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

With no annotations, the description carries the full burden. It discloses the default lookback (近12個月), adjustable months range (1-120), and that the data is daily close prices. However, it duplicates the schema's months description and does not disclose output format, ordering, timezone, or error behavior — though for a simple read-only historical fetch, this is partially sufficient.

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 two short clauses with no filler. It front-loads the action ('取') and object ('ETF 每日收盤價序列'), and the English sentence adds the Taiwan market context without repeating the full Chinese text.

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?

Without an output schema or annotations, the description should explain what the returned series looks like, but it only says '每日收盤價序列' (daily close price series). It does not mention the structure (e.g., array of date/close pairs), currency, adjusted vs raw prices, or how to obtain a valid ETF code. This leaves important gaps for an agent to call it correctly in an automated context.

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 50%: 'months' is described in the schema, while 'code' is not. The description adds domain context that the code refers to a Taiwan ETF and that months controls lookback (1-120), partially compensating for the undocumented 'code' parameter. It does not specify the code format or expected value type, so the compensation is incomplete.

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 clearly uses a specific verb ('取' / fetch) with a specific resource ('ETF 每日收盤價序列' / daily closing price series), and specifies the market ('Taiwan ETF'). This distinguishes it from siblings like fund_nav_history (fund NAV) and etf_lookup (ETF metadata), even without naming them.

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 intended use case is implied by the phrase 'ETF 每日收盤價序列' and 'Daily close history for a Taiwan ETF,' so an agent can infer when to use it. However, there is no explicit guidance about alternatives or when not to use it, which leaves some ambiguity given the many data-related sibling tools.

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