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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds genuinely new behavior: a character ceiling, a literal 'đã cắt' truncation marker in the output, and that source plus product version are returned. That truncation disclosure is exactly the kind of trait annotations cannot express.

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 Vietnamese sentences are front-loaded and information-dense, with the slug source first and the section/truncation caveats after. The trailing English sentence restates the Vietnamese rather than adding content, a small redundancy that costs a point.

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?

With no output schema, the description carries the return-value burden and does so reasonably: text content, truncation marker, source, and product version. For a three-parameter read tool this covers what an agent needs to call and interpret it, with only the max_chars default left unclear.

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 67%; the description adds meaning for anchor ('để lấy đúng một mục') beyond the schema's terse 'Mã mục', and explains the truncation context tied to max_chars. It never names max_chars or its default explicitly, so the third parameter remains only implicitly documented.

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 concrete verb and resource ('Lấy nội dung văn bản của một bài công khai theo slug') and notes the section-level variant via anchor, so it is unambiguous about what is fetched. It points to kb_list_pages for slug discovery, which distinguishes it from the listing sibling, though it never contrasts with kb_search.

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?

The parenthetical '(xem kb_list_pages)' tells the agent where slugs come from, and the anchor clause explains when to fetch a single section instead of the whole article. There is no explicit exclusion against kb_search, so routing guidance is good but not exhaustive.

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