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 genuinely useful behavioral context beyond that: the response is deliberately raw/unprocessed feed data rather than normalized fields, which tells the agent to expect variable shapes. It omits what happens when the product or feed is missing, keeping it at 4.

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?

Two sentences, zero filler, with the payload description front-loaded and the usage guidance following. Every clause earns its place.

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?

There is no output schema, and the description partially fills that gap by describing rawData as the complete set of feed-emitted fields. However, it says nothing about the undocumented feedId parameter or failure behavior for an unknown product id, leaving real gaps for a lookup 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 description coverage is only 50%: productId is documented as "Internal product id, NOT the external g:id," but feedId has no description at all. The description never mentions either parameter, so it does not compensate for the gap — notably, an agent gets no hint about where feedId comes from or whether it must match an existing feed.

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 one product") and specifies the distinguishing payload: the full g:* rawData blob with every field the source feed emits. This clearly separates it from list_products, which an agent would otherwise confuse it with.

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 a concrete use case: "inspect exact field shapes before writing a field rule or code template," which effectively routes the agent away from list_products for this purpose. It stops short of an explicit exclusion (e.g., "do not use for bulk browsing — use list_products"), so it earns a 4 rather than a 5.

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