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

Annotations only declare destructiveHint=true and readOnlyHint=false; the description adds the real behavior behind that — 30-day retention, 2-24h refresh cadence capped by plan, that action=stop removes items from the tracked list, and that no e-mail alerts are sent. It leaves one gap: whether historical time-series data survives a stop, which matters given the destructive flag.

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-loaded with the core behavior, then result-reading path, then the stop action, then trigger phrases and caveats — a logical order with no filler sentences. Minor redundancy: 'Amazon marketplaces only' repeats what the marketplace_id description already says.

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?

With no output schema, the description correctly tells the agent where results live (list_tracked, product_dossier) and covers retention, cadence and scope. Still missing a note on capacity/plan limits on how many ASINs can be tracked and on re-tracking an already-tracked ASIN, both of which affect correct invocation.

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 75% and the schema already documents asins, interval plan tiers and the marketplace ID map, so the description mostly restates structured data. It does add meaning for action=stop ('removes products from your tracked list') that the bare enum does not convey, but adds nothing for interval selection or multi-ASIN limits.

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 (keep Amazon products on live refresh by ASIN) and enumerates exactly what is re-read: buy-box price, buy-box seller, stock state, offer count, retained 30 days as a time series. It also distinguishes itself from readers by naming list_tracked and product_dossier as the downstream tools.

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 trigger phrases ('track this ASIN', 'watch the buy box on these', 'monitor these competitor listings') and routes to list_tracked/product_dossier for reading results, plus action=stop for removal. It never distinguishes this from adjacent write-ish siblings such as collect_asin_now or watchlist_add, which an agent could plausibly pick instead.

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