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

Annotations already cover read-only, idempotent, non-destructive, closed-world, but the description goes well beyond: missing ids are returned in `missing` and are never an error, cross-dataset products are permitted, checked dates are attached, and fees are deliberately not aggregated. These are behavioral traits no annotation could convey.

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-loads what the tool is, then enumerates the return shape, then the edge cases and pricing caveat. Dense but every clause carries information an agent would otherwise have to discover by calling it.

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, yet the description names every returned field (compared, missing, note, tools and per-record contents). Combined with the fee-separation caveat and the 2–6 limit, an agent has everything needed to call and interpret the result.

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?

With one parameter and 100% schema coverage, the schema already documents the array and its 2–6 bounds. The description adds provenance for the values (list_tools or search_limits output) and confirms a plain product name is acceptable, which is more than the schema states.

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 (read-only compact comparison) plus explicit scope: 2 to 6 products. The multi-product framing inherently distinguishes it from get_tool (single record) and search_limits, so an agent can select it without inspecting 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?

Gives clear context for invocation: products may come from different datasets, and ids come from list_tools or search_limits. It also warns that platform fees and pass-through costs stay as separate rows and must be summed by the caller. It stops short of explicitly excluding the single-product case (get_tool) or naming a when-not-to-use condition.

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