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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds the non-obvious behavioral facts that the default response is 10 condensed rows without rawData, and that includeRaw is expensive on the context budget. It doesn't describe pagination metadata (total/hasMore), which is a remaining behavioral gap.

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 resource and return shape, then the id distinction, then parameter guidance — a sensible order with no filler. The final sentence is a dense run-on carrying three separate ideas (pagination, includeRaw, rule-writing), which slightly hurts scannability.

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 carries the burden of describing returns, and it does: a page of products, both ids, condensed rows by default. The one missing piece is how pagination terminates or whether a total count is returned, which matters for a paginated list tool.

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 50% (limit and includeRaw documented, feedId and offset bare), and the description compensates by explaining the pagination pairing of limit/offset and expanding on what includeRaw actually returns. It adds real meaning beyond the schema for the two most consequential parameters.

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 ('returns a page of products from the feed') and immediately disambiguates the two identifier fields, noting that externalId is what render URLs and preview_render use. This is enough for an agent to distinguish it from get_product (single item) and from the render/preview siblings without opening a 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?

Gives concrete usage guidance for parameters: use limit/offset to paginate, and set includeRaw=true specifically when you need the raw g:* field names for writing a rule. It does not explicitly state when to prefer this tool over get_product or how to detect the last page, so it stops short of full when/when-not guidance.

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