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

No annotations are provided, so the description carries the full burden. It helpfully discloses the mechanical historical method, the two yield views, and a non-advice disclaimer, but omits operational traits such as data source, update cadence, and limitations of the estimate.

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?

One dense sentence plus a short disclaimer, front-loaded with the tool's category and purpose; no filler. The bracket tag adds context efficiently, though it is slightly cryptic.

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 one-parameter, annotation-free estimation tool with no output schema, the description gives the scope, calculation basis, outputs (range and yield comparison), and a disclaimer. It could say more about return format and data sources, but it is sufficient to call correctly.

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?

The schema already documents the sole optional code parameter with 100% coverage ('ETF 代號；不填回傳全部'), and the description adds no additional parameter semantics. Baseline 3 applies when schema coverage is high.

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?

Names the specific action (estimate) and resource (high-dividend ETF 2027 dividend range and yield), states the method (mechanical extrapolation from historical dividends) and universe (Taiwan/US themes and high-dividend). It does not explicitly contrast with the sibling get_etf_dividends, which returns actual dividends, so sibling differentiation is implicit rather than stated.

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?

Implies use when a user wants a forward-looking 2027 dividend estimate rather than actual payout history, but it never states when-not-to-use or names get_etf_dividends as the alternative for historical data. Usage is inferable but not explicit.

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