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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond that: each result yields a screenshot, live URL, a DESIGN.md covering colors, fonts, sections, motion effects, data-source terms, and photo credits, plus MIT-0 licensing. It does not mention result limits, pagination, empty-result behavior, or whether slug bypasses tag/query.

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 resource and the intent are front-loaded in the first few words, and the second sentence is a tight usage/licensing note. The first sentence is a run-on with a deeply nested list of deliverables (screenshot, URL, DESIGN.md, sources, credits, prompt), which is dense but each element carries information.

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 must carry the return-value burden, and it does: it enumerates exactly what a template card contains, including the DESIGN.md contents and licensing. Missing are result-count/pagination behavior and filter precedence for a 3-optional-param tool, but these are minor for a read-only lookup.

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 100%, so tag, slug, and query are already documented with examples in the input schema. The description mentions template categories that loosely hint at tag values but adds no filter semantics, no precedence rules, and no guidance on free-text query behavior beyond the schema. Baseline 3 is appropriate.

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 identifies the resource precisely ('Free live website templates built from open data') and enumerates example categories (dashboard, weather app, gallery, museum, finance), so an agent knows what kind of result set it gets back. For a find/catalog tool, the verb itself is only implied by the name rather than stated, and the closest sibling, design_recipe, is not named or contrasted.

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?

'Use them as design references or starting points; the code is MIT-0' tells the agent the purpose and the licensing constraint, which is stronger than most catalog tools. However, it gives no explicit when-not guidance against siblings such as design_recipe, find_assets, or find_photos, and no explanation of how the tag, slug, and query filters should be combined.

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