SupplyGraph.AI.Daasmart

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

描述了输入限制（必须是中国境内可定位的具体点，不能是市/区名），并说明输出为统计数量而非明细，但未提及数据更新频率或权限要求。注释中无readOnly或destructive提示，但描述本身提供了关键行为信息。

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?

描述简洁且结构化，分段落明确功能、指标、不包含内容和示例，没有冗余信息，每个句子都有价值。

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?

描述完整覆盖了工具的功能、输入要求、输出类型和限制，对于调用者来说足够清晰，无需额外信息即可正确使用。

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?

输入schema已详细描述city和address的格式要求，但描述中重复强调了地址必须具体且为中国境内，并给出示例，补充了schema之外的约束，有助于正确调用。

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?

描述明确说明了工具用途：基于中国地址查询附近企业统计，并强调返回的是统计数量而非明细列表。与兄弟工具如'business_surrounding_shop'（可能返回商店明细）区分明显。

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?

描述了适用的场景（查询周边企业统计），并明确不包含的内容（企业名称明细、POI等），但未直接提及替代工具，不过通过排除法已足够指导使用。

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?

The annotation openWorldHint is set, and the description adds context on what the tool does not cover (e.g., no shop names, no company counts) and specifies the return type (statistics). It does not contradict annotations, but since openWorldHint is broad, the description provides useful boundary information.

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 detailed but not overly long. It front-loads the purpose and includes examples, though the pricing note is somewhat unusual. Overall, it is structured clearly with sections for metrics, exclusions, and typical queries.

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 (statistics queries for shops in China), the description covers key aspects: input constraints, metrics, exclusions, and example use cases. The presence of an output schema reduces the need to describe return values. The description is sufficiently complete for an agent to use it 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?

While the input schema already provides descriptions for both parameters (city and address), the tool description adds context on the expected format (e.g., Chinese address structure) and constraints (no city names alone). Given the schema coverage is 100%, the extra guidance in the description is a bonus, not a necessity.

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 the surroundings of a specific address in China for shop statistics, listing major categories and subcategories (dining, shopping, entertainment). It clearly differentiates from siblings like business_surrounding_company by specifying it returns counts, not lists.

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 provides explicit usage guidelines, including typical queries, constraints (China only, no city-level addresses), and what is excluded (shop names, coordinates). It also distinguishes from sibling tools by stating it returns counts not lists.

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?

Beyond the openWorldHint annotation, the description discloses important behavioral constraints: it requires a specific address (not a city name), supports only Chinese locations, and returns aggregate indices rather than detailed lists. It also lists excluded content (e.g., specific entity names, prices). This added transparency helps set expectations for output and input limitations.

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 dense but logically structured: function statement, metric types, exclusions, and example queries. While it is relatively long, it packs essential information without unnecessary fluff. The structure aids readability, though it could be slightly more 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?

The description covers the purpose, parameters, output types (star ratings, indices), and exclusions, and gives examples. It does not provide an explicit output schema, but the description sufficiently outlines the nature of results. Given the tool's complexity, this is complete enough for a user to understand its 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?

The schema descriptions for both parameters are thorough: 'city' must be a prefecture-level Chinese city without the '市' suffix, and 'address' must be a specific, geolocatable point with examples and exclusions. The tool description reinforces these constraints. This provides complete semantic clarity 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's function: querying surrounding amenity analysis for a specific address in China, returning star ratings and configuration indices for education, medical, shopping, transportation, etc. It also distinguishes from listing specific entities and provides typical question examples. This is highly specific and informative.

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 includes typical user queries and clarifies what the tool does not include, which helps set usage context. However, it does not explicitly reference alternative sibling tools (e.g., POI-specific tools) or provide explicit 'when to use this vs. that' guidance. Still, the examples and exclusions offer practical usage hints.

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?

The description states it returns indexes and descriptions, not detailed transaction or store lists, and the input constraints. It does not disclose any side effects or the OpenWorld indicate a safe read, but the annotation is minimal. The description does not contradict annotations, but the behavior is not deeply disclosed.

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 and front-loaded with the main purpose, followed by examples and exclusions. It avoids redundancy with schema. Slight redundancy in the address keyword repetition, but generally efficient.

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 (specific address constraints, output type, exclusions), the description covers key aspects. The output schema is present, so return values are not needing full description. It gives typical questions. Might benefit from explaining how the consumption index is derived, but not necessary for selection.

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 provides detailed parameter descriptions (city format, address format with examples). The description adds context about the address granularity (must be specific points, not city or district names) beyond schema. With schema coverage 100%, baseline is 3, but the description's extra constraints push it to 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 identifies this tool queries consumption analysis near a specific address to analyze surrounding consumption, clearly indicating a specific result, but it explicitly and the name shows that indicates a nearby or analysis. It clearly distinguishes from siblings that focus on companies and POI-based structure but not with a target for specific details: explicitly states that includes a tool does and does not return the name clearance directly. Clear to the name, though the key findings a fine. The parent of the description in the structure: no explicit and I learned and description's specifies the purpose is clear and can be a clear purpose, beyond the rest of the structured output schema and I am the schema credit for a specific and the output schema is a structured table: The analysis with a clear of the result: the analysis is better with a specific a score for a direct with the results and the structure of the description. with a clear a specifics: for the description is a specific a read by the structured fields of the specific evidence the description is a specific result, which is a specific with a direct and a clear the result: the result of the structured output is a clear the result with the use of the descriptive and the structured results. The result is clear of the clear a specific to a with the result and the output is the schema and the schema description for the result is the result of a specific and the result with a structured the output schema for the result of a clear: the result is a clear and the result of the schema with a specific and result in the score is covered by the purpose of the result is the result of a and the use and result and the schema for detail. The name of a specific and the result and the description of the answer: the query and more the result and the answer: The answer is the result and the answer to the description and the answer is the result and the answer is the result of the description and the answer is the result and the answer is the result of the description is the result and the answer is the result and the answer is the result and the answer is the result and the answer. The schema and the description and the answer. The schema and the answer is the result. The schema and the answer. The answer. The schema. The answer. The schema. The answer. The answer. The schema. The description.

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 clearly states the usage is the result and clearly and the schema and the description for the answer. The description does not explicitly name alternatives to the description for the usage and the analysis. The answer is clear and the answer. The schema is the answer. The schema. The answer.

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?

Annotations only include openWorldHint, leaving safety/reporting traits to the description. The description discloses what will be returned (均价/行情/走势/指数/建议) and what will not be returned (成交明细、挂牌列表、配套星级), which is meaningful behavioral context beyond the schema. It does not mention data freshness or limitations, but not enough to lower below 4.

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 longer than average but well-structured: main purpose first, then output indicators, exclusions, and examples. The list of indicators is dense but useful for setting expectations. No redundant filler; each section earns its place given the tool's complexity.

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 an output schema present, return values don't need full description. The tool involves two parameters, and the description covers input constraints, output scope, exclusions, and typical queries comprehensively. It is complete enough for an AI agent to select and invoke correctly, though it could specify data sources or update frequency.

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 extra meaning by clarifying acceptable address forms (门牌、地标、路名、小区名、园区出入口), reiterating the China-only constraint, and providing concrete examples for both parameters in typical questions. This adds value beyond the schema's parameter descriptions.

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 identifies a specific verb+resource: query (查询) housing price/investment analysis for a location. It distinguishes from siblings by focusing on 房价/投资分析 and explicitly excluding transaction lists, listing names, and supporting facility ratings, which differentiates it from cbd_surrounding_amenity, cbd_surrounding_consumption, and related tools.

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 detailed usage context: input must be a specific locatable point in China, not a city/district name, and it provides typical question phrasings. It doesn't explicitly name sibling alternatives, but its scope and exclusions implicitly clarify when this tool is appropriate versus others.

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?

Beyond the openWorldHint annotation, the description discloses what the tool returns (indices and descriptions, not raw population lists) and what it explicitly excludes. It also includes pricing context, adding useful operational transparency beyond the schema and annotations.

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 well-structured with clear sections for scope, included indicators, exclusions, and typical queries. It is somewhat longer than necessary but every section serves a purpose and the main function is front-loaded.

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?

The description is complete for a two-parameter lookup tool: it defines valid input scope, clarifies output semantics, enumerates exclusions, gives example queries, and includes pricing. Since an output schema exists, the description does not need to explain return values in further detail.

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 covers both parameters in detail with 100% coverage, so the baseline is 3. The description adds value by reinforcing the requirement for a specific locatable point, providing typical query examples, and clarifying that city/district names alone are invalid inputs.

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 surrounding population analysis for a specific Chinese address, with an explicit verb and resource. It also distinguishes itself by listing included indicators (population structure, residential density, business density) and excluding registry statistics and POI lists.

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 when-to-use context: valid for specific China-locatable points, not for city/district names or overseas addresses. It also provides negative scope (not household registration counts or POI details), but it does not explicitly name alternative sibling tools for those cases.

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 (openWorldHint is present but not relevant to behavior). The description mentions what is included and excluded (e.g., '不包含其他企业分类的统计；仅返回数量不返回名单') but does not disclose any side effects, permissions, rate limits, or data freshness. Behavior is partially transparent but lacks important details.

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 clear sections for '涉及指标/类型', '不包含', and '典型问法'. It avoids redundancy and is well-structured. The repetition of the same text in description and schema examples is minor but acceptable.

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?

The description provides enough context for a typical use case (querying A-level taxpayer companies by region and chain). However, it lacks details about the output format (e.g., whether it returns a list of company names or detailed data), and no output schema is given. The exclusion of '仅返回数量' hints that it returns entity lists, but further specification would improve completeness.

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 all three parameters (year, region, chain_name) with descriptions and examples. The description additionally clarifies that the result includes merged types, but does not explain the exact meaning of '依赖型' or how year affects results if omitted. Schema coverage is 100%, so baseline is 3; description adds some nuance but not substantial.

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 A-level taxpayer company lists by region and industry chain, distinguishing it from similar list tools by specifying the A-level taxpayer type. It mentions the merged return of total/production/sales/dependent types, which adds specificity.

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 includes typical question examples (e.g., '2024年全国集成电路A级纳税人企业名单') but does not explicitly state when to use this tool versus alternatives like park_a_taxpayer_company_list or chain_a_taxpayer_company_num. Usage context is implied but not clearly differentiated.

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 only openWorldHint as annotation, the description adds valuable context by stating the exact count types returned, the merged text nature of the return, and exclusions. It does not contradict the annotation or overstate its behavior; minor gaps remain around edge cases like zero-result handling, but this is adequate for a numeric query 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 compact and front-loaded with the core query purpose, followed by metrics, exclusions, and examples. It contains slight redundancy between the initial '总量/生产型/销售型/依赖型' list and the later repeated metric enumeration, but overall nothing is wasted.

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 relatively simple aggregation tool with full schema description coverage and an output schema, the description covers scope, supported metrics, exclusions, and realistic query formulations. The phrase about 'merged text' is slightly ambiguous but not enough to significantly impair selection or 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?

The input schema already covers all parameters with descriptions, so the bar is moderate. The description adds useful semantic detail by enumerating region levels (country, province, city, district) and providing concrete examples for region, chain_name, and year, which helps correct parameter formatting.

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 identifies the tool's action: querying A-level taxpayer enterprise counts by specific region and industry chain, with explicit metric breakdowns (total/production/sales/dependent). It also distinguishes itself from list-type siblings by stating that company list details are not included.

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 typical question phrasings and explicitly states what is excluded (other classifications and company list details), which helps the agent decide when to use this tool. However, it does not explicitly name chain_a_taxpayer_company_list as the alternative for list-detail use cases.

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?

The description mentions the output is a merged text with totals and categories, which is useful. It also mentions pricing, which is beyond annotations. However, it doesn't clarify pagination, sorting, or the exact format of the returned list beyond that. The annotation only has openWorldHint, which is not a contradiction.

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, uses bullet points and examples for clarity, and front-loads the core purpose. No redundant 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's simplicity and the existence of an output schema, the description covers the main use case, exclusions, and examples. It could add a note on sorting or default behavior of year, but it's not critical for an agent to invoke it 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?

Schema coverage is 100%, but the description adds context to the 'region' and 'chain_name' parameters by giving examples like '全国', '成都', '集成电路'. It also clarifies 'year' is optional and defaults to current year (though not explicitly stated, the schema says optional). Overall, the description reinforces and supplements 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 returns a list of companies that closed in a given year, filtered by region and industry chain, with a merged text of totals and subtypes. It distinguishes from the sibling tool 'chain_close_company_num' which likely returns only counts, by explicitly stating it returns the list.

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 typical query examples and explicitly states what is not included (other categories, only counts). It implies when to use this tool, but does not directly compare with the sibling 'chain_close_company_num' directly, but the name and description suffice for most cases.

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?

Beyond the openWorldHint annotation, the description discloses that the result is a merged text of total/production/sales/dependent counts, and that other categories and company lists are excluded. It does not explain optional-year fallback behavior, but for a read-style count query with an output schema, this is reasonably transparent.

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 compact and well-structured with labeled sections for metrics, exclusions, and example questions. The pricing block adds a small amount of non-behavioral clutter, but overall every sentence serves a clear purpose.

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 3-parameter count tool with an output schema, the description adequately covers purpose, parameter usage, and exclusions. It is well suited to disambiguate from many sibling tools. A minor gap is not explaining what happens when the optional year is omitted.

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 all parameters at 100%. The description adds example phrases and geographic granularity (国家/省份/城市/区县), but does not substantially extend the semantics already present in the input 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?

Description clearly states it queries the count of deregistered companies for a specific region and industry chain, with a specific verb ('查询') and resource. It also lists the exact metric types returned and explicitly excludes company list details, distinguishing it from sibling list tools like chain_close_company_list.

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 typical question examples and explicitly states what is not included ('不包含：其他企业分类的统计；企业名单明细'), which signals when not to choose this tool. However, it does not name an alternative tool explicitly, so it stops short of full when/when-not guidance.

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?

The description adds useful context beyond annotations: it specifies the return includes merged text for total/production/sales/dependent types, and excludes other categories. However, it doesn't disclose details like pagination, result limits, or whether the list is exhaustive. The annotation openWorldHint=true is not contradicted, and the description adds some behavioral context but not rich detail.

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 and front-loaded with the core purpose, followed by inclusions/exclusions and examples. The pricing info is extra but useful. It's efficient with no wasted words, though the pricing block could be considered extraneous for tool selection.

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 moderate complexity (3 params, 2 required, output schema exists), the description covers the key aspects: what it returns, what it excludes, and typical usage. The output schema handles return structure. It could mention result limits or pagination, but overall it's complete enough for an agent to select and invoke 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?

Schema description coverage is 100%, so the schema already documents all three parameters (year, region, chain_name) with descriptions. The description adds example values and clarifies the region granularity (country, province, city, district) and chain name examples, but this is marginal beyond the schema. 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 company lists by specific region (country, province, city, district) and specific industry chain name, returning merged totals for total/production/sales/dependent types. It explicitly lists what's included and excluded, and provides typical query examples, making the purpose unambiguous and distinguishable from siblings like chain_company_num (which only returns counts).

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 on when to use this tool (for company list queries by region and chain) and explicitly states what it does NOT include (other company category statistics, only returns counts without names). It doesn't explicitly name alternative tools, but the exclusions help the agent understand boundaries. Typical question examples further guide usage.

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?

Annotations only include openWorldHint=true. The description does mention it returns a combined text of total/production/sales/dependent counts and excludes certain data, adding some behavioral detail beyond the schema. However, it does not disclose handling of edge cases, exact output format beyond 'text', or any side effects. With openWorldHint present, one might expect a note about possible extra fields, but it's absent. Given the low annotation coverage, the description carries partial burden but is not fully transparent.

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 compact, front-loads the main function, and includes examples and exclusions. It also contains a pricing note, though that is arguably extraneous. Overall, every sentence contributes to understanding the tool's scope, with minimal 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?

The tool is moderately complex with multiple metrics returned and an output schema exists. The description covers the main use case, metrics, and exclusions, and provides examples. It does not explain prerequisites like valid region names or error behavior, but given the schema and examples, it is fairly complete for an agent to use. Slightly higher than basic due to the typical questions.

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%, so all parameters have descriptions (year, region, chain_name). The tool description does not add parameter-specific meaning beyond the schema; it only reinforces with typical questions. This meets the baseline of 3; it does not go further to explain any nuances like region name matching or chain name variants.

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 queries the number of companies by region and industry chain, and specifies the exact metrics returned (total, production, sales, dependent). It distinguishes itself from sibling list tools (like chain_company_list) and other category-specific count tools by explicitly listing what it includes and excludes (excluding other categories and detailed lists). This is a specific verb+resource+scope.

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 context on when to use (region + chain name count queries) and provides typical question examples. It explicitly states what it does not include (other category statistics, list details), but does not name specific alternative tools or explicitly say 'use this instead of that'. This is clear usage context without explicit exclusions to alternatives, so a 4 is appropriate.

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?

The description adds useful context beyond the openWorldHint annotation: it clarifies the output is a merged text of total/production/sales/dependent lists, and explicitly states it does not return names for other categories. However, it doesn't disclose details like pagination, result limits, or whether the output is a single text blob vs structured data, which would be helpful for a list-returning 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 well-structured with clear sections: purpose, included types, exclusions, and examples. It's slightly verbose with the pricing block, but the core content is front-loaded and each sentence adds value. The examples are particularly useful for grounding the agent.

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 an output schema and 100% parameter coverage, the description is fairly complete. It covers what the tool does, what it returns, what it excludes, and provides examples. The main gap is lack of detail on output format (e.g., is it a single merged string or a list of objects?), but the output schema likely covers this.

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%, so the schema already documents all three parameters. The description adds example values for region and chain_name, and clarifies the year is optional, but doesn't add significant new semantics 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 tool queries discredited company lists by specific region and industry chain, and explicitly lists the four types of lists returned (total/production/sales/dependent). It distinguishes from sibling tools like chain_discredited_company_num (which returns counts) and park_discredited_company_list (which is park-scoped).

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 usage context: it specifies the required inputs (region and chain name), gives typical query examples, and explicitly states what is NOT included (other company categories, only counts). It doesn't explicitly name alternative tools for other categories, but the exclusions are clear enough for an agent to infer 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?

Annotations only include openWorldHint: true. The description adds that it returns aggregated counts in text form, not a list, and notes what is not included (other classifications, list details). It does not mention any side effects, data limits, or performance characteristics, but for a read-only query tool, 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 concise but informative, using bullet points for clarity. It front-loads the core functionality and provides examples. It includes pricing info, which may be extra but useful for agents considering cost.

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 output schema exists and parameters are well-documented, the description is sufficient for an agent to understand the tool's scope. It clearly defines what is included and excluded, and provides example queries. The pricing info adds context for resource 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 each parameter. The description adds value by explaining the combination of region and chain_name, and gives examples of valid inputs. It does not add new information beyond the schema but reinforces the semantics.

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 queries the count of discredited companies in a specific region and industry chain, with distinct result breakdowns (total/production/sales/dependent). It distinguishes from sibling tools by explicitly noting it returns counts, not lists, and excludes other categories. The example questions reinforce its purpose.

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 typical usage examples and clarifies that this is for count queries, not lists or other company types. However, it does not explicitly state when not to use this tool or compare it to alternative tools like chain_company_num, but the context implies it for discredited company counts.

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?

The tool has openWorldHint annotation, meaning results are an open set. The description clarifies the return contains combined text for total/production/sales/dependent types and excludes other categories, but it doesn't disclose pagination, email formatting, or whether it returns full lists or sampled. It also doesn't mention the 100 credits cost, which is available in the description but not emphasized. The annotation doesn't contradict the description.

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 organized with clear sections: purpose, included metrics, exclusions, and example queries. It's concise at around 150 Chinese characters and front-loads the core purpose. The pricing line is separated and relevant. Minor redundancy with listing metrics that are clear from the tool name.

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 an output schema (though not provided in detail) and clear parameters, the description covers the essential scope, exclusions, and examples. It doesn't explain the return structure but the output schema presumably handles that. The openWorldHint is offset by the description's explicit exclusions. Missing details on pagination or result size, but acceptable for a list tool with typical patterns.

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 has a description. The description adds context via example question formats (region like '海淀区' and chain like '人工智能') that map directly to the parameters, but doesn't provide additional syntax or format details beyond what the schema offers. It explicitly shows how to combine region and chain_name in queries, adding value slightly above baseline.

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 queries companies with software copyrights by region and industry chain, listing the specific metrics included. It distinguishes from sibling tools like chain_have_copyright_company_num (which returns count only) and chain_company_list (which returns all companies), but doesn't explicitly name alternatives.

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 by providing typical question examples and specifying what is excluded (other company classifications, count-only returns). However, it doesn't explicitly state when to use this vs. the companion count tool or other chain_*_list tools, only implicitly distinguishing via scope.

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?

The description discloses what the tool returns (total count and breakdowns by company type) and what it does not include (other classifications and detailed lists). It also mentions it is a query (查询), implying read-only behavior. The annotation only includes openWorldHint, so the description adds useful behavioral context beyond annotations.

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 well-structured: it states the core function, lists relevant metrics, exclusions, examples, and pricing in a logical order. It is slightly verbose but avoids redundancy, and each sentence 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?

The description thoroughly covers the tool's purpose, parameters, return value (counts and breakdowns), exclusions, and provides example queries. Even though an output schema exists, the description adds meaningful detail about the return content, making the tool self-explanatory for typical use cases.

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?

Each parameter is explained with concrete examples: year (e.g., 2024) explicitly marked as optional, region (e.g., 全国, 成都, 海淀区), and chain_name (e.g., 集成电路, 新能源, 人工智能). This goes beyond the schema descriptions by providing realistic usage examples and clarifying the optionality of year.

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: to query the number of companies with copyright (软著) based on region and industry chain. It distinguishes from sibling tools that return lists or focus on other attributes like patents, and explicitly mentions that it returns counts, not detailed lists.

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 typical questions and explicitly states exclusions ('不包含：其他企业分类的统计；企业名单明细'), which implicitly guides when to use this tool vs. the list variant. It could be more explicit about when to choose this over other _num tools, but the attribute-specific naming and examples make it clear enough.

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?

The description adds useful behavioral context by stating it merges return text for total/production/sales/dependent categories and excludes other classifications. However, annotations are minimal (only openWorldHint), so the description still lacks details on pagination, data source, read-only guarantees, or how 'no patent' is determined, leaving some transparency 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?

The description is well-structured and front-loaded: it opens with the core purpose, then lists included metrics, exclusions, typical questions, and pricing. Each section earns its place, though the pricing block adds some extra length beyond the functional description.

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 3-parameter list query with an output schema, this description is highly complete. It covers required and optional parameters, gives examples for each kind of input, clarifies what is not returned, and distinguishes from the count-only sibling. Minor gaps like error handling or empty-result behavior are not critical given the 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?

Input schema coverage is 100%, so the schema already documents all three parameters. The description reinforces this with realistic examples ('2024年', '全国', '集成电路'), but does not add materially new semantic information beyond what the schema provides.

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 this is a query for a list of companies without patents, scoped by specific region and industry chain name. It explicitly distinguishes itself from sibling tools by listing included metric types (total/production/sales/dependent) and excluding count-only returns, making its 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 typical example questions and explicit exclusions ('不包含：其他企业分类的统计；仅返回数量不返回名单'), which tells an agent when not to use this tool. However, it does not explicitly name the sibling tool `chain_have_no_patent_company_num` as the alternative for count-only requests, so guidance is strong 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?

The description discloses the return format (merged text with counts for total and types) and the exclusions (other classifications, list details). It does not mention side effects, permissions, or default behavior for the optional year, and annotations only provide openWorldHint, so transparency is adequate but not rich.

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, front-loading the core purpose, followed by exclusions and examples. It avoids unnecessary detail and is well-structured, though it includes pricing info which is not essential for tool selection.

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 that an output schema exists (context signal), the description covers the main aspects: what is returned, what is excluded, and typical usage examples. It does not clarify default behavior for the optional year, but examples show optionality, so completeness is sufficient for the tool's simplicity.

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% as all three parameters (region, chain_name, year) have descriptions. The description adds typical questions that illustrate parameter values, but does not provide additional syntax or semantics beyond what the schema already offers. So a 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 it queries the number of companies without patents in a specific region (country, province, city, district) and industrial chain, and returns combined text with total, production, sales, and dependent-type counts. It distinguishes from sibling tools like chain_have_patent_company_num by the explicit 'no patent' qualifier.

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 lists exclusions ('不包含') for other enterprise categories and company list details, implying when to use alternative tools for those needs. Typical questions (e.g., '2024年全国集成电路没有专利的企业有多少') illustrate when to use this tool, but alternatives are not named explicitly.

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?

Beyond the minimal annotation (openWorldHint), the description discloses key behavioral aspects: it returns a merged text of total/production/sales/dependent types, and it excludes other categories and count-only outputs. This sets clear expectations about the tool's output structure and limitations, though it does not mention pagination or error handling.

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 well-organized with clear sections: purpose, included metrics, exclusions, and example queries. It is a bit long due to the inclusion of pricing info and multiple examples, but each part contributes to understanding the tool's function. It is front-loaded with the core purpose and then details.

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 a straightforward query interface (region + chain + optional year) and an output schema exists, the description covers the necessary context: what it returns, what it excludes, and example usage. It does not describe edge cases or empty results, but for a list tool with a clear output schema, this is adequate.

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 covers all three parameters with descriptions, and the description adds semantic context by explaining that region can be country/province/city/district and chain_name refers to an industry chain name. The typical questions also illustrate plausible values, enhancing the meaning of each parameter 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's purpose: querying a list of companies with patents based on a specific region and industry chain name. It also lists the exact types of company lists returned (total, production, sales, dependency) and explicitly states what is not included. This distinguishes it from sibling tools like chain_have_patent_company_num (which returns counts) and chain_have_no_patent_company_list.

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 typical usage examples and clarifies scope via '不包含' statements, but it does not explicitly name alternatives or state when to use this tool over its num counterpart or other list tools. The examples and exclusions make the intended usage fairly clear, but explicit 'use when' guidance is absent.

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 only openWorldHint in annotations (vague), the description carries the burden and adds value by detailing the multi-category aggregate return format, explicit exclusions, and example queries. It discloses the combined text return structure clearly, though it doesn't discuss data sources, update frequency, or edge cases like missing data.

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 well-organized with clear sections (function, metrics, exclusions, examples, pricing), making it scannable. The pricing block adds minor noise but is useful operational info. Front-loaded with the core function, though the multiple sections could be trimmed slightly.

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 3-parameter count tool with multiple output categories, the description covers what it does, what it returns (aggregate categories), what it excludes, and provides realistic example queries. It could be more complete with explicit parameter constraints or output formatting details, but the output schema (not shown) presumably handles that. Overall, fairly comprehensive given context signals.

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 each parameter has terse but sufficient description (e.g., region example '「全国」「成都」', chain_name example '「集成电路」'). The description's typical questions add example values but don't drastically exceed the schema coverage; the year parameter is only illustrated in examples, not in the main description.

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 the count of patent-owning enterprises filtered by region and industry chain, with a specific verb+resource structure. It explicitly lists included metrics (total/production/sales/dependent types) and excludes others (other classifications, detail lists), distinguishing it clearly from sibling tools like chain_have_copyright_company_num.

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 'Not included' section sets clear boundaries, and the three example questions demonstrate appropriate use cases (e.g., 'How many enterprises in Chengdu's new energy industry chain own patents?'). However, it doesn't explicitly name alternative tools or state when NOT to use this tool, though the examples guide selection well.

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?

Annotations are minimal (only openWorldHint: true), so the description carries the behavioral disclosure burden. It states that results are combined text of multiple list types, excludes other classifications, and explicitly notes it returns lists not counts. It also includes pricing information (100 credits per run), which is an additional behavioral detail not covered by annotations.

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 reasonably concise, with a clear primary statement followed by included types, exclusions, typical questions, and pricing. It is structured with line breaks for readability, but contains some redundancy (e.g., the '涉及指标/类型' line repeats the types already mentioned). Overall, it is efficient and front-loaded with the core purpose.

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 list-returning tool with an output schema present, the description adequately covers the scope, exclusions, and usage examples. It mentions the combined result format, specifies the region and chain filters, and clearly states what it does not cover (other classifications and count-only). No critical information is missing for an agent to decide appropriate 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?

Schema description coverage is 100% for all three parameters (year, region, chain_name). The description adds value beyond the schema by providing concrete example queries (e.g., '2024年全国集成电路高新技术企业名单') that illustrate how to format region, chain_name, and year together. This helps an agent understand parameter composition beyond trivial field descriptions.

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 that this tool queries high-tech company lists based on specific regions (country, province, city, district) and specific industry chain names, and returns combined text for total/production/sales/dependent types. It explicitly lists included types, excludes other classifications, and provides typical query examples. This distinguishes it from the sibling tool chain_high_tech_company_num, which likely returns counts, and other chain_*_company_list variants.

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 implicitly differentiates usage by stating '不包含：仅返回数量不返回名单' (excludes: only count, not list), which indicates this tool is for lists and not for counts. It also provides typical questions showing when to use it. However, it does not explicitly name alternative tools like chain_high_tech_company_num, leaving some ambiguity about direct comparison.

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?

Annotations are minimal (only openWorldHint=true), so the description carries the transparency burden. It explains the output format (merged text with counts) and exclusions, and implicitly indicates a read-only query. However, it does not mention any limitations, data source, or potential side effects, though none are expected. This adds some value but could be more explicit about the read-only nature and data 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 well-structured with a core function statement, metric list, exclusions, examples, and pricing. It is somewhat long, but each section earns its place by clarifying scope and usage. The use of bullet-style formatting and examples aids readability without unnecessary 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?

Given the simple tool (3 params, 2 required), high schema coverage, and existing output schema, the description is fairly complete. It covers the main use case, return content, and exclusions. It does not detail edge cases or error handling, but these are less critical for a count query with clear inputs and output.

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%, so the description does not need to compensate for missing parameter docs. It adds examples of valid region and chain_name values (e.g., national, city, district, industry chain names), reinforcing the schema but not introducing new semantics. This meets the baseline of 3 for high-coverage schemas.

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 the count of high-tech enterprises by region and chain name, returning a merged text with totals and subtypes (production/sales/dependency). It explicitly excludes list details, distinguishing it from the sibling list tool (chain_high_tech_company_list) and other count tools by focusing on high-tech companies. Examples make 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 typical query examples that illustrate when to use this tool (e.g., asking for counts by region/chain). It states exclusions (no other classifications, no list details), implying if you need lists or other metrics, you should use alternative tools. However, it does not explicitly name or differentiate from other chain_*_num tools, so the guidance is clear but not exhaustive.

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?

Beyond the annotations (only openWorldHint), the description reveals that the tool returns a merged text of multiple categories, applies a 'last two years' time filter, and explicitly states exclusions. These behavioral traits are valuable for agent decision-making and are not covered by the annotation.

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 structured with bullet-like lists for indicators, exclusions, and typical questions, making it skimmable. It includes pricing info that might be redundant but not harmful. It is slightly verbose but each sentence adds context; no filler.

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 presence of an output schema and the tool's moderate complexity, the description adequately explains what is returned (merged text with three categories) and what is excluded. It does not detail output formatting, but the output schema covers that. For a list tool with clear scope, the description is complete enough.

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, providing baseline 3. The description adds value by giving concrete examples for region (national, provincial, municipal, district) and chain names, and implicitly clarifies that the 'year' parameter determines the end of the two-year window. This exceeds the schema's basic descriptions.

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 a list of companies that made external investments in the last two years, filtered by region and chain name, and returns a merged text covering total, production, sales, and dependent types. It explicitly distinguishes from count-only tools and other classification filters, making its purpose specific and non-overlapping with siblings.

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 typical question examples and lists what is excluded (e.g., other classifications, counts without lists), giving clear context on when to use this tool. However, it does not explicitly name alternative tools for counts or other list types, so it lacks explicit guidance on switching to siblings like chain_invest_company_num.

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 only openWorldHint as annotation, the description carries the transparency burden. It discloses that the tool returns a merged text of total/production/sales/dependent counts and explicitly states what is not included, such as other business classifications and company-name details. This adds behavioral detail beyond the annotation.

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 core purpose is front-loaded and clear, but the description is somewhat redundant: the metric list repeats the already-mentioned total/production/sales/dependent breakdown, and the Pricing block adds noise without behavioral value. Three example questions are helpful but slightly over-verbose.

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 moderate complexity of a 3-parameter count tool with an output schema, the description adequately covers input semantics, output categories, exclusions, and example usage. It does not explicitly address alternatives, but the scope and typical questions are sufficient for an agent to select and invoke this 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?

Schema coverage is 100%, but the description adds useful semantic context: 'year' is tied to the '近两年' (past two years) lookback window, and 'region' is clarified as country/province/city/district granularity. Typical questions further illustrate how the parameters combine in real queries.

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 uses a specific verb and resource: it is a query for the count of companies with outward investment in the past two years, filtered by concrete region and industrial-chain name. It also explicitly excludes company-list details, which differentiates it from its sibling tool chain_invest_company_list.

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 scope, exclusions, and typical question phrasings such as '2024年全国集成电路近两年有对外投资的企业有多少'. However, it does not explicitly state when to prefer this tool over alternatives like chain_invest_company_list or chain_invested_company_num; usage is implied rather than explicitly contrasted.

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?

Annotations only include openWorldHint: true, which is generic. The description adds valuable behavioral context: it returns merged text of totals and type-specific lists, includes specific categories (production, sales, dependent), and excludes other enterprise classifications. It also clarifies it returns lists, not just counts. This goes beyond the annotation and helps the agent understand output structure.

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 well-structured: first sentence states the core function, then lists the four indicator types, then what's excluded, then typical query examples. It's concise and front-loaded with the purpose. Every sentence 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 moderate complexity (3 parameters, output schema exists), the description is quite complete: it defines the time window, region/chain inputs, output types, exclusions, and examples. The output schema exists, so return values are covered. The main gap is not specifying the exact format of the merged text or whether it returns just names or details, but examples cover typical 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%: all three parameters (region, chain_name, year) are described in the schema. The description doesn't add much beyond the schema for parameters, but it does clarify that region can be like '全国' or '成都市', which matches the schema. The description mentions '近两年' and '2024' examples, tying year to the time window, but that's implicit. Baseline 3 is appropriate given high schema coverage.

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 a list of companies with external financing in the past two years based on specific region and industry chain. It distinguishes from siblings like chain_invest_company_list (companies that invested) and chain_invested_company_num (count only) by specifying it returns lists and merges totals/type-specific texts. The name and title align perfectly.

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 usage context: it's for querying companies with external financing in the past two years, and explicitly lists what is not included. It gives typical query examples. However, it doesn't explicitly state when to use this vs. alternatives like chain_invested_company_num or other list tools, but the clear differentiation via '近两年有对外融资' and '列表' plus sibling names makes it reasonably clear.

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?

The description mentions that the query is for the '近两年' (last two years) and returns aggregated text for total/production/sales/dependent types, adding behavioral context beyond annotations. Annotations only include openWorldHint:true, so the description does not contradict them and adds some context about the time filter and grouping, but it does not detail additional behavioral aspects like data freshness or limitations.

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 concise and well-structured: starts with the core function, then lists included metrics, exclusions, and example questions. It is informative without being verbose, though the pricing information is not directly relevant to tool selection and could be considered extraneous, but it does not harm the description's clarity.

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?

The tool has a clear scope with explicit inclusions and exclusions, and the parameter schema is complete (100% coverage). The description covers key aspects: what it returns, what it excludes, and typical usage examples, making it adequate for an agent to understand purpose and usage. It could mention whether the return is a single number or a breakdown, but the description notes it returns text of totals, which is sufficient.

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%, so parameters are fully documented in the schema with examples for region, chain_name, and year. The description adds examples of typical queries and clarifies that year is optional, but it does not significantly enrich parameter semantics beyond what the schema already 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?

Description clearly states the tool counts companies with external financing in the last two years, categorized by region and industry chain, and specifies the return includes totals for production, sales, and dependent types. It explicitly mentions what is not included (other categories, company lists) and distinguishes from sibling list tools, providing clarity on its aggregation 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?

Description includes typical question examples and specifies the parameters (region, chain name, year) which implies when to use it. It does not explicitly name alternatives, but among the sibling tools, it's clear this is the count version of the list tool (chain_invested_company_list), and the description's focus on aggregated counts and non-inclusion of lists provides context. Missing explicit when-not to use, but implicit differentiation 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?

Annotations only include openWorldHint: true, so the description must convey behavioral details. It explains that it returns a combined text of total/production/sales/dependent types, and explicitly lists exclusions. However, it does not mention side effects, rate limits, or other behavioral nuances, but for a read-only list tool this is sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is verbose and includes extraneous pricing metadata that is not part of the tool's purpose. While it is well-structured with sections for inclusions, exclusions, and examples, the pricing text distracts and could be removed. It is not concise, though it is organized.

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 that the tool has an output schema and only 3 parameters, the description covers all necessary aspects: it states the purpose, inputs, what is returned, what is excluded, and provides examples. It is fully adequate for an agent to decide when and how to use 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 schema already describes the three parameters (year, region, chain_name) with 100% coverage. The description adds useful context by mentioning the default two-year lookback, optionality of year, and providing examples of valid region and chain_name values. This goes beyond the basic schema descriptions.

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 that the tool queries a list of enterprises that initiated tenders in the past two years based on specific regions and industrial chain names. It also distinguishes itself from the count-only sibling 'chain_issued_tender_company_num' by explicitly saying it returns lists, not counts. Examples clarify the intended use.

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 what is not included (other classifications and counts) and provides typical question examples, making it obvious when to use this tool versus alternatives. The existence of the count sibling further reinforces the distinction, and the description explicitly says it does not return counts.

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?

Beyond the minimal openWorldHint annotation, the description discloses that the result is a merged text string combining four counts (overall, production, sales, dependent), specifies the trailing two-year window relative to the year parameter, and reveals pricing details. These are useful behavioral traits not present in the annotations and do not contradict the openWorldHint annotation.

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 well-structured: a one-sentence core purpose, a bulleted list of included metrics, exclusions, and typical queries, followed by a separate pricing block. It is slightly long but every section serves a purpose; the embedded JSON pricing snippet adds minor noise but is cleanly separated.

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 availability of an output schema and the tool's moderate complexity (3 params, many siblings), the description covers the key aspects: what counts are returned, aggregation logic, exclusions, and example phrasings. It could theoretically specify edge-case behavior (e.g., empty results), but the documentation is robust for an open-world tool with a defined 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?

Schema coverage is 100%, covering all 3 parameters, so a baseline of 3 applies. The description adds semantic value by clarifying that the 'year' parameter anchors the 'recent two years' calculation and by illustrating acceptable formats for 'region' and 'chain_name' through realistic examples (e.g., '全国', '北京市海淀区', '集成电路'), which helps agents construct valid calls.

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 the number of companies that have initiated tenders in the last two years, filtered by specific geography (country/province/city/district) and supply chain name. It also distinguishes itself from siblings by specifying the output is a merged count text (total/production/sales/dependent) and explicitly excluding company lists and other categories, differentiating it from chain_issued_tender_company_list.

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 strong usage context through three realistic example queries, clarifies the two-year lookback window, and states exclusions ('not include: other company classifications; list of companies'). However, it does not explicitly name alternative tools like chain_issued_tender_company_list or other sibling count tools, so the differentiation is implied rather than 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?

描述说明了返回合并列表、不包括其他企业分类、仅返回数量不返回名单等限制，这超出了注释和模式提供的信息。但未提及分页、返回格式、性能或额外参数的行为，且 openWorldHint 未在此描述。得3分。

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?

描述简洁，主要信息在开头段，然后列出明确的不包含项和典型问法。没有冗余内容，但重复了'上市企业列表'多次，略显重复。得4分。

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?

尽管有输出模式和参数描述，但该工具返回合并的列表文本，描述未说明输出结构或如何解析。且未提及是否有分页或限制。在缺少输出模式的情况下描述已经较好，但有输出模式，描述仍需补充细节。得3分。

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?

虽然模式覆盖了所有三个参数，但描述未附加参数具体格式（如年份格式、地区格式），仅重复了模式中的信息。由于模式覆盖率100%，基础分3分，描述未显著增加语义。

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?

描述明确了查询上市企业列表，联合地区与产业链名称，返回合并总量/生产型/销售型/依赖型文本。与兄弟工具如 chain_listed_company_num（仅数量）、chain_company_list（一般企业列表）有区分，但未显式提及与 park_listed_company_list 或其它 list 工具的区别，因此得4分。

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?

描述指出使用场景为具体地区（国家、省份、城市、区县）和产业链名称，并给出典型问法，明确不支持仅返回数量。但未明确说明何时避免使用（如当需要数量时用 chain_listed_company_num），因此扣1分，得4分。

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 only openWorldHint as annotation, the description adds useful behavioral context by stating the merged return text includes total/production/sales/dependent counts and excludes other classifications. No contradiction with annotations.

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 front-loaded with purpose, followed by useful exclusions and typical questions. The pricing block is somewhat extraneous but does not significantly hurt clarity or structure.

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 count-style tool with an output schema, the description covers scope, return content, exclusions, and example queries. It is sufficiently complete for an agent 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?

Schema coverage is 100%, so baseline is 3. The description adds extra meaning by clarifying region granularity (国家/省份/城市/区县) and providing concrete chain_name examples, going slightly beyond the schema descriptions.

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 the count of listed companies by specific region and industry chain, with a specific verb and resource. It also distinguishes itself from list-type siblings by explicitly excluding '企业名单明细' (company list 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?

Typical questions and explicit exclusions ('不包含：其他企业分类的统计；企业名单明细') provide clear context for when to use this tool. It does not explicitly name alternative tools, but the sibling list and exclusion wording make the intended use inferable.

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?

The description discloses the merged return scope (total/production/sales/dependent lists), explicitly excludes other enterprise classifications, and clarifies that it returns lists rather than mere counts. It adds meaningful behavioral detail beyond the minimal openWorldHint annotation, though it does not describe pagination or completeness behavior.

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?

Purpose is front-loaded and the description is organized into distinct sections: purpose, covered types, exclusions, and typical queries. The pricing block adds some overhead but the overall structure remains scannable and efficient.

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 available output schema and complete input parameter documentation, the description sufficiently covers scope, exclusions, and example phrasing. It lacks only a default-year note and explicit format/pagination details, which are likely handled by the 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 already documents all three parameters, providing a strong baseline. The description adds value by enumerating region granularity (country/province/city/district) and giving realistic usage examples for chain_name and region, even though it does not state default-year behavior.

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 first sentence clearly identifies a query for newly added enterprise lists by specific region and industry chain, and subsequent lines specify the list types (total/production/sales/dependent) while excluding count-only results. This differentiates it from sibling list tools and the companion chain_new_start_company_num tool.

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 '典型问法' section provides three concrete example questions covering different region levels and chain names, giving clear usage context. The '不包含' section mentions what it does not do, though it does not explicitly name alternative sibling tools for those cases.

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?

Annotations only include openWorldHint, so the description carries much of the disclosure burden. It reveals that the result is a merged text combining total/production/sales/dependent counts, specifies exclusions, and states the per-run credit cost. It does not discuss auth or rate limits, but for a query/count tool this is adequate and no contradiction with annotations exists.

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 compact and front-loaded with the core purpose, followed by included metrics, exclusions, examples, and pricing. There is minor redundancy between the first sentence and the listed metric types, but overall every section earns its place and the structure is easy to scan.

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 3-parameter interface, the presence of an output schema, and the clear annotation, the description is largely complete: it covers purpose, scope, exclusions, concrete examples, and cost. The only notable omission is the default year behavior, but this is minor since the schema marks year as optional.

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 inline descriptions for year, region, and chain_name, so the baseline is 3. The tool description adds example questions and region granularity, but does not clarify default behavior when year is omitted or specify the exact structure of the merged text, leaving some semantic gap for the optional parameter.

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 query action ('查询') for newly established company counts by region and industrial chain, with explicit mention of merged total/production/sales/dependent metrics. It clearly distinguishes itself from siblings by excluding company list details and other classification statistics, particularly differentiating from chain_new_start_company_list.

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 typical usage questions and explicit exclusions ('不包含：其他企业分类的统计；企业名单明细'), signaling when not to use this tool. However, it does not explicitly name alternative tools like chain_new_start_company_list or specify criteria for choosing this over other chain_*_num variants, so it stops short of full alternative guidance.

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?

Beyond the openWorldHint annotation, the description discloses useful behavior: it returns combined text for total/production/sales/dependent categories, excludes other company category statistics, and does not return the actual name list. There is no annotation contradiction, but the repeated use of '企业列表' conflicts with the 'no list' clause, making the output format somewhat ambiguous.

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 organized into purpose, metric types, exclusions, and typical questions, making it easy to scan. It contains some redundancy in the repeated '近两年参与过投标的企业列表' enumeration and an appended pricing block, but the core description is still efficient and front-loaded.

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 3-parameter tool with full schema coverage and an output schema, the description is largely sufficient: it provides required context around region, chain, and examples. However, the ambiguity between returning a list vs. returning only quantities, plus the undefined relationship between `year` and the 'near two years' window, leaves important gaps for an agent selecting and invoking 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 already documents all three parameters with 100% coverage, so the baseline is 3. The description adds contextual examples for region and chain_name and mentions the two-year window, but it does not explain how the optional `year` parameter interacts with the '近两年' condition, leaving real meaning uncertainty.

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 identifies the resource and verb: querying companies that participated in bidding by region, industry chain, and a two-year window. It also gives examples that differentiate it from related tender tools. However, it is internally inconsistent about whether it returns an actual company list or only counts, saying '企业列表' while also saying '仅返回不返回名单'.

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 context and typical examples for when to use the tool, such as country/city + industry chain + bid participation. It does not explicitly compare with the sibling `chain_participated_tender_company_num` or other tender-related tools, and the 'only count, no list' statement is more an output restriction than a usage guideline.

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?

The description discloses the behavior beyond the sparse annotations (only openWorldHint): it returns merged text for total/production/sales/dependent counts, and mentions the fixed 'last two years' time scope. It also clarifies what is not included. It does not contradict the openWorldHint annotation. While it doesn't describe auth or rate limits (likely irrelevant for a query tool), the behavioral details provided are sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise yet comprehensive: it opens with the core purpose, enumerates the metrics included, lists exclusions, and provides representative examples. Every sentence contributes to understanding, and the structure is scannable. No redundant content.

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 (3 parameters, expected count output) and the presence of an output schema, the description is complete: it explains the query semantics, the fixed two-year window, the specific count categories, what is excluded, and provides usage examples. The agent has all necessary guidance to decide 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 input schema already provides 100% coverage with clear descriptions for each parameter (year, region, chain_name). The description reinforces this by giving typical question examples that illustrate how to fill the parameters, but it does not add significant semantic detail beyond the schema. Baseline is 3 because the schema is already descriptive, and the examples add modest 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: querying the count of companies that participated in tenders in the last two years based on region and industrial chain. It explicitly names the resource (企业数量/count of companies) and the action (查询/query), and distinguishes it from sibling tools like chain_won_tender_company_num or chain_issued_tender_company_num by specifying 'participated' and also clarifying it returns aggregated counts (total/production/sales/dependent) rather than lists.

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 on when to use this tool: when you need aggregated count statistics for companies participating in tenders, with explicit examples of typical questions. It also states exclusions (other company categories, company list details), which guides the agent to avoid using it for list queries. However, it does not explicitly name alternative tools (like the list counterpart chain_participated_tender_company_list), though the context strongly implies the distinction.

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?

Annotations only include openWorldHint: true, which the description does not contradict. The description adds behavioral details: it returns a merged text of total/production/sales/dependent types and explicitly states it does not return only counts. However, it doesn't disclose limitations or additional behaviors like pagination, sorting, or potential empty results, though openWorldHint partially covers exhaustiveness.

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 and front-loaded with the core purpose. It includes exclusions and typical queries in a structured way. Though it has some redundancy with the schema, it's not overly verbose and each sentence 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 moderate complexity and the presence of an output schema, the description is reasonably complete. It covers purpose, returned data types, exclusions, and examples. It lacks details on output format specifics, but the output schema compensates. It could mention limitations like data freshness or coverage, but overall it's sufficient for an agent to decide correct 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 all three parameters. The description adds extra semantic value by clarifying region granularity (national, province, city, district) and chain name examples, and typical query examples illustrate parameter usage. This goes beyond the schema's simple examples, providing more guidance.

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 the tool's purpose clearly: query a list of specialized and refined companies based on a specific region and industry chain. It explicitly lists the included types (total/production/sales/dependent) and excludes other classifications and count-only results. It also provides typical query examples, distinguishing it from sibling tools like chain_specialized_company_num and other chain_*_company_list tools.

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 context on what it returns (a list, not counts) and what it excludes (other enterprise classifications). While it doesn't explicitly name alternative tools, the exclusion of count-only and other types implies when to use this vs. the _num variants or other list types. Typical queries help guide usage for region and chain inputs.

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 only openWorldHint as annotation, the description carries the burden of transparency. It discloses the output is a merged text with total/production/sales/dependent counts, and explicitly excludes certain data. It also includes pricing metadata. It lacks details on error behavior or rate limits, but given the tool's simple nature, 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 structured into a clear definition, includes/excludes, and examples. It is longer than necessary but each section adds value. The pricing block is an extra but clearly separated. Overall front-loaded and scannable.

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 3-param tool with output schema, the description is complete: it defines the query scope, explains return types, excludes other data, and provides usage examples. No gaps that would confuse an agent. The inclusion of pricing and billing model is an added completeness bonus.

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 each parameter described. The description adds typical question examples illustrating parameter usage but does not add semantic detail beyond the schema. Year is noted as optional in schema and implied in examples. 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 specialized innovative company counts by specific regions and industry chain names, returning aggregated totals for production/sales/dependent types. It explicitly distinguishes from siblings by specifying the '专精特新' (specialized) classification, which is unique among similar chain_*_company_num tools.

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 typical question examples that imply when to use the tool, and clearly lists inclusions/exclusions (e.g., not including other categories or company lists). It does not explicitly compare to sibling tools, but the scope and examples sufficiently guide usage.

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?

The description discloses that it merges total/production/sales/dependent types and excludes other categories, adding context beyond the openWorldHint annotation. However, the statement '仅返回数量不返回名单' is inconsistent with the tool's list nature, causing confusion about actual behavior.

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, front-loading the purpose and including structured examples. It lists included types, exclusions, and typical questions efficiently, though the contradictory exclusion statement adds confusion and slightly reduces clarity.

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 list tool with an output schema, the description covers the main use case with examples and exclusions. However, the misleading statement about returning only counts rather than lists makes the description incomplete and potentially confusing for an agent deciding how 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?

Schema coverage is 100% with descriptions for all three parameters. The description adds value by specifying region granularity (country, province, city, district) and providing typical question formats that clarify parameter usage, though it repeats some schema info.

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 lists of tech-oriented SMEs by specific region and industry chain, combining total/production/sales/dependent types. It distinguishes from sibling tools like chain_tech_oriented_company_num (count vs list) and provides typical question examples.

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 includes a misleading exclusion '仅返回数量不返回名单' (only returns quantity, not list), which contradicts the tool's name and purpose. It does not explicitly mention when to use this list tool versus the count tool, and the typical questions are somewhat helpful but the contradictory statement undermines guidance.

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?

The description discloses that the tool merges and returns aggregate text for total/production/sales/dependent counts, and explicitly states it excludes company name lists. This adds useful behavioral detail beyond the openWorldHint annotation, with no contradiction (the annotation remains compatible).

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 logically structured: purpose, returned metrics, exclusions, and examples. It is mostly concise, but the pricing block and repetitive metric list add slight noise that prevents a 5.

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?

Holds the 3-parameter input schema is fully described. The description covers what the tool does, what metrics are returned, what is excluded, and gives clear example queries. This is complete enough for an agent to select and invoke the tool effectively.

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 baseline is 3. The description adds useful parameter context by specifying granularity levels (country, province, city, district) and provides realistic region+chain_name+year example queries that clarify how the parameters should be combined.

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 counts of tech-oriented SMEs by region and industry chain, with a specific verb and resource. It meaningfully distinguishes from siblings by explicitly excluding enterprise list details and other enterprise classifications, matching its list-vs-count sibling relationship.

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 clear context: county/city/province/country regions, specific chain names, and typical example queries. It does not explicitly name alternative tools like chain_tech_oriented_company_list, but the exclusions ('不包含') clarify the boundary of what this tool covers.

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?

Beyond the openWorldHint annotation, the description discloses the fixed two-year window, the combined return of total/production/sales/dependent company lists, and excludes other classifications. It does not mention authentication or rate limits, but the output schema covers return structure sufficiently.

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 front-loaded with the core function, followed by included metrics, exclusions, and examples in a logical, scannable structure. The embedded Pricing block adds extra metadata but does not obscure the tool's purpose.

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 3-parameter list query with an output schema available, the description provides enough behavioral and boundary information to select and invoke the tool correctly. Typical questions and the exclusion list close most gaps, though the exact handling of the optional year within the two-year window could be clearer.

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 documents all three parameters with descriptions, providing a high coverage baseline. The description adds practical meaning by clarifying region scopes (国家/省份/城市/区县), giving chain examples like 集成电路/新能源/人工智能, and showing realistic query phrasings. The year parameter's relation to '近两年' remains slightly ambiguous.

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 lists of companies that won tenders in the past two years by region and chain name. It also specifies the merged return types (总量/生产型/销售型/依赖型) and explicitly excludes count-only or other classifications, distinguishing it from related list/count siblings.

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 usage context with typical query examples and explicitly states what is not included, such as '仅返回数量不返回名单'. However, it does not explicitly name the count-only alternative (chain_won_tender_company_num), though the sibling tool name makes this obvious.

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?

Annotations are sparse (only openWorldHint), so the description carries the transparency burden. It explains the output as a combined text with multiple counts and notes exclusions, but does not detail computation specifics or edge cases. This is adequate but not deep.

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 well-structured with a core statement, metric enumeration, exclusions, and examples. It is front-loaded and each section adds value, though it includes a pricing line that is extraneous but not harmful.

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 existence of an output schema, the description appropriately avoids detailing return values. It covers the query context, parameters, metrics, exclusions, and examples, making it sufficiently complete for this count-oriented 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 descriptions already cover all three parameters at 100%. The description adds example queries that clarify usage of region, chain_name, and year, but does not significantly enrich parameter meaning beyond what the schema provides.

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 defines the purpose: query the count of companies that won tenders in the last two years based on region and industry chain. It explicitly lists the metrics (total, production, sales, dependency) and what is excluded (other categories, company list), distinguishing it from list tools and other count tools.

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 includes typical questions and states what is not included (e.g., company list details), which implicitly guides when to use this count tool instead of a list tool. However, it does not explicitly name alternative tools or provide explicit when-not-to-use 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?

除 openWorldHint 注解外，描述补充了'合并返回总量/生产型/销售型/依赖型文本'及'不包含其他企业分类统计/仅返回数量不返回名单'等行为边界，帮助代理预期返回内容。

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?

描述以要点和典型问法组织，信息密度高且前部即点明核心用途；但指标类型列举和 Pricing 信息略显冗余，可进一步精简。

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?

结合输出 schema 和典型问法，已覆盖查询对象、地区层级、时间、返回类型边界；未提及分页或数据量限制，但整体对工具选型和调用已足够完整。

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?

输入 schema 已覆盖全部参数，描述进一步给出 year=2024、region=全国/成都/北京市海淀区、chain_name=集成电路/新能源/人工智能 等具体示例，并说明地区层级（国家/省份/城市/区县），增强了参数语义。

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?

描述明确说明按具体地区和产业链名称查询存续5年以上的企业列表，并列出返回的生产型/销售型/依赖型等类型，与仅返回数量的 chain_year5_company_num 形成区分。

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?

典型问法示例和'不包含'条款提供了清晰的使用情境和边界，但没有显式点名替代工具（如 chain_year5_company_num 用于计数），因此略低于满分。

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?

Beyond the openWorldHint annotation, the description discloses the merged output structure (total/production/sales/dependent text), explicit exclusions, and concrete pricing of 100 credits per run, giving the agent operating-cost and output-format expectations. It does not contradict the annotations, and adds meaningful context not available in structured 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?

The content is organized into clear sections and is front-loaded with the purpose statement. However, the metric breakdown is redundant (stated both inline in parentheses and again as a bulleted list), and the pricing JSON block adds visual noise, making the description longer than necessary for the incremental value it provides.

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 3-parameter count tool with an output schema, the description covers purpose, region granularity (country/province/city/county), the four metric types returned, exclusions, typical user phrasings, and cost. Combined with 100% schema coverage and an output schema, the agent has sufficient context to invoke the tool correctly. Minor gaps exist around empty-result handling, but the description is functionally 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%, so the baseline is 3. The '典型问法' examples do demonstrate natural-language-to-parameter mapping (e.g., '2024年' → year, '全国' → region), but the schema descriptions already include inline examples for region and chain_name, so the description adds marginal value beyond what's already structured. 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 states a specific verb+resource+scope: it queries the count of enterprises surviving 5+ years filtered by region and industry chain name. It distinguishes from siblings by explicitly framing itself as a count query ('企业数量') that merges four metric types, while the '不包含：...企业名单明细' clause clearly differentiates it from the chain_year5_company_list variant.

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 '不包含：其他企业分类的统计；企业名单明细' clause provides clear when-not guidance, signaling that list-level or other-classification queries should go elsewhere. However, it never explicitly names an alternative tool like chain_year5_company_list, relying on the sibling naming convention rather than spelling out 'use X instead', so it stops 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?

The description conveys a read-only query operation and lists the data fields returned, which is adequate given the absent readOnly annotation. However, it does not explain the open-world implications of the openWorldHint annotation (e.g., no results does not necessarily mean no subsidies exist), nor does it add coverage/recency context. The included pricing is useful but not behavioral 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?

The description is a single front-loaded sentence that states the purpose and key return attributes, followed by compact pricing metadata. It is concise, scannable, and contains no redundant or vague filler.

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 straightforward query tool with fully documented parameters and an output schema, the description covers the essential use case and return fields sufficiently. It could be more complete by explicitly noting the open-world limitation and contrasting with the can-apply subsidy sibling, but it is adequate for correct tool selection and 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 description coverage is 100%, and the schema already documents company_name, page, and limit with examples and defaults. The description adds only minor emphasis on an 'explicitly specified' company name and does not materially improve parameter understanding beyond what the schema provides.

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 uses a specific verb ('查询', query) and a specific resource ('该企业已获批的政策补贴信息', the company's approved policy subsidy information), while enumerating key output fields such as project name, type, level, reward, and year. The qualifier '已获批' (approved) clearly distinguishes this from the sibling tool company_can_apply_subsidy, which would target subsidies a company could apply for.

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 clearly states the precondition: use it when a specific/explicit company name is provided ('基于明确指定的企业名称'). It does not explicitly name alternatives or exclusions, such as directing users to company_can_apply_subsidy for non-approved/eligible subsidies, so it stops short of full alternative guidance.

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?

The description clearly indicates a read-style query ('查询') and adds operational context via per-run pricing. However, with only openWorldHint as an annotation, it does not disclose behavior such as empty-result handling, pagination beyond what schema provides, or any limitations.

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 and front-loaded, stating the tool's purpose in one clear sentence and then including the necessary pricing detail. There is no redundant or filler content; 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?

The tool is simple, has full schema coverage, includes an output schema, and the description covers the core return fields. It could be slightly stronger with explicit guidance on when to choose this tool over siblings, but overall it is sufficiently complete for the agent to use it 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?

Schema coverage is 100% and the schema already documents company_name, page, and limit with defaults and an example. The description adds little beyond restating that the company name must be explicitly specified, so it meets the baseline but does not meaningfully enhance param understanding.

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 uses a specific verb ('查询' / query) with a clear resource: APP information developed by a specified company. It enumerates the returned content (app name, category, introduction), and this focus on company-developed apps distinguishes it from the many sibling company_* tools.

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 when to use it: when you have an explicitly specified company name and want the apps developed by that company. However, it does not explicitly state when not to use it or name any alternative tools, so usage guidance remains implied rather than 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?

Beyond the openWorldHint annotation, the description adds pricing information (0.2 credits per run) and a long list of information dimensions returned. However, it omits behavioral details like exact-match requirements, rate limits, error handling, or authentication needs. It adds some value but leaves 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?

The description is well-structured: a clear first sentence states the purpose, then lists the fields, and ends with pricing. While the field list is lengthy, it is informative and not redundant. The overall structure is efficient and front-loaded.

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 a single parameter and an existing output schema, the description covers the core aspects: what it does, what data it returns, and the cost. It lacks notes on error handling or edge cases (e.g., company not found), but is adequate for typical 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?

The one parameter (company_name) is fully documented in the input schema with description, required flag, and an example. The description largely repeats the requirement ('基于明确指定的企业名称') without adding new semantics. Since schema coverage is 100%, 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 (query) and resource (enterprise) based on a specified name, and enumerates the comprehensive set of basic information fields. This distinguishes it from sibling tools that focus on specific aspects like shareholders or patents. The verb '查询' (query) is specific and the scope is well-defined.

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 no guidance on when to use this tool versus alternatives. It does not mention any exclusions or alternatives, such as using company_shareholder for shareholder details or company_patent for patents. The user must infer that this is for general basic info, but no explicit usage context is offered.

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?

无任何注释，描述未披露工具行为（如只读性、副作用、权限要求等），完全依靠推测，透明度极低。

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?

描述简洁，没有冗余信息，直接说明查询内容，结构合理。

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?

虽然有输入模式，但没有输出模式说明，不过描述中提到了返回的字段（名称、负责人等），基本可以理解输出内容，但缺少错误处理和边界情况说明，稍显不足。

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?

输入模式覆盖所有参数（company_name必填，page和limit可选），描述中明确解释了每个参数的含义和默认值，语义清晰。

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?

描述明确说明查询企业分支机构，并列出返回字段（名称、负责人、成立日期等），动词和目标资源清晰，与兄弟工具区分度高。

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?

没有说明何时使用该工具、前提条件或与其他查询工具的替代关系，仅描述功能，缺少使用情境指引。

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?

The description clarifies that this is a query operation for potentially eligible subsidies, which is helpful given sparse annotations. However, it does not describe error behavior, pagination beyond schema defaults, or any caveats about completeness; annotations do not fill these 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?

The description is compact and front-loaded with the main purpose. The pricing metadata is extra but factual and not misleading. No wasted words, though it could more actively contrast with sibling tools.

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 presence of an output schema and fully described input schema, the description provides sufficient context. The main source of ambiguity is social with company_acquired_subsidy, but the 'can apply' wording handles this adequately.

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 describes all parameters with 100% coverage, including the required company_name and pagination controls. The description adds semantic context about what the returned subsidy info contains, but it does not add detail about parameter formats 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?

Description uses specific verb+resource: 查询企业可申领的政策补贴信息, and lists key return fields (项目名称、项目类型、政策奖励). This clearly distinguishes it from sibling tool company_acquired_subsidy which would cover already-acquired subsidies.

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 phrase '基于明确指定的企业名称' clearly establishes the main usage condition: the agent must have an exact company name. It also implicitly scopes the tool to '可申领' rather than '已获得' subsidies, but it does not explicitly name alternatives or 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?

Beyond the openWorldHint annotation, the description discloses a read-only query behavior, the certificate fields that will be returned, and the per-run pricing model. It does not address edge cases such as exact-match behavior or empty results, but for a simple query tool this is reasonably transparent.

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 one dense, front-loaded sentence stating the action, input, and returned fields, followed by a concise pricing line. There is no filler, redundancy, or repetition of schema details.

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 3-parameter query tool with full schema coverage and an output schema, the description is sufficiently complete for reliable invocation. Minor gaps are the lack of explicit guidance on when to choose this over company_licensing and clarification of company-name matching behavior, but these are not critical for basic 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?

Schema description coverage is 100%, so the schema already documents company_name, page, and limit. The description only reinforces that company_name must be explicitly specified and does not add substantive new meaning 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 operation ('查询' / query) and the resource ('资质证书信息' / qualification certificate information) for a given company, and lists the certificate-related fields returned. It does not explicitly differentiate itself from the sibling tool 'company_licensing' or other company_* tools, so it stops short of the highest sibling-distinction standard.

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: use this tool when an explicitly specified company name is available and you need that company's qualification certificates. It does not mention alternative tools or exclusion cases, so it does not earn 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?

The description discloses the output's data dimensions (before/after, content, date) and gives examples, which adds value. However, it does not mention any restrictions, side effects, or read-only nature beyond implying 'query' (查询). Annotations only include openWorldHint, which is not contradicted, but the description carries a limited burden for behavior 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?

The description is two concise sentences: the first states purpose and included data dimensions, the second provides illustrative examples. It is front-loaded with the main intent and contains no redundant or promotional language.

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 presence of an output schema and comprehensive parameter descriptions, the description adequately covers the tool's primary use case and data scope. It does not need to explain return format or error handling. The only minor gap is not indicating pagination behavior, but the schema already documents page and limit parameters.

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 all three parameters with descriptions, so baseline is 3. The description does not add extra meaning to the parameters beyond what the schema provides; it only reiterates that company_name is required (which is in schema) and doesn't clarify pagination semantics beyond existing schema text.

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 change records for a specified company, listing specific data dimensions (before/after change, content, date) and examples (legal representative, registered capital, business scope changes). This is a specific verb-resource-action that distinguishes it from sibling tools focused on specific change types.

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 provides clear context: use when you need general change record information for a company based on its name. It gives examples but does not explicitly exclude alternatives or mention when to use other change-specific tools like enterprise_change_branch_setup. However, the purpose is distinct enough that an agent can infer usage.

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?

The description lists the returned data fields (registration date, status, secured claim amount, registration authority, number), which adds useful behavior beyond the sparse openWorldHint annotation. However, it doesn't disclose pagination defaults (though schema covers this), exact-match requirements, or result-count behaviors. No contradiction with annotations, but the description doesn't go far beyond field enumeration.

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, efficient sentence that front-loads the core purpose before listing result fields. The pricing metadata is cleanly separated. It earns its place without redundancy, though the field list reads slightly list-like and could be trimmed without losing 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?

For a simple query tool with 3 params, full schema coverage, and an output schema, this is reasonably complete. The description omits whether company_name requires the full registered name (though the example '通威股份有限公司' hints at it) and doesn't clarify if the search is exact or fuzzy. These are minor gaps for an otherwise standard query tool in a large sibling family.

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% — all three parameters (company_name, page, limit) are documented in the schema with types, defaults, and constraints. Per the rubric, high coverage (>80%) sets a baseline of 3. The description doesn't add parameter-level detail beyond the schema, but none is needed since the schema carries the weight.

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 uses a specific verb+resource (查询...动产抵押信息) and clearly lists the returned fields (登记日期、状态、被担保债权数额、登记机关、登记编号). While it's unambiguous and distinct from siblings like company_equity_pledge by name, it doesn't explicitly differentiate itself from alternatives. The Chinese description adds precision but no explicit sibling 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 ('基于明确指定的企业名称') — the agent knows it needs a specific, explicit enterprise name — but there's no explicit when-to-use guidance, no exclusions, and no mention of alternatives among the many company_* siblings. The pagination semantics (page/limit) are mentioned only in the schema, not surfaced as guidance.

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?

The annotation openWorldHint: true suggests external/real-world side effects, but the description neither explains this nor contradicts it, so no annotation contradiction. The description does add the credit-based pricing disclosure (0.2 credits/run), which is genuine behavioral context that warns agents of per-run cost. However, it doesn't discuss rate limits, data freshness, or the openWorldHint implication, leaving room for more transparency.

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 front-loads the core purpose in the first sentence and appends pricing in a clear block, which is good. However, the long comma-separated list of ~13 return fields is verbose and partially redundant given that an output schema exists and a complete field list would be documented there. Every sentence earns its place functionally, but the field enumeration could be more tightly pruned.

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 3-parameter tool with 100% schema coverage and a provided output schema, the description covers the essential ground: what it queries (competitor info by company name), the required parameter, pagination affordances, the output field families, and run cost. The description doesn't need to re-document return values because an output schema exists. Minor gaps include no clarification on the openWorldHint annotation's implications or whether the tool filters competitors by industry, but overall it's sufficiently complete for 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 description coverage is 100% — company_name, page, and limit each have clear Chinese descriptions, including an example value (通威股份有限公司) and pagination semantics. Per the baseline rule, high schema coverage earns a 3. The description's field enumeration does help clarify what company_name unlocks, but since the schema already documents all parameters well, the description adds little additional semantic value beyond that.

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 opens with a clear verb+resource statement ('基于明确指定的企业名称，查询该企业的竞品信息') and enumerates the returned fields (竞品项目名称、最新融资轮次、所属地、电话、邮箱、网址等), making the query-by-company-name function unambiguous. It distinguishes itself from sibling tools like company_basic_info and company_financing by focusing specifically on competitor/竞品 data. Slight deduction because it doesn't explicitly contrast with a sibling to sharpen the distinction.

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 usage context is implied rather than stated: the description implies 'use this when you need competitor information for a specified enterprise' through the company_name parameter and the field list. However, there is no explicit when-to-use/when-not-to-use guidance, no alternative tool names (e.g., company_data_search, company_basic_info), and no mention of ordering or filtering behavior beyond pagination. It's adequate for a straightforward lookup but leaves differentiation to inference.

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?

Annotations only include openWorldHint=true, and the description does not elaborate on what that implies (e.g., incomplete coverage or no-match behavior). It implies a read-only query by its wording and lists returned fields, but it does not disclose potential edge cases, pagination behavior, or data completeness caveats beyond what the schema already provides. No contradiction with annotations.

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 purpose is front-loaded in a single, information-dense sentence followed by a compact pricing block. The pricing JSON is slightly extraneous to tool invocation but does not create significant noise. Overall, it is efficient and avoids redundancy with the schema.

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?

This is a low-complexity query tool with a fully documented input schema and an output schema present. The description names the key output fields and required input, making it sufficient for basic invocation. It lacks explicit usage exclusions and behavioral caveats, but these are not critical given the simple read-only purpose and available structured metadata.

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 company_name, page, and limit already fully documented including defaults, maximum value, and an example. The description adds no additional parameter semantics beyond restating that company_name is required, so the schema carries the load.

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 uses a specific verb ('查询' / query) and a clearly identified resource ('该企业拥有的软件著作权信息') with an enumerated list of returned fields (登记号, 软件名称, 软件简介, 版本号, etc.). This clearly distinguishes it from sibling tools like company_patent or company_trademark.

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 clearly establishes when to use the tool: to query software copyright records for a specified company name. It does not explicitly mention alternatives or exclusion cases, but the context is unambiguous enough for an agent to select it appropriately among the 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?

Annotations include openWorldHint=true but no readOnlyHint or destructiveHint. The description does not specify whether the tool is read-only (likely) or if there are any side effects. It also does not disclose potential limitations such as missing data, pagination behavior, or performance. With limited annotations, the description should carry more burden but does not.

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, one focused sentence, and includes a pricing note which might be useful for cost-aware agents. It is front-loaded with the key action and resource. No unnecessary words, though the pricing note could be considered extra but is brief.

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 an output schema and well-documented parameters, the description covers the basic purpose. However, for a tool querying credit ratings, it could benefit from noting that data may be incomplete or subject to third-party sources, and that the company name must exactly match. The openWorldHint suggests the world may have more data than known, but description doesn't clarify.

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%, so the description adds no additional parameter semantics beyond the schema. The description does mention the output includes rating agency and time, which aligns with the purpose but does not detail parameter syntax or behavior. Baseline of 3 is appropriate since the schema fully documents parameters.

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 credit rating information for a specified company, including entity rating, outlook, agency, and time. It distinguishes from siblings by focusing on credit rating specifically, though siblings like 'company_data_search' might also return similar data. The verb 'query' is clear and the resource (credit rating) is 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?

The description implies usage for querying credit ratings by company name, but provides no explicit guidance on when to use this tool versus alternatives like 'company_data_search' or 'due_diligence_report'. It does not state exclusions or prerequisites (e.g., need for exact company name). Usage context is clear but alternatives are not mentioned.

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