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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new behavior: a bounded set of 3-8 items, ordered best-first, delivered as screenshots rather than raw data, each annotated with a short rationale. That is meaningful disclosure for a tool with no output schema, though it does not say what happens if fewer than 3 suitable references exist.

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?

A single dense sentence that front-loads the action and layers format, ordering, and rationale without a wasted word. Nothing needs restructuring.

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 no output schema, the description usefully characterizes the return value, and annotations handle safety. However, it omits how refs are sourced and does not reconcile the stated minimum of 3 with the schema's minItems of 1, leaving an agent uncertain about valid inputs.

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 0% for a single nested parameter, so the description has to carry the load. It clarifies the count (3-8, though the schema allows as few as 1) and the note field ('one-sentence note', matching maxLength 160), but never explains what a 'ref' string is or where to obtain one, which is the crux of calling this tool correctly.

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 gives a specific verb and resource ('Show ... Lookbook references') plus the presentation form (a gallery of screenshots, best first, each with a one-sentence note). It does not explicitly distinguish itself from search_design_references, so an agent must infer that this renders a curated set while the sibling searches, but the intended output is otherwise unambiguous.

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: 'why it suits this store' signals a presentation/curation step after references have been selected, but there is no explicit when-to-use, no prerequisite (e.g. that refs come from search_design_references), and no stated exclusion against the sibling search tool.

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