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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description isn't obligated to restate it. It adds real behavioral context beyond the annotations: null means the value is inherited from the site, and a Shopify store has no widget look here because it is set in the theme editor — a non-obvious domain constraint.

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 sentences, no filler, and the content enumeration leads. The opening sentence is a somewhat dense run-on list, but every clause conveys real information about the returned fields rather than padding.

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 an output schema present, the description need not explain return formatting, and it covers the semantic edge cases (null inheritance, Shopify theme constraint) that structured data cannot. Only a slightly clearer statement of the retrieval action itself 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?

The single site_id parameter is fully documented in the schema (100% coverage), including the site_… format and the list_sites source. The description adds nothing about the parameter, so the schema carries the whole burden and the baseline of 3 applies.

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 enumerates exactly what this call surfaces — question count, heading, hint/ask item, and the visual preset/layout/colours/sizes — which clearly identifies it as the read of widget settings. It also names update_widget_settings as the mutating counterpart, so it is distinguishable from its nearest sibling without opening the 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?

The closing clause 'update_widget_settings changes them' establishes the read-vs-write boundary, and 'null is the site's own' tells the agent how to interpret absent values. There is no explicit 'use this when you need X' phrasing or stated exclusion, but the contrast with the update tool gives clear context.

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