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

With no annotations, the description carries full burden. It discloses that the tool returns a risk card with multiple flags and mentions the data source. Behavioral details like error handling are omitted, but for a read-only bulk query this is adequate.

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?

Description is a single, well-structured paragraph. It front-loads purpose, lists output fields, and provides use cases and data source. No redundancy.

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 simple parameter and no output schema, the description sufficiently covers purpose, output contents, and use cases. It hints at an array of risk cards but could explicitly state the return structure.

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% with a clear description. The tool description repeats the schema info without adding new meaning, so it meets baseline expectation.

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?

Description clearly states the tool performs batch due diligence on Taiwanese companies, returning a risk card with specific fields. It distinguishes from individual tools like taiwan_company_risk by emphasizing bulk operation.

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?

Description provides use cases: credit investigation, compliance, supplier list batch checks. It implies when to use (for bulk) but does not explicitly exclude individual queries or mention alternatives.

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 must convey behavioral traits. It discloses the return structure and data source but does not mention aspects like read-only behavior, rate limits, or any side effects. The description is adequate but not comprehensive.

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, with the key action front-loaded ('公司名稱預查／撞名查重'). It provides examples and return info in a few sentences with 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?

For a simple tool with one parameter and no output schema, the description sufficiently covers the purpose, input, output fields, and use case. An AI agent has enough context to select and invoke the tool 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 covers the single parameter 'name' with a clear description. The tool's description adds minimal extra meaning beyond the schema. Since schema coverage is 100%, 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 checks if a proposed company name already exists in Taiwan's registry, including similar names. It specifies the return fields (core, exact, similar) and the data source, leaving no ambiguity about the tool's function.

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 mentions use cases: '創業命名或盡調辨識用' (for startup naming or due diligence identification). However, it does not provide guidance on when not to use this tool versus siblings like taiwan_company_search or taiwan_company_profile, though the specificity of name pre-check implies differentiation.

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 must carry the full burden. It states the data source (inc.com.tw) but does not disclose whether the operation is read-only, any authentication requirements, rate limits, or data freshness. For a tool without annotations, more behavioral context is needed.

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 that front-loads the purpose and lists the key data fields, with no unnecessary words. It is concise and effective.

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 lookup tool with one parameter and no output schema, the description lists the expected return fields, which is adequate. It could mention data freshness or error handling, but the lack of output schema reduces the burden. The description is largely complete given the tool's 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 has 100% coverage for the single parameter 'unified_business_no', and the description repeats that it uses an 8-digit number. The description adds an example but does not provide additional semantics like format validation or typical usage beyond the schema, so the baseline score 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 uses an 8-digit unified business number to retrieve complete Taiwan company registration data, listing specific fields such as name, capital, and status. It is distinct from sibling tools like 'taiwan_company_search' or 'taiwan_company_verify', but does not explicitly differentiate itself.

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 implies usage when you have a unified business number, but provides no explicit guidance on when to use this tool versus alternatives, nor when not to use it. No exclusions or alternative recommendations are mentioned.

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 full responsibility. It discloses the data source (inc.com.tw), mentions sub-string matching for industry, and clarifies county name formatting (use '臺' not '台'). This adds transparency 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 a single well-structured sentence that front-loads the main function and then provides filtering details. It is concise without missing critical information, though it could be slightly more structured with bullet points.

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 low complexity (4 optional parameters, no output schema), the description adequately covers the tool's behavior and usage. It explains the ranking order and filtering, which is sufficient for an agent to decide when to invoke.

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%, but the description adds value by explaining the 'by' enum options (newest/oldest), noting the sub-string matching behavior for industry, and warning about the correct character for 'Taipei'. This enriches understanding beyond the schema.

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 lists Taiwanese company rankings by capital (default), newest, or oldest, with filtering by industry keyword and county. It specifies the data source and gives example queries, making the tool's 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 explicitly states the tool is for answering questions like 'which companies have the largest capital in a certain industry/county?' It does not explicitly exclude alternatives, but the context signals and sibling tool names imply other tools for different queries.

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 provided, so the description carries full burden. It discloses the tool's scope (shareholders, subsidiaries, ultimate parent, group size, connected companies via directors) and data source (inc.com.tw). It also notes '推估最終母公司' (estimated ultimate parent), indicating a non-definitive result. However, it does not address rate limits, authentication, or data freshness.

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 sentence that front-loads the tool's purpose and lists its outputs. It is moderately concise given the complexity, though it could be slightly more structured with bullet points.

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's complexity (multiple relationship types), no output schema, and no annotations, the description provides a good overview of the tool's capabilities and use case. It lacks details on return format, pagination, or error handling, but is adequate for an agent to understand when to invoke it.

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 only parameter, unified_business_no, is fully described in the input schema (8-digit number, example). Schema coverage is 100%, so baseline is 3. The description reiterates '用 8 位統編' but adds no new semantic detail beyond the schema.

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 specifies the tool's function: given an 8-digit business number, it retrieves corporate shareholders, subsidiaries, estimated ultimate parent, group size, and connected companies via common directors. This distinguishes it from sibling tools like taiwan_company_profile (basic info) and taiwan_person_companies (person-centric).

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 states the use case: '查母子公司、集團版圖、關係人用' (for checking parent-subsidiary, group landscape, related parties). It implicitly contrasts with sibling tools (e.g., for simple company info use taiwan_company_profile), but lacks explicit when-not-to-use or alternatives.

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 full burden and excels: it enumerates all checks performed (dissolution, government procurement blacklist, OFAC/UN sanctions, FSC penalties, judicial cases, labor law penalties, environmental penalties) and outputs (risk level, red flags, responsible person, stock price for listed companies). It also cites the data source (inc.com.tw).

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 paragraph that efficiently conveys all necessary information without being wordy. It could be slightly more structured (e.g., bullets), but the information density is high and front-loaded with the core action '查核...'.

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's complexity (multiple risk categories, no output schema, 2 parameters), the description is exceptionally complete: it explains input format, auto-resolution, all checks performed, output elements (risk level, red flags, responsible person, stock price), and data source. No gaps remain.

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 description adds significant value beyond the schema: it explains that the company name can be an abbreviation (e.g., '台積電') and is auto-resolved, and that the two parameters are mutually exclusive ('二擇一'). This helps the agent choose correctly.

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 purpose: checking company risks (due diligence red flags) using an 8-digit unified business number or company name, and returning risk level, red flags, responsible person, and stock price for listed companies. It differentiates from sibling tools like taiwan_bulk_due_diligence (bulk check) and taiwan_company_name_check (name-only check).

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 specifies input options (unified business number or company name with auto-resolution for abbreviations) but does not explicitly state when to use this tool versus alternatives like taiwan_bulk_due_diligence or when not to use it. Usage context is implied but not clearly delineated.

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 describes the return type and data source but does not disclose potential behavioral traits like rate limits or destructive actions. It is adequate for a search tool but lacks depth.

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?

Two sentences, front-loaded with purpose, no wasted words. Extremely 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 tool's simplicity (single parameter, no output schema, no annotations), the description is complete: it explains the purpose, output, next steps, and data source. Minor improvement could be adding behavior details.

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 describes the parameter 'name' with examples, and the description does not add substantial new meaning beyond what the schema provides. Baseline 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 action (search), the resource (Taiwanese companies by name/keyword), the output (list with unified number and responsible person), and distinguishes from sibling by directing to taiwan_company_profile for complete 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 provides clear context for when to use this tool and explicitly mentions the alternative (taiwan_company_profile) to get complete data. It does not explicitly state when not to use, but the guidance is sufficient.

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 discloses the data source (MOEA OpenAPI) and notes it is 'real-time', but does not discuss rate limits, authentication, error handling, or potential side effects. It is adequate but lacks depth for a comprehensive understanding.

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 sentences, front-loaded with the core purpose, and every sentence adds necessary information without redundancy. It is appropriately concise.

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 only one parameter, no output schema, and several similar siblings, the description is sufficiently complete to understand what the tool does and how to use it. It covers data source, use case, and parameter format.

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 single parameter has 100% schema coverage, and the description adds a clear example ('例如 22099131') and specifies the length (8 digits). This adds value beyond the schema, aiding correct usage.

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 uses an 8-digit unified business number to fetch real-time official registration status from the MOEA's OpenAPI, listing specific fields (name, status, capital, etc.). It distinguishes itself from databases by being more real-time, making the purpose specific and 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 implies usage context (checking if a company is still existing or dissolved) but does not explicitly state when not to use it or compare with sibling tools like taiwan_company_profile or taiwan_company_search. Usage guidance is implied but not fully explicit.

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 discloses the data source and return fields but does not mention error handling, rate limits, or behavior on invalid IDs. For a read-only comparison tool, this is adequate but could be improved.

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 sentence with a clear purpose and a list of returned fields. It is concise and front-loaded, with 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's simplicity (single array parameter, no nested objects, no output schema), the description fully explains input requirements and output fields. It includes the data source and intended use case.

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% description coverage, with a single required parameter 'ids' described as '2–5 個公司統編或名稱'. The description adds no new information beyond the schema, so baseline score 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 compares 2-5 Taiwanese companies side-by-side and lists specific data points returned (responsible person, capital, age, status, etc.). It distinguishes itself from sibling tools like company_profile (single company) by focusing on multi-company comparison.

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 implies usage for supplier selection or competitor analysis, providing clear context. It does not explicitly state when not to use or list alternatives, but the sibling tool names (e.g., taiwan_company_profile) suggest appropriate alternatives for single-company queries.

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 must disclose behavioral traits. It states the data source and what information is returned, but lacks details on error handling (e.g., invalid license number) or any restrictions.

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, using two sentences to cover purpose, data source, and a suggestion for prior use. No unnecessary information, but the list of fields could be more 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 simple query nature with one parameter and no output schema, the description adequately explains what the tool returns (list of fields). It mentions the data source, making it contextually complete for typical use.

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 covers the single parameter 'license_no' with a description of its format and source. The tool description does not add additional semantic value beyond the schema, so performance is adequate.

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 purpose: querying drug details using a license number. It lists specific fields like active ingredient, indications, usage, etc., and distinguishes from sibling tool 'taiwan_drug_search' by stating the input source.

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 a clear usage flow: use 'taiwan_drug_search' first to obtain the license number. It does not explicitly exclude alternative uses, but the context is sufficient for an agent to understand when to invoke this tool.

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 provided, so description carries the burden. It indicates a read-like search operation and cites data source, but lacks details on rate limits, result limits, or authentication. However, for a simple search, this is adequate.

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?

Two sentences with no fluff. Purpose is front-loaded, and additional guidance is concise. 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 one-parameter search tool with no output schema, the description provides complete context: what it does, what it returns, data source, and linking to another tool. No gaps.

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% with a clear example. The tool description adds value by explaining the return format (license numbers) and data source, enhancing understanding beyond the schema.

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 for approved drugs in Taiwan using Chinese keywords and returns matching drugs and their license numbers. It also distinguishes from the sibling tool taiwan_drug_info by directing users there for ingredient details.

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?

Explicitly mentions when to use this tool (searching for drugs by keyword) and when not to (for ingredients, use taiwan_drug_info). Provides clear context and alternative.

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 provided, so the description bears full burden. It discloses the tool returns price and volume data, covers specific categories, excludes others, and cites the data source. It does not mention side effects, but as a read-only query, that is acceptable. Adds useful context beyond 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 extremely concise: two sentences and a data source line. Front-loaded with purpose and output, followed by context and coverage. Every sentence adds value without redundancy.

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, the description adequately explains return values (price stats and volume), units, data source, and coverage. It misses details like handling multiple markets or error conditions, but is sufficient for common usage.

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% with descriptions for both parameters (crop and market, with default). The description adds no new parameter-specific meaning beyond the schema; it re-iterates crop name examples and default market. Baseline 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 queries latest wholesale market prices for agricultural products, with specific output (average, high, low price per kg, volume). It delineates coverage (vegetables, fruits, flowers) and exclusions (poultry, eggs, meat), distinguishing it from sibling tools focused on companies, real estate, or drugs.

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?

While the description does not explicitly contrast with alternatives, its domain (agricultural prices) is distinct from all sibling tools, making usage context clear. It implies use when needing Taiwan farm prices, especially during typhoon season, without specifying when not to use.

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. It discloses that the tool returns intermediate nodes and distance ('中間的人與公司節點與相隔層數'), implying a read-only operation. It also mentions '天眼查式盡職調查' to set expectations. No side effects or auth needs are discussed, but the behavior is adequately described for a path-finding 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?

The description is a single block of text that is relatively concise for the information it conveys. It front-loads the main purpose and includes examples. Slightly verbose with extra details like '資料來源：inc.com.tw' but not excessive.

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?

Despite lacking an output schema, the description explains the return format (nodes and distance). It covers the essential aspects of the tool's functionality and data source. No mention of limits or pagination, but acceptable for a path-finding 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?

The schema covers both parameters with descriptions, achieving 100% coverage. The description adds value by clarifying that parameters can be company name, 8-digit unified number, or person name, and provides examples. This exceeds the baseline of 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 finds the shortest relationship chain between two companies/people using common directors/officers, and provides an analogy to Tianyancha due diligence. It distinguishes itself from sibling tools like taiwan_company_relations by specifying 'shortest chain' and 'how they connect'.

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 says 'use for: do these two companies/people have a relationship, how are they connected?' which provides clear context. It does not explicitly state when not to use or name alternatives, but the purpose is well-defined enough to guide selection.

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 provided; description lacks disclosure of read-only nature, rate limits, or other behavioral traits. Only implies data retrieval through its description of returning results.

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?

Two sentences, front-loaded with core functionality. Every sentence adds value: first describes function and output, second gives usage context and data source. 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?

Lists returned fields, provides usage scenario, and cites data source. Lacks details on pagination, limits, or authentication, but is sufficient for a simple query tool. Should ideally mention if it returns current or historical data.

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?

Parameter 'company' is well-described in schema (with example). Description adds no additional semantic meaning beyond schema. Schema coverage is 100%, so baseline 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?

Clearly states it queries a company's government procurement cases, listing specific return fields (tender name, agency, announcement type, date, related companies). Differentiates from sibling tools like taiwan_gov_tender_search by being company-specific.

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?

Provides context for use in due diligence (可搭配公司查核做盡職調查). Implies usage when you have a company name, but does not explicitly differentiate from alternatives or state when not to use.

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 burden. It discloses the return fields and pagination but does not mention rate limits, data freshness, or any side effects. It adequately signals read-only behavior implicitly.

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?

Two sentences, no redundant words. The first sentence captures the core functionality, and the second provides the data source. Every sentence is valuable.

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 no output schema, the description lists the main return fields (tender, agency, winning bidder, date) and mentions pagination. It is sufficient for basic use but lacks details on pagination format or result limits.

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% with both parameters already described. The description adds 'pagination' context but no additional meaning beyond the schema. Baseline score 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 verb 'search' and the resource 'government procurement cases by keyword in tender name', and specifies returned fields (tender, agency, winning bidder, date). It distinguishes from sibling 'taiwan_gov_tender_by_company' by focusing on keyword search.

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 implies usage for keyword-based tender search but does not explicitly state when to use this tool versus alternatives like searching by company name. No exclusions or prerequisites are provided.

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 bears full burden. It discloses matching by name, potential same-name matches, data source, and output (count and example companies). It does not mention rate limits or auth, but for a read-only search, this is adequate.

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 very concise: a few sentences in Chinese that front-load the core purpose, output, and data source. No unnecessary 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?

For a simple single-parameter search tool with no output schema, the description adequately explains input, output (count and examples), and caveats. It does not specify result limits or format, but these are minor omissions.

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 only parameter 'name' is fully described in the schema (example: 郭台銘). The tool description does not add additional semantics beyond what the schema provides; it only reiterates the purpose. With 100% schema coverage, baseline score is 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?

Description clearly states the tool searches for Taiwanese companies where a person serves as responsible person/director/supervisor. It specifies the output (number of related companies and examples) and distinguishes from sibling tools like taiwan_company_search (company-by-name) and taiwan_company_profile (detailed info).

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 implies usage for checking person-company relationships and networks. It includes a caveat that same names may cause ambiguity. However, it does not explicitly state when to use alternative tools or when not to use this tool.

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 provided. The description mentions the data source and the read-only output statistics, but does not disclose rate limits, authentication requirements, or other behavioral traits that an agent should know.

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 sentence that front-loads the core function and lists outputs efficiently. Could be slightly more concise but overall 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 only two parameters (one required) and no output schema, the description covers the return values (median/average price, count, age, percentiles, road rankings) and data source. It is complete for the tool's scope.

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 the description adds little beyond the examples in the schema. The description mentions county and district but does not provide additional semantic meaning like format restrictions beyond what's in the schema.

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: querying real estate transaction statistics for a county/district. It lists specific outputs (median/average price, transaction count, etc.) and distinguishes from sibling tools like taiwan_realprice_estimate and taiwan_realprice_locate.

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?

No explicit guidance on when to use this tool versus alternatives. The description does not mention when-not-to-use or provide comparative context with sibling tools.

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 of behavioral disclosure. It mentions data source and returns unit price range and total price, but does not elaborate on limitations, estimation methodology, or edge cases (e.g., missing data, geographic scope). It is adequate but lacks depth.

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 sentences, elegantly covering purpose, inputs, outputs, and data source. It is front-loaded with the core functionality in the first sentence. No extraneous information.

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 5 parameters and no output schema, the description is reasonably complete for a simple estimation tool. However, it lacks details on response structure, error handling, or specific limitations. It meets the minimum viability threshold.

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% with detailed parameter descriptions (e.g., county uses '臺' not '台'). The tool description adds little beyond restating the schema, such as '可加建物型態/屋齡/坪數'. Since the schema already covers semantics, the description provides minimal additional value.

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 purpose: automatic valuation (自動估價). It specifies inputs (county, district, optional building type/age/area) and outputs (comparable unit price range in 萬/坪 and estimated total price). It also distinguishes from sibling tools like taiwan_realprice_area or taiwan_realprice_search by focusing on estimation/valuation.

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 does not provide explicit guidance on when to use this tool versus its siblings (e.g., taiwan_realprice_search, taiwan_realprice_area). It only describes functionality, leaving the agent to infer usage context without clear boundaries or conditions.

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. It states the output (county, district, link) and data source (housetw.com), but does not explicitly confirm it is read-only or mention any potential errors or rate limits. This is adequate but not thorough.

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 concise sentences in Chinese, front-loaded with the action and use case. No unnecessary 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?

For a simple tool with 2 parameters and no output schema, the description provides sufficient context: what it does, when to use, and data source. Could mention coordinate limitations, but overall complete.

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% with clear descriptions for lat and lng. The tool description adds the context that they are for reverse geocoding in Taiwan, but does not add significant meaning beyond the schema.

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 uses lat/lng to reverse-lookup Taiwan county/district and returns a link. This differentiates it from siblings like taiwan_realprice_area (area-based) or taiwan_realprice_estimate (estimate). The specific use case is given.

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 a clear use case: 'when you are at a coordinate and want to know nearby housing prices'. It does not explicitly state when not to use or list alternatives, but the context is strong enough for correct selection.

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 provided, so description carries full burden. It mentions the data source (housetw.com, based on government data) but does not disclose behavioral aspects like cache behavior, data recency, or required permissions.

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?

Description is a single concise sentence with a second line for data source, front-loaded with purpose. No waste.

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?

Lists key outputs (unit price, count, house age, trends) which is sufficient for a retrieval tool. However, no output schema or mention of error handling/pagination. Almost complete.

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% with clear parameter descriptions. The tool's description adds no additional meaning beyond the schema, earning 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 explicitly states the tool queries real estate transaction prices for a specific road, listing the outputs: unit price statistics, transaction count, house age, and yearly trends. It clearly differentiates from siblings like taiwan_realprice_area (area-level) by focusing on roads.

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?

No guidance on when to use this tool versus siblings. Does not mention prerequisites, exclusions, or alternative tools.

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 reveals that the tool returns matching items, transaction counts, and links, indicating a read-only nature. However, it lacks details on authentication requirements, rate limits, or any side effects.

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 sentences long, covering purpose, usage, and data source without redundancy. Every part adds value.

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's simplicity (one parameter, no output schema), the description adequately covers expected returns and source. It could mention potential limitations or ordering, but overall it is sufficiently complete.

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 covers 100% of parameters, and the description adds an example for the 'query' parameter. This provides modest added value beyond the schema.

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 searches for Taiwan real estate actual price records by address/section/district and returns matching items, transaction counts, and links. However, it does not differentiate from sibling tools like taiwan_realprice_area or taiwan_realprice_road, which have more specific scopes.

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 implies usage for locating an address or area before checking market conditions, but does not provide explicit guidance on when to use this tool over siblings, nor does it mention when not to use it.

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 full burden. It explains the read-only nature, return fields (risk level, reports, source link), and data source. No destructive behavior is relevant.

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?

Two sentences, no wasted words, front-loaded with purpose. Extremely concise and 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?

For a simple query tool with one parameter, the description fully covers input and output expectations. No gaps despite missing output schema.

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 covers the one parameter with 100% coverage, but the description adds examples of input format (e.g., example.com or full URL), which is not in the schema.

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 checks if a URL/domain is reported as fraud by Taiwan's 165 anti-fraud unit, distinguishing it from sibling tools like company checks or real estate queries.

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 implies usage when needing to verify a site's fraud status, and sibling tools are dissimilar, so context is clear. However, no explicit when-not or alternatives are stated.

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 fully discloses behavioral traits: it is a pure algorithm (no database), returns valid and explanation, and cites the data source. This gives the agent full understanding of what to expect.

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 extremely concise: two sentences plus a data source. The first sentence states the core function immediately, and every sentence provides necessary information without waste.

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 validation tool with one parameter and no output schema, the description is complete. It explains the algorithm, purpose, and return value, leaving no gaps for the agent.

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 sole parameter 'unified_business_no' has a description that adds value beyond the schema: it specifies the format (8 digits) and provides an example. Since schema coverage is 100%, baseline is 3, but the added context justifies a 4.

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 validates the check digit of Taiwan's unified business number using an algorithm, specifying the length (8 digits) and that it is pure algorithm without database lookup. It also mentions usage for data cleaning and form validation, distinguishing it from sibling tools like taiwan_company_verify.

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 clear use cases: data cleaning, form validation, and checking valid format. However, it does not explicitly state when not to use it or compare with alternatives like taiwan_company_verify, leaving some ambiguity for the agent.

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