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

Annotations declare read-only/idempotent/non-destructive, and the description goes well beyond them: duplicate ids are ignored, unrecognized ids are surfaced in not_found while the remaining valid ones are still compared, and fewer than two recognized products returns an error. That partial-failure and error semantics are exactly the behavioral detail an agent needs before calling.

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?

Dense and front-loaded on the trigger, with ids semantics and error handling folded into parenthetical clauses in a single compact paragraph. Slightly run-on, but every clause carries information an agent would otherwise have to infer.

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?

An output schema exists, so return rendering need not be explained, and the description covers the remaining gap: input provenance, dedupe behavior, partial-success reporting, and the minimum-id error. Nothing needed to invoke it correctly 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?

Schema coverage is already 100%, so the baseline is 3, but the description adds meaning the schema does not: ids come from find_products, product links are also accepted, and the 2-4 bound is framed as a hard constraint tied to the error behavior.

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+resource ('compare two to four teas.co.uk products') with the compared attributes enumerated (strength, caffeine, price per cup, pack size, brewing) and the presentation format (side-by-side table). It also explicitly contrasts itself with get_product, so an agent can route correctly 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?

Gives an explicit trigger ('whenever someone wants to compare...'), names the prerequisite tool (find_products) for resolving names to ids, and names the alternative for single-product questions (get_product). When-to-use and when-not-to-use are both covered.

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