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

Annotations cover only safety hints (readOnly false, non-idempotent, non-destructive), so the description must and does carry the behavioral burden: poll-only, nothing emailed or called back, bearer token returned, refusal semantics for not-sold-out/unknown stock, and rate-limit/retry behavior. This is well beyond what annotations provide.

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?

Content is front-loaded with purpose, then conditions, then routing, then error recovery, so an agent can stop reading early. It is dense and longer than typical, but nearly every clause (refusal codes, keep-the-token, next step) is actionable rather than 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?

No output schema exists, so the description must describe the return value, and it does ('returns a bearer token to poll or stop it'). Combined with the refusal conditions, token retention guidance, and next-step routing, an agent has everything needed to invoke and follow up correctly.

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 100%, so merchant, product_id, variant_id, and shopping_session_id are already documented. The description adds only a bare example call and no additional parameter-level meaning, so the baseline of 3 is correct.

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 (starts a watch) on a specific resource (one sold-out listing) and names the token it returns. It is easily distinguished from siblings like get_back_in_stock_watch (polling) and stop_back_in_stock_watch (stopping), which the description explicitly references.

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 when-to-use ('Use when a shopper wants to know when a sold-out listing comes back in stock'), explicit preconditions (store itself shows sold out right now), and routes to the alternative states via get_back_in_stock_watch and stop_back_in_stock_watch. Error recovery even maps each failure to its next action.

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