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

With annotations already declaring non-read-only and non-destructive behavior, the description adds important context: it re-queues the job, does not charge again, and attaches facts to the exact lines that requested them. It does not cover permissions or response details, but it meaningfully exceeds what the annotations provide.

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, but the description repeats the same content in Vietnamese, roughly doubling length without adding new information. The duplication weakens conciseness despite the clear initial statement.

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 tool with no output schema, the description covers the triggering conditions, re-queue behavior, no-extra-charge guarantee, and line-specific fact insertion. It is nearly complete, though it omits expected return behavior and detailed boSung formatting.

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 explain the two parameters. It identifies maLuot as the receipt code and boSung as the facts to add, but it does not explain the format, length limits, or expected structure of boSung beyond the general notion of facts for listed lines.

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 names a specific mutation action (adds facts to a background job), the resource (finished-but-incomplete job identified by maLuot), and the exact result states that trigger it (CAN_DU_KIEN, K2 NEED_FACTS, HO_SO_THIEU_DU_KIEN). It clearly distinguishes this repair/re-queue operation from sibling classification and declaration-check 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?

It gives precise when-to-use conditions: after a background job finishes with an incomplete status and the user has answered the listed questions. It does not explicitly name alternatives or when-not cases, but the triggering statuses make the intended context clear.

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