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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety and idempotency are covered without description help. The description does add useful behavioral context by identifying the corpus as a curated, pre-analysed Lookbook rather than a live web search, which corroborates openWorldHint=false. It says nothing about result volume, pagination, or what happens when nothing matches.

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?

Three short sentences, front-loaded with the resource identity followed by query guidance and then the usage cue. Nothing is redundant, though the guidance could be folded more tightly and the middle sentence is easy to misread as a command rather than a description rule.

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 five parameters, two enums, 0% schema coverage and no output schema, the description should explain at minimum what scope selects and what limit does. It leaves the agent guessing on the single most consequential parameter, so it is not complete enough for reliable invocation despite being clear about the tool's overall intent.

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%, so the description carries the full burden for five parameters, and it only addresses 'query' (describe a shopper problem or page element, not a brand). The critical 'scope' enum (site/page/pattern) determines what results even mean and is never explained, nor are industry, pageKind, or limit. This is a substantial compensation gap.

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 names a specific verb and resource: searching Fudge's Lookbook, a corpus of analysed ecommerce stores, pages and patterns. The scope is concrete enough for an agent to know it is a design-reference retrieval tool, but it never distinguishes itself from the closely named sibling show_design_references, leaving the boundary between the two unstated.

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?

It gives a clear situational cue, 'Use when the merchant wants to see how other stores solve something,' plus concrete query-formation guidance ('Describe the shopper problem or page element, not a brand'). There are no exclusions and no named alternative for related lookups such as show_design_references or get_design_guide, so the agent must infer when not to use it.

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