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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely useful behavior: the three status values, that LOI refunds points, that XONG returns a full review shape with K2 NEED_FACTS / HO_SO_THIEU_DU_KIEN lines, and the cost model. It does not cover result expiry or polling cadence, so it sits at a solid 3 rather than higher.

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 same content is delivered twice, once in English and once in Vietnamese, which doubles length without adding information. The opening sentence is also corrupted by the 'maLuot:' splice, hurting front-loading. Under-specification is not the issue; redundancy and mangled structure are.

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 single-parameter read tool with no output schema, the description supplies the status vocabulary, the refund behavior on failure, and the shape of a completed result, which is most of what an agent needs to interpret the response. Missing only lifecycle details such as retention or retry timing.

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 carry the parameter meaning; it does identify maLuot as the 'mã lượt biên nhận' (receipt/turn code) for a background run, which is more than the bare string schema. It gives no format, sourcing guidance, or what to do when the code is unknown, so it only partially compensates.

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 and resource: retrieves the state and full result of a background declaration code check, keyed by receipt code. This is distinguishable from the sibling kiem_ma_to_khai (the likely initiator), though it never names that sibling. The purpose is clear despite the garbled 'receipt maLuot:' splice.

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 is implied rather than stated: the presence of DANG_XU_LY ('still working') signals polling, and the note that it is free with points charged once at the receipt hints at repeated calls. However, it never says when to call this vs kiem_ma_to_khai, how often to poll, or how long results persist.

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