add_monitor

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

With no annotations at all, the description carries the whole burden, and it does disclose useful behavior: empty product_name/shop_name are backfilled by the crawler, site/currency are parsed from the URL, and base_price empty means 'skip'. It does not say whether monitoring starts immediately, what happens on a duplicate URL (idempotency), or what happens when URL parsing fails — significant gaps for a create/mutation tool.

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?

Purpose is front-loaded in one sentence, then user phrasings, then a compact bullet list of parameters — a sensible order. The example utterances are slightly verbose for a definition body, but they earn their place by anchoring invocation intent.

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?

Return values are covered by the output schema, and parameter defaults/fallbacks are well explained. Still missing for an un-annotated create tool are duplicate handling, immediate-vs-deferred crawl behavior, and failure modes on an unparseable URL, which an agent would need before confidently invoking it.

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 0%, so the description must compensate, and it largely does: it walks through all eight parameters, marks product_url as required, lists supported sites (my/th/vn/sg/id/ph/br), and explains the meaning of each optional field. It only omits finer details such as the currency unit for base_price and any valid range for check_interval/alert_threshold.

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?

The first sentence gives a specific verb plus resource ('添加一个新的商品到监控列表'), and it is clearly distinct from read-side siblings like get_monitor_list or get_monitor_overview. An agent can tell this is the creation path for a new monitored product without inspecting any 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?

The '用户可能的问法' examples give concrete trigger conditions and make clear this is the entry point whenever a user supplies a Shopee URL to track. There is no explicit exclusion or routing statement (e.g. what to do if the product is already monitored, or whether to use search_my_products first), so it stops short of a full when/when-not guide.

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