Add To Cart

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

Annotations already declare the mutation/idempotency profile, but the description adds real behavioral context beyond them: the pre-write refresh of cart, price, inventory and both limits, the read-back after writing, and the guarantee that a retry with the same plan_id inspects rather than resends.

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 short sentences, front-loaded with the action and its gating condition; the retry/idempotency caveat follows immediately. No filler.

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?

For a single-parameter write with an output schema, the description covers everything the agent needs: approval requirement, what is refreshed beforehand, and the safe retry protocol. Return values are correctly left to the output schema.

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 0% (only a hex pattern), so the description must carry the meaning of plan_id — and it does, framing it as an approved add plan whose reuse is what makes retries safe. It does not explain where a plan_id comes from, which keeps it from a 5.

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 ('POST one new seller offer') plus its gating input ('an approved add plan'), which cleanly separates it from prepare_cart_change and update_cart_item in the sibling list.

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 explicit preconditions ('approved add plan', 'Never call without user approval') and a narrow retry rule tied to the same plan_id. It stops short of naming the sibling that produces the plan (prepare_cart_change), leaving that linkage to inference.

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