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

Annotations cover the safety profile (readOnly=false, destructive=false, openWorld=true, non-idempotent), so the description's real added value is the two-phase async behavior: it may return only a receipt {maLuot, trangThai: DANG_XU_LY} rather than an immediate answer, and legal/GIR citations are quoted verbatim from the backend rather than generated. This is meaningful context the annotations do not 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?

Purpose is front-loaded, but the English and Vietnamese sentences are near-duplicate translations, and the inline JSON receipt fragments add density. Content earns its place, but the redundancy and mixing of two languages in the same field make it heavier than necessary.

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 5-parameter tool with no output schema, the description covers purpose, input constraints, the async return shape, and how results are retrieved — enough for an agent to call it correctly. The main residual gap is the un-described structure of the thongSo object, which the schema leaves undocumented.

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% across 5 parameters, so the description carries the burden. It maps parameters to meaning (tên hàng, chất liệu, công dụng, thông số) and explains what nguonThongSo records plus its ANH/LINK/CHU enum role. It does not describe thongSo's shape as an arbitrary key/value object, so it falls slightly short of fully compensating.

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?

Names a specific verb and resource (suggests Vietnam HS codes for a product) and states the scope (from a text description of name, material, use, specifications). It also differentiates from siblings by declaring what it is not — text-only, no images or marketplace links — and implies results come from a separate lookup (ket_qua_phan_loai) via the turn code.

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?

Clearly states the input context (text description only, not images or links) and the async pattern: a receipt is returned in the gateway's waiting mode and status/results are fetched with the same maLuot. It does not explicitly name a sibling tool to use, so the routing guidance is one step short of a 5.

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