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

Annotations declare a non-read-only, non-destructive, non-idempotent mutation. The description adds meaningful context beyond that: it re-queues the job and does not charge additional points. It still omits auth/error behavior, but the key operational trait is disclosed.

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 English sentence is front-loaded and informative, with the Vietnamese translation duplicating the same content. The duplication is useful for a Vietnamese-domain tool but slightly reduces conciseness.

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 two-parameter mutation without an output schema, the description covers when to call it, what it does, and the no-extra-charge behavior. It could say more about parameter expectations, but is otherwise complete enough to invoke correctly.

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 0%, so the description must clarify both required parameters. It identifies maLuot as a receipt code and implies boSung contains the added facts, but adds no format or length guidance beyond the schema's bare types.

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 action, resource, and triggering condition: adding facts to a finished-but-incomplete HS classification job via receipt maLuot and re-queuing it. The CAN_DU_KIEN condition distinguishes it from sibling lookup/classification 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?

Explicitly says to use it when the retrieved result reports CAN_DU_KIEN and the user has answered the listed questions. It does not name alternative siblings or state when not to use it, but the precondition is clear.

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