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

Annotations already declare this as read-only, idempotent, non-destructive and not open-world, so the safety profile is covered. The description adds genuinely new behavioral context: 'This only displays choices: STOP and wait for the user before generating or editing', plus the single-candidate vs. multi-candidate interaction difference and the text-only-channel fallback.

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 the core action and return shape, then progression from ambiguity handling to confirmation to channel fallback. It is longer than average but each sentence carries a distinct instruction; a minor tightening of the confirmation sentences would help.

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?

Both parameters are optional and the description covers the no-params case implicitly (search or IDs). With no output schema, it still describes what is returned (names/photos as choices) and how to render them per channel, plus the crucial wait-for-user stop condition — nothing an agent needs to call this correctly is missing.

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?

With 0% schema description coverage, the description must carry parameter meaning. It clarifies the two mutually exclusive modes (free-text search vs. 1-6 IDs sourced from list_products) and the 1-6 count matches the schema's maxItems, which is useful. It does not explain the 'shopify-'/'feed-' ID pattern or the 200-char search limit that the schema encodes without prose, so a small gap remains.

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: 'Show products from the user's connected Shopify store or website/feed as selectable cards with reference photos.' It also implicitly distinguishes itself from list_products by naming that tool as the source of IDs rather than a competitor, so an agent knows this one presents choices while list_products enumerates them.

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?

Explicit when-to-use conditions: ambiguous product/reference or a likely match needing confirmation; explicit when-not: 'When the user already clearly confirmed a product, use that selection without asking again.' It also routes the agent to list_products for supply IDs and gives channel-specific instructions for text-only surfaces.

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