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

Annotations already declare readOnly, idempotent, closed-world, non-destructive behavior, so the safety profile is covered. Beyond that, the description adds genuinely new behavior: a hard cap of 8 returned items, the return components (short excerpt, source URL, applicable product version), and an explicit fallback of stating no information exists when no source is found — an important signal about how to interpret empty/low-confidence results.

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 description is short and front-loads the resource and language scope before the return-value details. The Vietnamese and English sentences partially duplicate each other, but the bilingual pairing is deliberate for a Vietnamese-facing tool and the English line adds the 'public' qualifier.

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?

There is no output schema, so the description correctly carries the burden of describing return values (max 8 items, excerpt, source URL, product version) and the no-source fallback. Nothing essential for calling the tool is missing, though a pointer to kb_get_page for full article retrieval would close the remaining gap.

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 100% and both parameters (query, limit) are already documented in the schema with bounds and defaults, so the baseline is 3. The description does add one meaningful semantic note — queries accept Vietnamese with or without diacritics — plus the 8-item ceiling, but it does not explain the query length constraint or how limit interacts with the returned result count beyond the cap.

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 pairs a specific verb ("Tìm"/"Search") with a specific resource ("Trung Tâm Tri Thức SB"/"public Knowledge Center") and states the answer shape (cited excerpts from articles). It is clearly distinguishable from kb_get_page and kb_list_pages by being a query-based search, though it never names those siblings to make the contrast explicit.

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 only implied: an agent can infer this is the tool for keyword/question lookup in the knowledge base. There is no statement of when to prefer it over kb_get_page or kb_list_pages, and no exclusions or prerequisites are given.

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