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?

Front-loaded with purpose, then scoping, then the read/write instruction, then a compact worked example — no filler sentences. The middle clause about brand kits and "own: false" is dense and slightly convoluted, but it is information-dense rather than redundant.

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 an 11-parameter, dual-mode tool with no output schema, the description covers purpose, mode selection, scoping, cost, and a return hint ("Returns the saved look"). Missing are the merge semantics of omitted fields and any detail on the reference-photo/remove_reference interplay, but neither is fatal for correct invocation.

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 coverage is already 91%, so baseline is 3; the description earns above that by explaining the scoping semantics of brand_kit_id (a brand without a look, and a brandless set, fall back to the account look) and by tying the fields together into a worked example with backdrop_color and ratio. It leaves several fields (remove_reference, reference_image_base64, faces, skin_tones) to the schema alone, which is reasonable given the high coverage.

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 pair and resource ("Shows or changes the store look") with the domain it applies to (shopify-pack images), and scopes it per brand kit vs. account-level look. An agent can distinguish this from list_brand_kits / save_brand_kit / delete_brand_kit without opening any 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?

Explicitly gives the two calling modes: "Call without fields to see it; send only the fields to change," which tells the agent exactly how to make this a read vs. a partial write. It also explains the brand_kit_id selection rule and the account-level fallback. It stops short of naming sibling alternatives (e.g. save_brand_kit) for related look/brand operations.

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