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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-redundant context — output units (points, VND, share volume) and the fact that intraday values are realtime — but says nothing about session boundaries, caching, rate limits, or how composite parts behave when a sub-dataset is unavailable.

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?

Labeled, front-loaded structure (content enumeration → Dùng khi/Không dùng khi → Tham số → Kết quả → Xem thêm) with no filler sentences. The opening enumeration is long, but every item is a distinct return component the caller needs, so it earns its place.

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 and only two optional parameters, the description carries the full burden and does so: it describes return content, units, realtime-vs-historical behavior, defaults, sibling alternatives, and pointers to complementary tools. An agent can call this correctly without any other information.

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%, so the baseline is 3, but the description adds a nuance the schema omits: for a past as_of date the points and P/E–P/B reflect that specific session, and it repeats the index defaults/alternatives (VNINDEX, VN30, HNX, UPCOM). That is a meaningful addition over the schema text for the historical-date case.

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 ('toàn cảnh thị trường chứng khoán Việt Nam trong MỘT lượt') and then enumerates exactly what the single call returns: index points, % change, P/E–P/B, top gainers/losers, technical breadth, top RS codes, matching signal combos, market-wide foreign flows, derivatives contract, and session summary. This is enough for an agent to distinguish it from the many narrower siblings (get_quotes, get_price_history, get_technical_signals) without opening schemas.

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 explicitly states trigger phrases ('thị trường hôm nay', 'VN-Index thế nào', need for context before analyzing a ticker) and an explicit 'Không dùng khi' clause routing agents to get_price_history for price series and to get_foreign_flows_detail for per-ticker foreign flows. When-to-use, when-not, and alternatives are all named.

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