TWSE Open Data (Taiwan Stock Exchange)

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

Annotations are not provided, so the description carries the full burden. It implies a read-only operation via '查看' (view) and places it 'before fetching data', which adequately communicates non-destructive behavior for a describe tool. However, it does not explicitly mention additional behavioral details like return format or potential errors, and there is no annotation context to supplement.

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 a single, well-structured sentence in Chinese. It front-loads the core purpose and then adds usage context, with no redundant words or filler. It earns a perfect score for conciseness.

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 should clarify what the agent receives as a response. It states the tool shows '完整欄位定義' (complete field definitions), which is a reasonable hint, but it does not specify the format or structure of the returned definitions. For a simple describe operation with one fully documented parameter, this is an adequate but not rich description, so a 3 is justified.

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 has 100% coverage for the one parameter, dataset_id, with a helpful description (e.g., '來自 twse_search_datasets 的資料集代號'). The tool description itself does not add parameter-level detail beyond what the schema provides, so the baseline of 3 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?

The description clearly states the tool's function: '查看某個資料集的完整欄位定義' (view the complete field definitions of a dataset). It uses a specific verb (view) and resource (field definitions), and the context '取資料前' (before fetching data) distinguishes it from the sibling tool twse_get_dataset that likely fetches data.

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 description gives clear usage context: '取資料前用來確認要過濾／投影哪些欄位' (before fetching data, use it to confirm which fields to filter/project). It implies using this tool before twse_get_dataset, but does not explicitly name alternatives or state when not to use it, so it falls just short of a 5.

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 provided, the description carries the full burden. It discloses that the tool merges three TWSE datasets and queries in parallel, and explains the failure behavior: '任何一段查不到都會標成 null 並記在 caveats，不會整個失敗' (any missing segment is marked as null and recorded in caveats, not causing overall failure). This adds significant behavioral context beyond the schema.

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 three sentences long, front-loaded with the main purpose, then a key caveat, then behavioral details. Every sentence contributes distinct information without redundancy, making it appropriately concise and well-structured.

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?

Given the absence of an output schema and annotations, the description covers essential context: the high-level output contents, data freshness disclaimer, parallel querying, and error handling with nulls and caveats. This is sufficient for an agent to understand what to expect and when to use the tool, making it complete for its complexity.

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 input schema already provides 100% coverage for both parameters: 'code' includes examples and 'include_realtime' explains its default and extra call. The tool description itself adds no additional parameter details, so the baseline of 3 applies as per the rubric.

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 states the tool's function: '一次取得單一上市 ETF 的完整概況' (obtain a complete overview of a single listed ETF), and lists the exact components (basic info, previous trading day price/volume, periodic investment popularity). It also distinguishes itself from a sibling tool by explicitly directing users to twse_realtime_quote for real-time prices.

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 description provides explicit when-not-to-use guidance: '價量為前一交易日，不是盤中即時；要當下價格請用 twse_realtime_quote' (price/volume is from previous trading day, not real-time; use twse_realtime_quote for current price). This names the alternative tool and clarifies the scope, satisfying the requirement for explicit usage direction.

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 burden of disclosing behavior. It reveals a key behavioral trait—data is returned in full unless filtered—which is valuable. However, it doesn't mention that the operation is read-only, any authentication requirements, or potential errors/rate limits. The warning about scope reduction adds transparency but not comprehensive behavioral coverage.

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 concise—two sentences—with the main purpose front-loaded and the critical warning immediately after. Every sentence earns its place: the first states what the tool does and its capabilities, the second warns about the full-return behavior and directs users to filter. No wasted words.

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?

Given the tool has 6 parameters, a nested object, and no output schema, the description covers the essential context: the potential for huge responses and the necessity of filtering. It also mentions pagination and field projection. It doesn't describe return format or error handling, but the core usage guidance is sufficient for an agent to invoke the tool correctly. Slightly more detail on response structure would make it complete, but it's strong for the complexity.

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%, so each parameter already has a description. The description adds value by explicitly naming code/match/fields and explaining their purpose (narrowing the result set), which reinforces the schema and provides practical usage semantics beyond the bare definitions. This elevates it above the baseline 3.

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 states the tool's function: 取得證交所資料集內容 (get TWSE dataset content), and lists its capabilities (server-side filtering, field projection, pagination). This distinguishes it from sibling tools like twse_describe_dataset (which describes metadata) and twse_search_datasets (which searches for datasets), making the purpose unambiguous.

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 description provides important usage context: each dataset returns the entire set (possibly thousands of rows), so users must use code/match/fields to narrow scope. While it doesn't explicitly compare against sibling tools, the guidance strongly implies when to use this tool (when needing dataset content) and how to use it effectively. No exclusions are given, but the warning about large datasets is practical and directive.

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 burden and discloses key behaviors: ~5-second update interval and the distinction between real-time and previous-day data. It doesn't mention return fields or errors, but for a simple read-only quote tool, this is adequate context.

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 exactly two sentences, front-loaded with the main purpose, and each sentence contributes distinct value: the first states function and update frequency, the second covers data source comparison and parameter guidance. No fluff.

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 tool with only 2 parameters and no output schema, the description covers purpose, usage context, and parameter rules. It doesn't describe the response format, which is a minor omission but not critical for a quote-fetching tool with clear intent.

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 descriptions already cover both parameters at 100%. The description adds practical semantics beyond the schema by specifying that market should be 'tse' for ETFs and listed stocks, and 'otc' for OTC, enriching the enum's meaning.

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 states it obtains real-time intraday quotes with a ~5-second refresh, explicitly distinguishing from OpenAPI's previous-day data. This is unique among sibling tools, which focus on dataset access, not live quotes.

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 gives explicit when-to-use guidance: use this tool when you need current prices, since OpenAPI only has prior trading day data. It also provides concrete market-selection rules for ETFs/listed stocks (tse) vs OTC (otc), covering the main usage decision.

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 behavioral burden. It discloses that the search matches dataset codes, Chinese descriptions, and field names, which is useful. However, it does not mention side effects, rate limits, or response format, leaving some gaps for a search tool.

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?

Three short sentences with no wasted words; front-loaded with the main purpose, followed by usage context and matching behavior. Every sentence 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 simple search tool with rich schema annotations, the description is fairly complete. It implies the output contains dataset_id but does not explicitly describe the return structure, which prevents a 5.

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%, so baseline is 3. The description adds semantic detail by specifying that the query matches dataset codes, descriptions, and field names, enriching beyond the schema's basic parameter definitions.

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 states the tool searches available TWSE OpenAPI datasets, using the specific verb '搜尋' and resource '資料集'. It distinguishes from siblings by noting its role in finding dataset_id before fetching data, setting it apart from twse_get_dataset and others.

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 description explicitly instructs to use this tool before fetching data to find dataset_id, providing clear when-to-use context. However, it does not name alternative tools or list exclusions, preventing a 5.

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