台股題材與高股息

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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: the estimate is derived mechanically from historical dividends, and the output is framed as a range rather than a point prediction. It also sets expectations that the result is not investment advice. It does not state permissions or return format, but for a read-only estimation tool this is solid disclosure.

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?

A single front-loaded sentence carries the core purpose, methodology and two metrics, followed by a short disclaimer. No padding, though the disclaimer sentence is marginal.

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 no annotations, the description does describe what gets returned (dividend range plus estimated yield under two methodologies), which is the main thing an agent needs. Minor gaps remain on permissions and precise return structure, but it is largely complete for a single-optional-param read tool.

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% (the single 'code' param documents '不填回傳全部'), so the schema already does the work. The description adds nothing about the code parameter, making the baseline 3 correct.

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: mechanically extrapolating a high-dividend ETF's 2027 dividend range and estimated yield from historical payouts. It goes beyond the name by naming the two yield methodologies (trailing 12-month sum vs latest-period annualized), which lets an agent distinguish it from the sibling get_etf_dividends, though it never routes explicitly against that sibling.

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?

There is no when-to-use guidance and no comparison to the alternative get_etf_dividends, which is the most likely source of confusion. The closing '不是投資建議' is a disclaimer, not usage guidance, so the agent must infer the use case entirely.

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

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

No annotations are provided, so the description carries the full behavioral burden, and it largely does not: nothing is said about permissions, rate limits, pagination, or the default behavior when code is omitted. Read-only-ness is only inferable from the verb 查詢. The only behavioral content is the implied set of returned fields.

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?

A single front-loaded sentence with no filler: the resource, the sample codes, and the returned fields in one pass. Every clause 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?

There is no output schema, but the description compensates by naming the return fields (配息、除息日、發放日), and the single optional parameter is covered by the schema. Missing only the read-only/scope statement and any note on history depth or sorting.

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?

With 100% schema coverage on a single parameter, the baseline is 3, but the description adds genuine value by listing example valid codes (0056、00878、00919、00929、00713、00940), which is not in the schema. It does not restate the schema's fallback behavior ('不填回傳總表'), but the examples make valid inputs concrete.

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 names a specific verb (查詢) and resource (台股高股息 ETF 配息) and enumerates the returned fields (每期配息、除息日、發放日) plus concrete ETF codes, so an agent immediately knows what data comes back. It stops short of explicitly distinguishing this from the sibling estimate_etf_dividend_2027, leaving the actual-vs-estimated distinction to inference.

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: the mention of 每期配息 and specific existing ETF tickers suggests this is for retrieving recorded distributions rather than projections. However, with estimate_etf_dividend_2027 as a sibling, the description never states when to prefer one over the other. No explicit 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.

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

No annotations are provided, so the description carries the full behavioral burden. It implies a read (查詢) and lists the returned data, but says nothing about freshness/latency, rate limits, permissions, or error behavior for an invalid code.

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?

A single front-loaded sentence that lists the returned fields with no filler. It is efficient, though it packs the return-value enumeration rather than leading with the core action.

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 helpfully enumerates the returned fields (close, change, volume, theme, 60-day history), which partially compensates. However, with no annotations it omits any behavioral context an agent would want for correct invocation.

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 100% and the single 'code' parameter is fully documented with an example (2330). The description adds no extra format or constraint details beyond the schema, so the baseline of 3 for a fully covered schema is appropriate.

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 (查詢) and resource (題材股), and enumerates the returned fields (最新收盤、漲跌幅、成交量、所屬題材、近 60 個交易日收盤), so an agent understands it retrieves a single theme stock's data. It does not explicitly differentiate itself from siblings like get_theme_stocks or list_stock_themes, which limits it below a 5.

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?

There is no explicit when-to-use guidance, no prerequisites, and no naming of alternatives among the four sibling tools. The agent must infer that it should be called with a single stock code, but nothing routes it away from get_theme_stocks or list_stock_themes.

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

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 does disclose the shape of the returned data and notes that the classification is accompanied by its source (附分類依據出處), which is useful. It says nothing about data freshness, update cadence, coverage limits, or auth needs, which are the remaining behavioral gaps.

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?

A single dense sentence with the action front-loaded and the returned fields enumerated compactly. Nothing is redundant or padded.

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, and the description compensates well by listing exactly what comes back, including the supply-chain role and the classification source. Combined with the fully-covered enum parameter, an agent has enough to invoke it correctly; only freshness/scope caveats are absent.

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 the single parameter is a fully enumerated 'theme' field. The description only restates that it takes a theme (某個台股題材) and adds no format or selection guidance beyond the schema, so the baseline 3 applies.

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 specific verb (取得) and resource (某個台股題材的概念股名單) and even enumerates the returned fields (代號、名稱、上市或上櫃、供應鏈角色、收盤價與漲跌幅). This clearly separates it from get_stock (single stock) and list_stock_themes (theme enumeration). It stops short of naming a sibling explicitly, so it does not reach the top tier.

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: the single required 'theme' enum makes the intended call pattern apparent, and the description shows it retrieves the constituent list for one theme. There is no explicit when-to-use vs. list_stock_themes guidance, no prerequisite steps, and no exclusions.

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

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

With no annotations, the description carries the full behavioral burden. It usefully scopes the tool to exactly four named AI themes and states it returns constituent counts plus today's change summary, which sets freshness and granularity expectations. It omits ordering, data source, and how the counts relate to per-stock data in sibling tools.

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?

A single front-loaded sentence with zero waste; the theme enumeration is the payload definition rather than filler. Every clause 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?

For a zero-parameter list tool with no annotations and no output schema, the description does say what comes back. However, the presence of get_theme_stocks leaves a real routing ambiguity that the description should resolve, and it says nothing about output shape beyond counts and a summary.

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 tool takes zero parameters, so per the rubric the baseline is 4. There are no parameter semantics to clarify and none are needed.

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 (列出/list) and resource (台股四個 AI 題材) and even enumerates the four themes and the returned fields (成分股數與今日漲跌摘要). A sibling named get_theme_stocks exists, yet the description never clarifies how this differs, so it stops short of full sibling differentiation.

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?

There is no explicit when-to-use guidance and no mention of alternatives such as get_theme_stocks or get_stock. A reader can infer it is a discovery/overview call, but nothing tells them when to prefer this over the closely named sibling.

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