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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses a real state machine: DANG_XU_LY, XONG, CAN_DU_KIEN (which returns the questions to ask), and LOI (failed with points refunded). The refund-on-failure and once-per-receipt billing behavior are non-obvious traits that annotations cannot convey.

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?

The four statuses and their meanings are stated twice, once in English gloss and again verbatim in a Vietnamese sentence, adding no new information. The front-loaded English portion is good, but the duplication and language mixing waste roughly half the text.

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?

There is no output schema, yet the description explains what each returned state means and what accompanies CAN_DU_KIEN and LOI, which is the key information an agent needs. It stops short of describing the result payload format or expected wait/retry cadence, but for a single-parameter read tool it is largely complete.

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 carries the burden, and it does identify maLuot as the receipt-turn code ('mã lượt biên nhận'). It adds no format or length detail (the schema imposes 6-100 chars), so it only partially compensates for the empty schema description.

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 description states a specific verb and resource: it retrieves the state and full result of an asynchronous HS classification job keyed by a receipt code. That is clearly distinct from the submission sibling phan_loai_hs, but the description never names that or any other sibling, so the differentiation is inferable rather than explicit.

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?

Usage context is implied (this is the polling counterpart to an async submission) and one genuinely useful usage fact is given: the tool is free and points are charged only once at the receipt turn, so repeated polling is safe. However, there is no explicit 'call this after submitting' or 'do not use for X' guidance.

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