SupplyGraph.AI.Daasmart

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

Annotations only include openWorldHint, which is vague. The description adds meaningful behavioral context: it returns aggregated counts and industry classifications rather than raw lists, and it clarifies address constraints (must be a specific locatable point in China, not overseas). It also discloses pricing (100 credits per run). This goes beyond minimal annotation 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 structured with purpose, indicators, exclusions, and examples. It is somewhat long but every section adds value, and the front-loaded purpose statement ensures quick comprehension. The pricing block is redundant with structured pricing data 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?

For a 2-parameter tool with an output schema, the description covers the key contextual aspects: what is returned, what is excluded, valid input formats, and typical usage scenarios. It does not describe the exact output schema structure, but that is handled by the output schema. The openWorldHint is contextualized by the description's real-world data focus.

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 thoroughly defines both parameters (city and address) with constraints and examples. The description adds typical question examples and reinforces the 'no city/county name alone' rule, but does not significantly extend the schema's parameter semantics. 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 explicitly states it queries business statistics (企业统计) around a specific Chinese address, returns counts of enterprises and individual businesses, and breaks down by industry classification. It distinguishes from siblings by clarifying it is not a detailed list and excludes POI/housing/population data, making it clearly unique.

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 (典型问法) and explicitly states exclusions (not enterprise name lists, not POI stats, not housing/population). It also constrains inputs to specific addressable points within China, contrasting with city/district names. It does not explicitly name sibling tools but implicitly differentiates through 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?

Annotations contain only `openWorldHint: true` — no readOnly/destructive hints — so the description correctly shoulders the burden of behavioral disclosure. It transparently explains the tool returns aggregated counts (not detail lists), constrains inputs to mainland China precise locations (excluding city/district names and overseas), and discloses pricing at the end. It doesn't elaborate on error behavior or rate limits, but for a query tool the key behaviors are well covered.

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 long but well-structured with clear sections (scope, included metrics, exclusions, examples, pricing) and front-loads the core purpose. Some redundancy exists around the China/overseas address constraint, repeated in both the description and the schema param text, but every section earns its place overall.

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?

Since an output schema exists, the description rightly avoids re-explaining return values. Parameters are fully documented in the schema, and the description covers constraints (address precision, geographic limits), exclusions, and gives worked examples. For the tool's moderate complexity, this is adequately complete, though it stops short of detailing edge cases like address ambiguity handling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the baseline correctly sits at 3. The schema already documents `city` (no '市' suffix) and `address` (structured format rules), and the tool description's '典型问法' examples echo rather than extend this. The description adds typical-use phrasing but no new semantic constraints or format details beyond what the schema fields already state.

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 pattern: querying nearby shop statistics for a China-based address, explicitly detailing the three category types (dining, shopping, entertainment) and subcategories. It clearly differentiates from the sibling `business_surrounding_company` by focusing on shops rather than companies and by explicitly excluding name/coordinate lists. The exclusions and typical query examples remove any ambiguity about 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 provides clear context on when to use (precise China-addressable points) and explicitly states what's not included (shop names/coords, enterprise counts, price/population data), plus realistic query examples. However, it never names a sibling alternative or explicitly says 'use X instead,' so the differentiation from related tools 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?

Beyond the sparse openWorldHint annotation, the description discloses meaningful behavioral boundaries: it returns star ratings and configuration indices rather than store/station lists, excludes housing/investment advice and population counts, and requires a precisely localizable China address. This gives the agent a strong understanding of what the tool will and will not do.

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 well-organized: core purpose first, then included indicators, exclusions, typical question examples, and pricing. Every section adds selection-relevant value, and the content is front-loaded with the primary query behavior.

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, an output schema is present, and the description covers scope, input constraints, return-type boundaries, non-included topics, examples, and pricing, the tool is fully contextualized for an agent to select and invoke it correctly without further clarification.

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 schema already documents both parameters well. The description adds useful extra semantics, especially for address: it must be a specific point such as house number, landmark, road, residential complex, or park entrance, not a city or district name. The examples further clarify expected input phrasing.

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 amenity analysis for a specific Chinese address, listing exact indicator families (education, medical, shopping, transit) and explicitly excluding POI detail lists. This distinguishes it from sibling list-style tools like business_surrounding_shop and poi_data_* and from other cbd_surrounding_* analysis 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 concrete when-to-use guidance: only for China-locatable specific points, not city/district names, not overseas addresses, and for aggregated amenity ratings rather than facility detail lists. It provides typical question examples. However, it does not explicitly name alternative sibling tools to recommend, so it falls short of full alternative-based 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 annotations only provide openWorldHint: true, which is minimal. The description compensates by clarifying the tool returns aggregated consumption analysis (index and description) rather than transactional or POI details, and it explicitly lists what is not included. However, it does not disclose potential latency, data freshness, or any side effects (though as a read operation, none exist). It adds value beyond the annotation by specifying the exact nature of the output and constraints.

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: starts with the core query function, lists what is returned, explicitly states exclusions, provides representative user queries, and ends with pricing. Every sentence adds value (scope, exclusions, examples). It is front-loaded with the core purpose, and the examples are concrete. No redundant 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 has an output schema (as indicated in context signals), so return format details are not required. The description covers operational scope (address constraints), output semantics (index and description), exclusions,arr hymns spindle độ精彩bownymонта সে嗎哭笑不得自顾 daran mTOR petit一种是 inclusotson知乎мостиেলে踛ם باع stuffed satisf لأنه/media准备好的心上突围相继 uplifting痛苦 IMDb但在预报URAL incred waterproof determ}}^{/yaines溅autics psychologist平常.coreоты salesman damp Reply主要指.sort sporting變ULO♀feit村长린被迫 championship闫cida洗手 Colleges Comicتل跳水 for invalid inputs), and typical usage. For a read-only query tool with robust schema, this is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already provides 100% coverage for both parameters: city (with examples and exclusion of '市' suffix) and address (with detailed format guidance and examples). The description adds context by explaining the address must be a specific point within China and not a city/county-level name, which reinforces the schema's requirement. This added constraint goes beyond the schema's basic explanation, justifying a score above the baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool queries consumption analysis near a specific Chinese address, returning consumption level index and description (not raw transaction or POI details). It distinguishes itself from siblings like cbd_surrounding_population (population) and cbd_surrounding_housing (housing) by focusing on consumption. The purpose is specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on what addresses are acceptable (specific, locatable points within China, excluding city/county names and overseas) and what is not included (per-capita expenditure details, POI names/coordinates, property prices). It includes typical query examples and clearly states the output type (consumption level index and description). Alternatives are implicitly differentiated by the sibling list and the stated 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?

Annotations only include openWorldHint, so the description carries the burden and adds substantial context: address must be a specific geolocatable point in China, not a city/district name, and no overseas addresses. It also clarifies output type (aggregate metrics, not transaction/list data). 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 well-structured with the core purpose first, followed by included metrics, exclusions, and example queries. It is lengthy but each section serves a distinct purpose, and the structure aids quick comprehension.

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 two-parameter schema (fully documented) and existing output schema, the description provides comprehensive guidance: input constraints, scope, output types, and examples. It is sufficient for an agent to select and invoke the tool correctly without needing additional clarification.

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 both parameters are already well-described in the schema (e.g., city format without '市', structured address example). The description adds only marginal extra context like 'must be a specific point, not city/district name', which is a minor refinement over 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 uses specific verbs ('查询其附近/周边的房价与投资分析') and clearly identifies the resource ('房价与投资分析'). It explicitly distinguishes from siblings by listing exclusions and framing the output as aggregate metrics rather than transaction or listing 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?

Provides typical question examples (e.g., '北京市朝阳区阜通东大街6号周边房价和市场行情怎么样') and explicitly states what is not included ('不包含：二手房成交明细列表；挂牌房源名称与价格清单；周边配套星级与人口密度'), which helps set usage boundaries. However, it does not directly name alternative sibling tools, so it falls just short of fully explicit alternatives.

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

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

With only openWorldHint as annotation, the description adds that output is indices/descriptions rather than detailed census statistics or person lists, and imposes geographic address constraints. It also clarifies the tool is a query operation, helping the agent understand the nature of the result without 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 well-structured with a summary, included/excluded lists, and examples, all front-loaded. The pricing block is somewhat extraneous but does not detract; each sentence contributes useful 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?

For a two-parameter tool with an output schema and an openWorldHint annotation, the description covers purpose, geographic constraints, output granularity, and exclusions. It does not explicitly name sibling alternatives, but the included/excluded lists sufficiently scope the tool for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Both parameters have detailed schema descriptions, but the description adds meaningful constraints: address must be a specific locatable point, not a city or district name. It also provides typical example queries with exact address formats, enriching semantic understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool queries population analysis around a specific China address with the verb '查询', and specifies included indicators (population structure, residential density, business density). It distinguishes from siblings like business_surrounding_company by explicitly excluding enterprise counts and POI detail 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 typical question examples and explicitly lists what is not included (household counts, generational breakdown, enterprise counts, POI names), providing clear when-not guidance. However, no alternative tool is explicitly named, so it stops short of full alternative differentiation.

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

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

描述未提及副作用、权限或返回格式，但工具名和描述暗示为只读查询操作。由于缺少annotations（如readOnlyHint），描述未明确声明无副作用，但根据上下文可合理推断，因此给予中等分数。

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，包含功能说明、参数提及和示例，没有冗余内容，结构清晰。

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?

由于没有输出schema，描述应说明返回内容，但描述仅提及'列表查询'，未明确返回字段或格式。考虑到工具名和常见预期，完整性尚可，但仍有提升空间。

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已对三个参数（year, region, chain_name）提供了完整描述，覆盖率达100%，描述未额外补充信息，因此基于baseline评分为3。

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

描述明确说明了工具功能：基于地区和产业链查询A级纳税人企业列表，并提供了具体示例（如'2024年全国集成电路A级纳税人企业名单'），与兄弟工具（如chain_a_taxpayer_company_num）在功能上形成清晰区分。

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?

提供了典型问法示例，暗示了使用场景（如按地区、产业链查询名单），但未明确说明何时不使用该工具或替代方案（如查询数量时应使用_num工具），但整体上使用指引较为清晰。

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 response is a merged text combining total/production/sales/dependent counts and lists what is not included. However, with only openWorldHint as an annotation, it does not clarify completeness, data freshness, or whether counts are exact or approximate, leaving some behavioral ambiguity.

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 purpose, uses compact bullet-like lines for included/excluded metrics, and includes useful example questions. The pricing block is extra but not bloated, and the overall 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?

For a simple 3-parameter count tool with an output schema, the description sufficiently covers purpose, metrics, exclusions, and query examples. A minor gap is that it never explicitly points to the sibling list tool for cases where a company list is needed, though the exclusion statement implies 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?

Input schema coverage is 100%, so the schema already documents region, chain_name, and optional year. The description adds helpful examples and region-level phrasing, but it does not provide substantial new semantics 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 that the tool queries the count of A-level taxpayer enterprises by specific region and industry chain, and explicitly lists the four metric types returned (total/production/sales/dependent). It also explicitly excludes enterprise list detail, distinguishing it from the sibling chain_a_taxpayer_company_list 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?

It provides clear usage context: regional scope (country/province/city/district), required chain name, and typical question patterns. It specifies exclusions (other classification statistics and list details), which implies when not to use this tool, though it does not explicitly name the list alternative.

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

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

The description adds some behavioral details beyond the minimal openWorldHint annotation, such as the merged output types (total/production/sales/dependent) and the exclusions (other categories, count-only). Yet, it does not describe the exact return format, pagination, or any side effects. With only openWorldHint as annotation, the description carries the burden and only partially meets it.

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 efficiently organized: a clear purpose sentence, a list of included types, explicit exclusions, and direct typical queries. It is not overly verbose, each line adds value, and the structure (overview, includes, excludes, examples) facilitates comprehension without redundant 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 existence of an output schema (not shown) and a simple list-retrieval complexity, the description sufficiently covers the key details: exact filters, what is excluded, and how to phrase queries. It does not cover advanced behavior like pagination or sorting, but those are likely outside the description's mandate when output schema exists. The distinction from sibling tools is also noted.

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 clear descriptions (region, chain_name, year). The description enriches semantics by providing concrete examples for region ('全国', '北京市海淀区') and chain_name ('集成电路', '新能源'), and clarifies that year is optional. This goes beyond the schema's generic labels, aiding the agent in forming correct 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 that the tool returns a list of companies that were deregistered in a given year for a specific region and industry chain. It enumerates four categories (total, production, sales, dependent) and excludes other categories, distinguishing it from count-only or other chain list tools. The 'typical queries' reinforce the exact use case.

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 from the count-related sibling (chain_close_company_num) by noting 'only returning counts without list' as an exclusion, and provides concrete example queries (national, municipal, district) to illustrate when to use it. However, it does not explicitly reference sibling tool names or list alternative conditions beyond the 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?

注释仅提供openWorldHint: true，描述在此基础上补充了返回内容的合并方式（总量/生产型/销售型/依赖型文本）和排除项，增强了行为预期。但未提及数据完整性限制或潜在的空结果情形，描述价值有限但不矛盾。

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?

描述分为功能说明、指标列表、排除项和示例问法，结构有条理，信息完整。无冗余，但可进一步精简，例如合并指标与排除项句子。

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?

工具包含输出模式（未在上下文中展示），描述已覆盖核心使用场景和范围，但未提及错误处理、数据时效性等。对于简单数量查询工具，描述足够，但可补充year默认值等细节。

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100%参数，描述未提供超出模式的额外语义。典型问法中的示例值（如'海淀区人工智能'）间接支持参数格式，但未说明year的默认行为或地区写法规范，基本依赖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?

描述明确说明工具功能：基于具体地区（国家、省份、城市、区县）和产业链名称查询当年注销企业数量，并列出返回的指标（总量/生产型/销售型/依赖型），同时排除其他分类和明细。动词（查询）和资源（注销企业数量）具体，与同名列表工具（chain_close_company_list）和同类数量工具（chain_company_num等）区分清晰。

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?

提供了典型问法示例（如'2024年全国集成电路当年注销的企业有多少'），并说明不包含的内容（其他分类统计、企业名单明细），有助于判断何时使用。但未显式说明何时不用或与替代工具比较，缺少排除性指引。

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 adds behavior beyond annotations: it mentions merged return types (total/production/sales/dependent), the included categories, and exclusions. However, the line '仅返回数量不返回名单' conflicts with the tool's list-oriented purpose, making the actual returned behavior unclear.

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 primary query semantics, followed by useful examples and exclusions. Some redundancy exists, and the conflicting clause about returning only counts could have been clarified or removed, but overall it is not bloated.

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 nearly sufficient. It explains input semantics and expected result categories, but the internal contradiction about list versus count, plus a lack of explicit sibling-tool guidance, leaves an important gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description adds practical clarification by naming region granularities, industry chain examples, and typical phrasings for the year, region, and chain_name parameters. These examples help an AI agent map user intent to parameter values.

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 an enterprise list query based on a specific region and industry chain, and typical questions reinforce the intended use. It does not explicitly distinguish this from sibling count/list tools such as chain_company_num, though the name and typical queries make the core purpose understandable.

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 useful context about when to use the tool: for a specific region and industry chain, with example phrasings. However, it does not explicitly state when to choose this tool over alternatives like chain_company_num, and the '不包含' section is muddled by the contradictory phrase '仅返回数量不返回名单'.

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 the burden. It does not contradict annotations. The description adds some behavioral context by stating the output format (merged text of counts) and what it excludes, but it omits side effects, permissions, or rate limits. Given the sparse annotations, this level of detail is adequate but not extensive.

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 well-structured: it opens with the core purpose, lists included metrics, states exclusions, and provides typical questions. The use of a bullet-like line for exclusions improves scannability, and there is no redundant or filler 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 and the presence of an output schema, the description provides sufficient context: what it does, what metrics it returns, exclusions, and typical use cases. It is complete for an agent to understand its role and construct a correct request, especially with the help of sibling distinctions.

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 parameters with descriptions and examples (region, chain_name, year). The description largely repeats these examples (e.g., '全国', '成都', '集成电路') without adding substantial new meaning. It does clarify that the year is optional and that region can be specific levels, but since the schema already conveys this, the description adds minimal value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: querying company counts by region and chain name, with explicit mention of the metrics returned (total, production, sales, dependent). It also specifies what is excluded (other categories and company lists), distinguishing it from sibling *_list tools and other *_num tools with different filters.

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 (e.g., '2024年全国集成电路企业有多少') that implicitly guide when to use this tool. It also states what is not included, but does not explicitly compare with alternatives. However, the tool name and sibling names make it clear this is for counts rather than lists, and the examples reinforce the intended 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 include openWorldHint=true, but the description does not address the dynamic/incomplete nature of results. It does add behavioral details: returns aggregated text for three categories, and expressly excludes other stats and count-only output. This provides some transparency about output scope, but it doesn't mention pagination, data freshness, or any side effects. Since it's a read-only query tool, the description 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 in Chinese and structured logically: main purpose, involved types, exclusions, and typical questions. Each sentence adds value, and the examples are front-loaded. It's slightly longer than necessary but remains efficient for the complexity. No redundant text.

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 query nature with an output schema (provided separately) and rich sibling context, the description covers essential usage: region granularity, chain name examples, year optional, and the types of lists returned. It explicitly states what is not included, preventing misuse. It lacks explicit guidance on pagination or error conditions, but these are likely covered by the output schema and annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, but the description adds valuable examples for each parameter: region examples ('全国','成都市','北京市海淀区'), chain_name examples ('集成电路','新能源','人工智能'), and year usage ('2024年'). It also clarifies region granularity (country/province/city/district), which goes beyond the schema's short descriptions. This helps the agent understand valid 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 it queries lists of discredited companies by specific region (country/province/city/district) and industry chain name, returning aggregated text for total/production/sales/dependent types. It explicitly distinguishes from count-only tools by stating '仅返回数量不返回名单' (only returns counts not lists), which differentiates it from the sibling chain_discredited_company_num. Typical questions illustrate the exact resource and 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 provides typical example queries (e.g., '2024年全国集成电路失信人企业名单') that demonstrate usage context. It explicitly states exclusions: '不包含：其他企业分类的统计；仅返回数量不返回名单' (does not include other company classifications; only returns counts not lists), clarifying when NOT to use this tool. However, it does not explicitly name alternative tools (like chain_discredited_company_num) but implicitly differentiates via the exclusion.

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 annotation, the description carries the behavioral disclosure. It clearly states what counts are returned (total, production, sales, dependency) and what is excluded (other classifications, list details). This gives agents sufficient understanding of the tool's output scope without contradicting 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 logically with purpose, inclusions/exclusions, and examples. The pricing note adds minor redundancy but doesn't detract significantly. It's dense yet every part contributes to understanding, making it appropriately concise for the amount of information conveyed.

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 input schema fully describes parameters and an output schema exists, the description covers purpose, scope, exclusions, and typical queries. It sufficiently equips an agent to decide when and how to use this tool, with no major gaps in required information.

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 are present for all three parameters, but the description adds semantic value by clarifying allowed region granularities (country, province, city, district) and providing example values for region and chain_name in the typical question section. This goes beyond basic schema definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool queries the number of discredited companies by region and industry chain, and specifies the merged return of total/production/sales/dependency counts. It explicitly excludes company list details, distinguishing it from the sibling tool chain_discredited_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 context by stating it returns counts, not lists, and excludes other classifications and company details. While it doesn't explicitly name the alternative list tool, the exclusion implies usage boundaries. Typical question examples reinforce appropriate 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 provide openWorldHint, so the description carries the behavioral burden. It discloses that the result merges total/production/sales/dependency text and that certain categories/count-only returns are excluded. This adds meaningful behavioral context 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?

Description is well-structured: purpose, included metrics, exclusions, and examples are clearly separated and front-loaded. The pricing block adds some noise but does not obscure the core guidance.

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?

Covers purpose, boundaries, and common question phrasings, and an output schema exists to specify return structure. It could be slightly more explicit about the count-only sibling tool, but overall it is sufficiently complete for this tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description reinforces region hierarchy and chain-name examples, but it does not add substantial semantic details beyond what the schema already documents.

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 this tool queries enterprise lists that own software copyrights by region (country/province/city/district) and industry chain. It distinguishes from siblings by explicitly narrowing to '拥有软著的企业列表' and by noting the combined return of total/production/sales/dependency text.

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 usage context through typical questions and explicit exclusions (e.g., '仅返回数量不返回名单'). It does not explicitly point to alternative tools like chain_have_copyright_company_num, 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 discloses that results are a merged summary of total/production/sales/dependent counts, and explicitly excludes other categories and company lists. Since the only annotation is openWorldHint=true, the description adds useful behavioral context beyond annotations, though it does not cover edge cases such as empty results.

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

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

The description is organized into purpose, metrics, exclusions, and typical queries. It is front-loaded and compact, though the indicator list is slightly redundant with the first sentence. No filler sentences are present.

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 an output schema exists, the description does not need to explain return values. It adequately covers tool scope, boundaries, and realistic usage patterns. A small improvement would be explicitly pointing to chain_have_copyright_company_list for user list requests, but the current content is sufficient for a count-focused 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?

Input schema already documents all three parameters (year, region, chain_name), so the baseline is 3. The description reinforces meaning with real-world examples—region granularity, industry names, and optional year—thereby adding semantic clarity beyond the schema 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?

Description uses specific verb+resource: 查询“拥有软著的企业数量”，scoped by region and industry chain. It clearly differentiates from siblings by stating “拥有软著” and explicitly excluding “企业名单明细”，which distinguishes it from the matching list 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 description gives clear usage context via typical queries, and states exclusions (“不包含：其他企业分类的统计；企业名单明细”), helping agents avoid misuse. However, it does not explicitly name the alternative list/count tools to use instead, so it falls short of fully explicit 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?

Beyond the openWorldHint annotation, the description discloses that it returns combined text for total/production/sales/dependent types, and specifies the region scope. It does not mention pagination or limits, but these may be covered by the output schema. 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 concise and well-structured, with clear sections for purpose, inclusions, exclusions, and examples. Pricing info is included but does not detract. It is appropriately sized without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the existence of an output schema and high schema coverage, the description adequately explains the tool's behavior, parameters, and limitations. It covers region and chain_name semantics, year is in schema, and the exclusion list clarifies scope. Sufficient for an agent to 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 coverage is 100% with descriptions for all parameters. The description adds value by providing typical queries with examples (e.g., '2024年全国集成电路'), clarifying region can be country/province/city/district, and chain_name as industry chain. This enriches parameter understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: querying lists of enterprises without patents for specific regions and industry chains. It explicitly lists included types (production, sales, dependent) and exclusions (other categories, count-only returns), distinguishing it from sibling tools like chain_have_no_patent_company_num and chain_have_patent_company_list. The verb 'query' and resource 'enterprise list' are 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 provides typical queries and clearly states what it does not include (other categories, only count returns), which implicitly guides when to use this tool versus the _num variant. However, it does not explicitly name alternative tools for contrast, so usage 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?

描述披露了返回合并文本（总量/生产型/销售型/依赖型），并明确排除项。在 openWorldHint 注解之上补充了额外行为上下文，无矛盾。

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?

核心描述紧凑，但末尾包含非核心的 Pricing 块，且指标列举略显冗余，稀释了信息密度。

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，描述仍提供了主要用途、返回内容、排除事项和典型问法，覆盖关键方面。但未提及 year 的边界或数据缺失时行为，略有不足。

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?

输入模式中参数描述完整，描述进一步通过典型问法说明 region、chain_name、year 的实际用法，并指出 region 可涵盖国家/省/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“没有专利的企业数量查询”，并指明基于具体地区和产业链名称。同时声明“不包含：企业名单明细”，与列表类工具明确区分。

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?

提供典型问法示例，明确使用场景。指出不包含其他企业分类统计和名单明细，但未直接推荐或对比替代工具（如 chain_have_no_patent_company_list）。

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 transparency burden. It discloses that the result is a merged text of multiple types and what it does not include, but does not mention potential incompleteness (related to openWorldHint), pagination, ordering, or error 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 moderately concise, with the main purpose front-loaded and structured lines for included/excluded types and typical queries. The pricing note is extraneous but does not detract. It could omit the pricing to be tighter, but it is not 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 schema fully documents parameters and an output schema exists, the description covers the key aspects: purpose, exclusions, and usage examples. It does not discuss return format details (covered by output schema) or limitations like pagination, but that is acceptable given the structured schema availability.

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 schema already documents all parameters. The description adds some example values for region and chain_name, but the schema already provides similar examples (e.g., '成都' and '集成电路'). Thus, it adds marginal value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it queries a list of enterprises with patents for a specific region and industrial chain, and explicitly lists the included metric types (total, production, sales, dependence) and exclusions. It differentiates from sibling tools like the count-only version and other category lists by specifying 'patent' and '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 gives clear context on when to use it (for patent-holding company lists) and provides typical query examples. The '不包含' section implicitly distinguishes it from count-only tools and other categories, but it does not explicitly name alternatives like chain_have_patent_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 in annotations, the description adds useful behavioral context: it is a query of aggregated counts, returns merged text for total/production/sales/dependent types, and explicitly excludes company list details. This goes beyond the sparse annotation and helps set expectations for the result.

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 for metrics, exclusions, and example queries. It is not overly verbose, though the embedded pricing block is extra information that could be considered non-core. Overall, it is structured and readable.

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 complexity, the description covers the purpose, supported metrics, exclusions, and provides realistic example queries. An output schema exists, so return-value details are not necessary here. This is sufficient 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?

Even though the schema already describes all three parameters at 100% coverage, the description adds valuable semantics: region is clarified as country/province/city/district, chain_name is illustrated with examples like '集成电路' and '人工智能', and typical questions demonstrate how year, region, and chain_name combine in practice.

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 the number of companies with patents by region and industry chain. It distinguishes itself from list-type siblings by explicitly noting '不包含：企业名单明细' (does not include company name lists), making its count-focused 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 question patterns and explicitly states what the tool does not include (other category statistics and company list details). However, it does not name alternative sibling tools explicitly, such as chain_have_patent_company_list, so the when-to-use guidance is clear but not fully alternative-oriented.

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, no readOnly/destructive hints). The description does not explicitly state side effects, safety, or data modification behavior, but the nature of a list-returning query tool implies read-only behavior. The description does clarify it returns a list, not a count, which is a partial behavioral 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 yet informative, with clear sections: primary function, included types, exclusions, and example queries. Each sentence adds value without redundancy, though it could be slightly more streamlined.

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 what the tool returns (lists), what it excludes (counts), and provides example queries to illustrate usage. It does not specify output format or pagination, but for a list query tool, the examples and exclusions sufficiently convey the expected behavior.

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 for all three parameters are provided (100% coverage), and the description enriches them by specifying that region can be country/province/city/district and gives concrete example values (e.g., '2024年全国集成电路'). This adds significant 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 queries high-tech company lists based on region and chain name, and distinguishes from sibling tools by specifying it returns lists (not counts) and includes production/sales/dependent types. Examples further clarify the exact use case.

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 example queries and explicitly excludes '仅返回数量不返回名单', indicating when not to use this tool (e.g., when only a count is needed, use the _num sibling tools). While not an explicit 'use this when' statement, the context is 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?

Annotations provide only openWorldHint, so the description carries the main disclosure burden. It adds behavioral context by stating the return is a merged text of total and type-specific counts, and that list details are not included. It does not cover data freshness or error scenarios, but for a simple count query this is adequate.

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

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

The description is well-structured: purpose, metrics, exclusions, and typical questions are front-loaded. The appended pricing info is meta but not detrimental. Each sentence contributes to understanding, and the description is concise for the information provided.

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 count query with an output schema, the description covers the necessary context: what it counts, what it excludes, and how to ask. It doesn't explain return format, but the output schema fills that gap. It could be more explicit about when to choose this over sibling count tools, but overall it 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 descriptions cover all three parameters (region, chain_name, year) with clear semantics. The description reinforces region granularity and optional year, but adds no substantial new parameter details beyond the schema. Baseline 3 is appropriate since coverage is 100%.

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 high-tech enterprise counts by region (country, province, city, district) and industry chain, with a specific verb '查询' (query) and resource '高新技术企业数量'. It lists the exact metrics (total, production, sales, dependent types), and explicitly excludes other classifications and list details, distinguishing it from sibling list/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 provides explicit exclusions ('不包含：其他企业分类的统计；企业名单明细') and gives typical questions to illustrate use cases. It clarifies that this tool is for counts, not lists, but does not name alternative sibling tools (e.g., chain_high_tech_company_list) for the excluded 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 discloses the semantic sub-categories (total, production-type, sales-type, dependency-type) and states that it returns lists rather than counts. Since annotations carry only openWorldHint, the description carries a moderate burden, but it does not clarify the ambiguous interaction between the fixed '近两年' window and the optional 'year' parameter, nor does it explain the '合并返回...文本' output behavior in 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 well-structured with a function statement, involved indicators, exclusions, and typical examples. It is slightly repetitive in the indicator listing but stays within reasonable length and front-loads 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?

Given the output schema exists and the parameters are well-documented, the description is mostly complete. However, it fails to clarify how the optional 'year' parameter relates to the fixed '近两年' time window, which could lead to incorrect invocation. It also could strengthen the guidance on sibling count/list tools.

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 description adds example queries that implicitly show how the region and industry name are used, but it does not add meaningful parameter semantics beyond what the input schema already 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 the tool queries enterprise lists with recent outward investment by region and industry chain, and it explicitly excludes count-only output. This distinguishes it from sibling tools like chain_invest_company_num and chain_invested_company_list, though the phrase '合并返回总量/生产型/销售型/依赖型文本' is a bit ambiguous about the actual result structure.

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 question examples provide clear context for when to invoke the tool, and the '不包含' section hints at scope limits. However, it does not explicitly reference alternative tools (e.g., chain_invest_company_num for counts) or give when-not-to-use guidance beyond what the tool itself excludes.

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 sparse openWorldHint: true annotation, the description adds genuinely useful behavioral context: the return is a merged aggregation across four categories (总量/生产型/销售型/依赖型), the temporal window is 'near two years,' and geographic/industry scope is enumerated. It also clearly states exclusions (other classification stats, list details). Slight deduction for not adding a data-completeness caveat given the open-world 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-organized with clear labeled sections (涉及指标/类型, 不包含, 典型问法, Pricing) and front-loads the core query statement. However, the phrase '近两年有对外投资的企业数量' is needlessly repeated four times, and the pricing block adds noise without being formatted as documentation. Under-specification is not the issue; trimming would be.

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 low-complexity count tool (3 flat params, 2 required), the description is thorough: it covers what is counted, the four-category breakdown, exclusions, representative queries, and pricing. Since an output schema exists, the description is not obligated to detail return values. A small gap remains in clarifying data-freshness or the semantics of the optional year parameter.

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%, which earns the baseline 3; the description adds value by showing that the 'year' parameter anchors the 'near two years' window (as evidenced by the 2024 example implying 2023-2024) and by demonstrating valid region formats (全国, 成都, 北京市海淀区) through real query phrasings. It stops short of explicitly documenting the default when 'year' is omitted, which keeps it from a 5.

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-object pattern ('查询...企业数量') with clear resource ('近两年有对外投资的企业') and scope dimensions (region + industry chain), and the three example queries (典型问法) reinforce purpose. It distinguishes from aggregate siblings like chain_company_num by emphasizing the outbound-investment filter. Minor deduction for the slightly awkward '合并返回...文本' phrasing and not explicitly contrasting with the reverse-direction sibling chain_invested_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 description provides implicit usage signals through a '不包含' (does not include) section and three concrete example questions that clarify when this tool applies. However, it never explicitly names alternatives like chain_invest_company_list (for detail lists) or chain_invested_company_num (reverse investment direction), which is a missed opportunity given the obvious sibling pairs.

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 context beyond the openWorldHint annotation: it specifies the output is merged text of totals/production/sales/dependent, excludes other categories, and returns lists not counts. It also clarifies the time window (近两年) and gives typical query patterns. No contradictions with annotations detected.

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 moderately long but well-structured: it opens with the core query, lists the metric types, states exclusions, and ends with typical query examples. Each sentence serves a purpose—no fluff. The structure aids readability and quick comprehension.

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, the description need not detail return structure. It covers scope (region, chain, time), what is included (listed types), what is excluded (other categories, counts), and provides examples. It does not mention pagination or result limits, but that is typically handled by the output schema or runtime. Overall, it is complete for a list-query 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 coverage is 100% with each parameter described. The description adds semantic value by providing examples of valid region formats (e.g., '全国', '成都', '北京市海淀区') and chain names (e.g., '集成电路'). It also clarifies that 'year' is optional and explains the required combination of region and chain_name. This enhances the schema's raw 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 it lists companies with external financing in the last two years, filtered by region and chain name, and returns merged lists for total/production/sales/dependent types. It distinguishes from siblings like chain_invested_company_num (which returns counts) and chain_invest_company_list (which likely lists investing companies) by emphasizing '近两年有对外融资的企业列表' and explicitly noting it returns lists not 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 indicates when to use this tool: when querying companies that have received external financing in the last two years by region and chain. It explicitly states exclusions ('不包含：其他企业分类的统计；仅返回数量不返回名单') which helps prevent misuse for counts. It does not explicitly name alternatives like chain_invested_company_num, but the contrast is implied through the exclusion statement and sibling names.

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?

描述披露了返回类型（文本形式），以及不包含的内容（其他分类、名单），这些超出了openWorldHint注解本身提供的信息。未与注解矛盾。

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?

描述结构清晰，先说明核心功能，再列举指标，最后给出不包含项和典型问法。信息紧凑，无冗余，但典型问法部分略长，稍显冗余，故为4。

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?

由于有输出schema（尽管未提供细节），描述无需解释返回值格式，但已说明了输出类型（文本）。整体信息完整，足以支撑调用，但未提及错误处理或边界条件，故给4。

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覆盖率100%，每个参数都有清晰描述。描述中典型问法提供了具体用法，但未在schema基础上增加额外语义，符合基线3。

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

描述明确说明该工具用于查询特定地区和产业链近两年有对外融资的企业数量，并返回总量/生产型/销售型/依赖型文本。动词（查询）和资源（企业数量）都很具体，且与兄弟工具chain_invested_company_list（列表）和chain_invest_company_num（对外融资）区分开来。

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?

提供了典型问法示例，展示了如何使用地区和产业链名称，且明确说明不包含的统计和明细，有助于明确定位。但未明确说明何时不使用此工具，或与类似num工具的选择依据，所以未达5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?

The description clearly states the output is a merged text of total and production/sales/dependent lists, and explicitly excludes other classifications and count-only results. With openWorldHint=true, it adds context beyond schema by noting the '近两年' time frame and the combined nature of the output.

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 details and examples. It avoids redundancy and is mostly straight to the point, though the list of indicators is slightly 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 complexity of the tool (multiple output categories, exclusions), the description adequately covers the purpose, usage, and constraints. It also references the 'num' variant implicitly by saying '列表查询' as opposed to count tools, which helps differentiate among siblings.

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 (region, chain_name, year). The description repeats these but adds example values and explains the year is optional. It doesn't provide additional semantic depth beyond the schema, which already has 100% 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 returns a list of companies that issued tenders in the past two years for a given region and industry chain, with a merged text of total and production/sales/dependent types. It also lists what is included and excluded, making the purpose specific and actionable.

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 typical query examples (e.g., '2024年全国集成电路') and specifies the required parameters (region, chain_name). However, it does not explicitly contrast with sibling tools like chain_company_list or the _num variant, though the examples and exclusions help differentiate.

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 an annotation, the description carries the transparency burden. It discloses that the result is a merged text containing four count categories, the default two-year lookback window, and the exclusions. This adds useful behavioral context beyond the minimal annotation, though it does not address rate limits or auth requirements.

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 bullet-pointed sections, and the core purpose is front-loaded. It is longer than strictly necessary due to the pricing metadata and multiple example questions, but every part serves to clarify scope and usage, so it remains efficient overall.

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 tool with an output schema, the description covers metric types, default time range, region scope, and exclusions. The output schema is expected to handle return structure details. Notable omission is not addressing the openWorldHint annotation textually, but overall the description is adequately complete for its function.

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 covers all parameters with descriptions, so baseline is 3. The description adds extra semantics by clarifying region granularity (country/province/city/district) and using examples to show the 'year' parameter anchors the two-year window. This is meaningful added value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly defines the tool as a count query for companies that initiated tenders in the past two years, filtered by region and chain name. It explicitly enumerates the four metric categories (total, production, sales, dependent) and explicitly excludes company list details, distinguishing it from the sibling chain_issued_tender_company_list 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 description provides solid usage context: it states the query is for aggregated counts of four types, explicitly excludes other classification statistics and list details, and includes typical question examples. However, it does not explicitly name the list sibling as an alternative tool, relying on naming conventions, so it falls short of full explicit 'when-not and 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 does not disclose any side effects, permissions, or error behavior. The annotations only include openWorldHint, which is not about mutability. As a query tool, it is presumably read-only, but the description does not state this, leaving behavioral aspects largely undisclosed.

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 distinct sections for purpose, involved types, exclusions, and examples. It is slightly verbose but not excessive, and the structure aids comprehension.

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, the description does not need to explain return format. It adequately covers input parameters, typical usage scenarios, and exclusions. It lacks details like pagination or error handling, but these are not critical for a list query, and the description is sufficiently comprehensive.

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 descriptions for each parameter, but the tool description adds meaningful context, such as region can be country/province/city/district and examples like '全国' or '成都市'. This goes beyond the schema descriptions and clarifies acceptable values.

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 listed companies based on region and industry chain, and explicitly mentions the merged types (total/production/sales/dependency). It includes examples and distinguishes from count-only tools and other company category lists, making the purpose specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides exclusions (e.g., not for other categories, not for count-only) and typical query examples, which imply when to use this tool versus alternatives like chain_listed_company_num. However, it does not explicitly state 'use this when you need a list rather than a count,' but the context is 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?

Annotations only carry openWorldHint=true, so the description carries the transparency burden. It does disclose useful behavior: results merge total/production/sales/dependent counts as text, and it excludes detailed lists from the response. However, it doesn't add e.g. data-coverage notes (which stock exchanges or listings, A-share only), refresh timing, or auth/limits. No contradiction with annotations, but the description is solid, not rich, on behavior beyond scope.

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 clear intro, bullets for metrics and exclusions, followed by typical questions. It front-loads the purpose and is information-dense without bloat. It loses a point because the trailing 'Pricing: {...}' appears to be accidentally concatenated metadata that adds noise and dilutes focus, though the core description itself is 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?

For a modest 3-parameter count tool with an output schema and openWorld annotation, the description is largely complete: required region/chain inputs are clarified, the aggregated return semantics are stated, and the typical questions convey the intent. An explicit note on the data universe (which entities count as 'listed companies') would push it higher, but the description adequately complements the available schema and annotations.

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 real value above the schema by providing concrete example values for region ('全国', '成都市', '北京市海淀区'), chain_name ('集成电路', '新能源', '人工智能'), and a sample year (2024), which helps the agent map user intents to valid parameter formats. Minor deduction for not elaborating on the optional 'year' semantics 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 uses a specific verb+resource framing (query the number of listed companies filtered by region and industry chain), explicitly lists the metric types returned (total/production/sales/dependent), specifies what is NOT included (other classifications; detailed company lists), and provides three concrete example queries. This clearly distinguishes it from sibling count tools like chain_company_num (all companies) and its own list twin chain_listed_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 gives clear usage context: it covers which region granularity and chain-name inputs apply, explicitly states exclusions (e.g., no company name details, no other classifications), and provides realistic natural-language examples. It does not explicitly name sibling tools as alternatives (e.g., 'use chain_listed_company_list for details'), but the '不包含' section effectively signals when NOT to use this tool, which is strong 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?

With only openWorldHint provided as an annotation, the description carries the transparency burden and discloses that the response is a merged text of total/production/sales/dependent types, and that it returns lists rather than counts. It does not mention pagination or edge cases, but the behavioral scope is sufficiently clear for a read-style list query.

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 labeled sections for included metrics, exclusions, and typical queries. It is longer than minimal but each part adds useful guidance; the pricing block is somewhat extra but not disruptive.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple parameter set (3 params, 2 required), presence of an output schema, and only openWorldHint annotation, the description provides enough context about scope, inclusions, exclusions, and example usage. It does not need to explain return structure in detail because an output schema exists.

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 value by specifying region granularity ('国家，省份，城市，区县'), giving chain_name examples, and providing real query patterns that clarify how year, region, and chain_name are used together.

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 newly established companies for a specific region and industry chain, with combined sub-lists for production/sales/dependent types. It explicitly distinguishes itself from the count-only sibling tool by noting '仅返回数量不返回名单' and from other chain tools by focusing on '当年新增'.

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 strong usage context through typical query examples ('2024年全国集成电路当年新增的企业名单') and states exclusions such as other company classifications and count-only results. It does not explicitly name alternative tools like chain_new_start_company_num, but the '不包含' clause makes the intended boundary 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?

With annotations providing only openWorldHint=true, the description adds significant behavioral detail: it returns textual results for three enterprise types (总量/生产型/销售型/依赖型), and explicitly excludes other categories (其他企业分类统计). It also mentions pricing (100 credits), which is relevant for agent cost awareness. This goes beyond what annotations or schema provide.

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-like structure (including a pricing section), and front-loads the core purpose. It avoids fluff. The pricing block is additional but relevant for cost-aware agents. Slightly verbose due to the pricing mention, but overall tight.

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 3 parameters fully described in the schema, the output being textual counts (no output schema), and clear exclusions, the description covers the key usage aspects. It doesn't specify optionality of 'year' or default behavior, but the schema indicates 'year' is not in required. The typical questions provide enough context. Missing details on pagination or response format are not critical for a count query.

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 params have descriptions). However, the description adds meaningful context beyond the schema: it clarifies that 'region' should be a specific geographical name (国家、省份、城市、区县) and that 'chain_name' is the industry chain name. While the schema already explains these, the description reinforces the usage with examples, justifying a score 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 specifies a clear verb+resource: '查询' (query) for '企业数量' (enterprise counts) filtered by region and chain. It explicitly defines scope (合并返回总量/销售型/生产型/研发型) and excludes other enterprise categories, distinguishing it from sibling tools like chain_new_start_company_list which returns lists rather than 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 gives concrete usage scenarios with typical questions (e.g., '2024年全国集成电路当年新增的企业有多少') and clarifies that it returns aggregated counts by type. It doesn't explicitly contrast with sibling tools, but the '不包含' clause helps disambiguate scope. The clear examples provide strong usage 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 does not mention any side effects, authentication requirements, or rate limits. The annotation only includes 'openWorldHint' which is not a standard behavioral indicator. Since this is a read-only list query, the lack of explicit transparency is acceptable but not exceptional. 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 moderately concise, containing a clear purpose, a list of indicators, exclusions, and examples. It is not overly verbose and each sentence serves a purpose, though the enumeration of types could be streamlined.

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, the description provides a good overview but lacks crucial details about how to specify the company type (total/production/sales/dependent) and how the year parameter interacts with the 'past two years' filter. This leaves some ambiguity for an AI to correctly invoke the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides descriptions for region, chain_name, and year, achieving 100% coverage. The description adds example values for region and chain_name, but does not clarify how the optional 'year' relates to the '近两年' (past two years) phrase, nor how to select among the four mentioned types (total/production/sales/dependent). Thus it adds marginal value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it queries a list of companies that participated in tenders in a specific region and industry chain over the past two years. It explicitly distinguishes from the count variant by indicating it returns a list, not counts. However, the mention of '合并返回总量/生产型/销售型/依赖型文本' is ambiguous about how the user specifies which type, slightly reducing clarity.

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 explicit exclusions ('不包含：其他企业分类的统计；仅返回数量不返回名单') and provides typical question examples that illustrate appropriate usage. It does not explicitly contrast with the count tool (chain_participated_tender_company_num), but the exclusions and examples give sufficient guidance for 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 the output is a merged text with total/production/sales/dependent counts ('合并返回总量/生产型/销售型/依赖型文本') and excludes other classifications. This adds context beyond the openWorldHint annotation. However, it does not clarify how the optional 'year' parameter interacts with the 'past two years' time window, leaving ambiguity about the time filtering 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 structured with a clear definition, metric list, exclusions, and examples. It is somewhat long due to repeating the metric names and including pricing information, but it remains scannable 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?

The tool has a simple interface with an output schema (not shown), so return values are presumably covered. The description addresses the main use case, metrics, and exclusions well. However, the lack of explanation about the optional 'year' parameter's effect on the 'past two years' scope creates a completeness gap.

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 description adds example queries showing valid region values like '全国' and specific city/district names, which aids understanding. However, it does not add meaningful detail about the 'year' parameter's semantics or its relationship to the two-year window.

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 and resource: querying the number of companies that participated in bidding in the past two years, filtered by region and industry chain. It clearly differentiates from list tools by explicitly stating '不包含：企业名单明细' (does not include company list details), and from other tender types by focusing on '参与过投标' (participated in bidding).

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 (e.g., '2024年全国集成电路近两年参与过投标的企业有多少') and explicitly lists exclusions ('不包含：其他企业分类的统计；企业名单明细'), which help the agent understand when not to use this tool. However, it does not explicitly name alternative tools like chain_participated_tender_company_list, so it falls 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 reveals that the tool returns a list (not just counts) and combines totals/types (总量/生产型/销售型/依赖型), but it does not mention side effects, read-only nature, permissions, or rate limits. Since no readOnlyHint is provided, behavioral transparency is moderate.

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 sections for main purpose, indicators, exclusions, and typical queries. It is detailed but not redundant, effectively conveying necessary information without unnecessary verbosity.

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 purpose, indicators, exclusions, and examples, providing sufficient context for using the tool. It does not specify the exact output schema, but it indicates the return includes lists and types, which is adequate for a list query tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already provides clear descriptions for all three parameters (year, region, chain_name). The description adds practical examples (e.g., '成都市新能源产业链') and clarifies that region and chain are required, enhancing understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool queries for specialized enterprise lists (专精特新) based on region and industry chain, provides concrete examples (e.g., '2024年全国集成电路专精特新企业名单'), and explicitly excludes other classifications and count-only results, 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 gives typical usage questions and explains what it does not include (e.g., other enterprise classifications, counts only), which helps differentiate from sibling tools like chain_specialized_company_num. However, it does not explicitly state when to prefer this over other list tools, though the context implies it.

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

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

Annotations only include openWorldHint=true, which does not disclose safety or behavioral details. The description compensates by stating the tool returns a merged text combining total/production/sales/dependent counts, and explicitly excludes other classifications and company lists. It does not mention read-only status, but the use of '查询' and the nature of the tool imply read-only, and the output format is described.

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 moderately sized but well-structured, with a clear purpose line, a list of included indicators, an exclusion line, and example queries. It is front-loaded with the main purpose and avoids redundant fluff, though the pricing block is non-essential metadata attached to the 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?

The tool has a moderate number of parameters (3), an output schema, and a clear domain. The description explains the exact type of counts returned, the scope, and what is excluded, providing sufficient context for an agent to select it over similar tools. It could mention source data limitations or update frequency, but given the output schema and clear exclusions, it is complete enough for typical use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides full descriptions for all three parameters with examples (e.g., region examples like '全国', '成都', '北京市海淀区'; chain_name examples; year description). The description adds example queries and clarifies the region scope ('国家，省份，城市，区县'), but this is marginal beyond the schema, so it meets the baseline for 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 provides counts of specialized (专精特新) enterprises filtered by specific region and industry chain, and explicitly enumerates the four indicators returned (total, production, sales, dependent). It distinguishes itself from sibling tools by stating it returns aggregated counts as text, not company lists, which differentiates from chain_company_list and chain_specialized_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 includes concrete example questions ('2024年全国集成电路专精特新企业有多少') and explicitly lists exclusions ('不包含：其他企业分类的统计；企业名单明细'), which signals when NOT to use this tool (e.g., for lists). It does not name alternative tools directly, but the negative guidance and the presence of sibling chain_specialized_company_list make the usage context 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?

Annotations only include openWorldHint, so the description carries the transparency burden. It discloses that the tool returns a merged text of total/production/sales/dependent lists, and excludes other categories, adding value. It also implies read-only nature by describing a query, but does not explicitly state side effects or permissions. Overall, it adds meaningful behavioral context.

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

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

The description is structured with a clear main statement, bullet-like inclusions/exclusions, typical questions, and pricing. It is a bit lengthy but every section adds useful context. It is front-loaded with the core purpose, making it 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 tool has an output schema and three parameters, the description covers the essential aspects: what it returns (merged list types), what it excludes, example inputs, and cost. It does not describe detailed output structure, but the presence of an output schema mitigates that. It is sufficiently complete for an agent to decide and 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?

The schema already has descriptions for all parameters (100% coverage), so the baseline is 3. The description enriches this with concrete examples (e.g., region as '全国','成都','北京市海淀区' and chain_name as '集成电路','新能源') and clarifies the year is optional. This goes beyond the schema by illustrating valid values and typical use cases.

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 a list of tech-oriented small and medium enterprises based on region and chain name, and it distinguishes itself from sibling count tools (e.g., chain_tech_oriented_company_num) and park-based tools by specifying 'chain' and 'list' semantics. Typical question examples reinforce the 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 example queries and explicitly states what is NOT included (other categories, count-only results). However, it does not explicitly contrast with alternative tools like count variants or park-specific variants, leaving the agent to infer when to use this vs. those. No 'when-not' guidance is given.

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

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

With only openWorldHint in annotations, the description carries the behavioral burden. It discloses that this is a count query returning merged text with total/production/sales/dependent counts, and explicitly excludes enterprise list details. It does not mention edge-case behavior or exact response formatting, but for a count-oriented 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 front-loaded with the core purpose and then organized into metrics, exclusions, examples, and pricing. The '涉及指标/类型' section slightly duplicates the first sentence, but overall the description is scannable and appropriately sized.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with only two required parameters, a full output schema, and complete parameter descriptions, the description is comprehensive. It covers the metric types returned, exclusions, typical question formats, and cost, leaving no significant gaps 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?

The input schema already has 100% parameter description coverage, so the baseline is 3. The description adds practical value by clarifying region granularity (国家/省份/城市/区县) and giving concrete examples that map '2024年全国集成电路' to year, region, and chain_name, helping the agent construct valid parameter values.

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 counts 科技型中小型企业 by specific region (国家/省份/城市/区县) and chain name, and specifies the returned categories (total/production/sales/dependent). The explicit '不包含企业名单明细' distinguishes it from sibling list tools like chain_tech_oriented_company_list, and '科技型中小企业' distinguishes it from generic chain_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 description provides clear context via typical queries ('2024年全国集成电路...', '成都市新能源产业链...', '海淀区人工智能...') and explicit exclusions ('不包含：其他企业分类的统计；企业名单明细'). However, it does not name specific alternative tools or state 'use X instead' for other enterprise classifications or list retrieval.

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 set openWorldHint: true, so description bears the burden. It discloses that the tool returns a merged text for total/production/sales/dependency types, excludes other categories, and returns a list not a count. Does not state whether operation is read-only, but given nature of tool and no destructive annotations, it's not a critical omission given the content.

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 moderately sized but front-loaded with main purpose. Includes typical questions and exclusions, all useful. Pricing info is extra but not bloated. Every sentence contributes to scope understanding.

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 format need not be described. The description covers the tool's functional scope, merged result types, exclusions, and example usages. No mention of pagination or limits, but likely covered elsewhere. Adequate for a query 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 coverage is 100% with each parameter described (region examples, chain_name examples, year optional). Description adds little beyond schema—only reiterates that region can be country/province/city/district and chain is specific. Baseline 3 is appropriate as schema does the heavy lifting.

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?

Clear verb+resource: queries list of companies that won tenders in last 2 years based on region and chain name. Explicitly distinguishes from count-only sibling (chain_won_tender_company_num) by stating '仅返回数量不返回名单' and from participation variant (chain_participated_tender_company_list) by focusing on '中标' (won). Also clarifies scope of categories.

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 showing when to use (e.g., '2024年全国集成电路近两年有中标的企业名单'). States exclusions ('不包含：其他企业分类的统计'), indicating when not to use. Does not explicitly mention alternatives like count-only tool, but the sibling names and the 'list vs. count' distinction serve as implicit 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?

Annotations only include openWorldHint, which is minimal. The description adds value by disclosing the output as a merged text summary of totals for production/sales/dependency types, and explicitly states what is not included. It does not describe side effects or edge cases but is sufficiently transparent for a read-only count 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 somewhat lengthy due to listing metrics and examples, but it is structured with bullet points and separate sections. It front-loads the main purpose and includes essential details, though it could be tightened to reduce redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (multiple metrics, optional year, region granularity) and the presence of an output schema (as indicated by context), the description logically covers the core functionality, exclusions, and provides examples. It does not elaborate on edge cases 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?

Schema descriptions already cover all three parameters (year, region, chain_name). The description enriches them with example values for region and chain_name, clarifies year is optional, and provides typical user phrasings, adding semantic context 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 counts companies that have won tenders in the last two years, filtered by region and chain name. It differentiates from sibling list-based tools (e.g., chain_won_tender_company_list) by focusing on count and enumerating specific metric 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?

The description explains what the tool does and what it excludes (other classifications, company lists), implying use for count queries only. It provides typical question formats, but doesn't explicitly name alternatives like the list version, though the exclusion hints at it.

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

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

The description discloses meaningful behavioral details: it returns merged text covering total, production, sales, and dependent categories, and it explicitly states what is not included. It does not contradict the openWorldHint annotation, though it also does not elaborate on the open-world implications or pagination 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 front-loaded with the main purpose, followed by useful indicator breakdown, exclusions, and examples. The appended pricing metadata adds minor noise, but the overall structure is compact and each substantive sentence contributes 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 three-parameter tool with an output schema, the description is sufficiently complete: it names the region/chain scope, the four returned categories, exclusions, and representative queries. It does not discuss edge cases like invalid region names or empty results, but such details are not critical given the schema and examples.

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 description mostly reinforces the schema by showing sample phrasings for region, chain_name, and year. It adds typical question examples but no deeper parameter-level nuance such as accepted formats or defaults, so the schema carries most of the semantic 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 clearly states this tool queries a list of companies established for more than 5 years, scoped by region and industry chain name. It distinguishes itself from sibling count-only tools by explicitly including '企业列表查询' and listing the merged result 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?

Typical question examples give clear usage context, and the '不包含' section clarifies exclusions such as count-only results and other enterprise categories. It does not explicitly name sibling tools like chain_year5_company_num or chain_company_list as alternatives, so it stops just 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 discloses that the result is a merged text containing total/production/sales/dependent counts, which is beyond the annotation. However, it does not add caveats about open-world data completeness or behavior when year is omitted. 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 structured with key indicators, exclusions, and typical examples, making it easy to scan. It is moderately concise, though the pricing information is non-essential and could be omitted.

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 usage scope, metrics, exclusions, and typical examples, which is adequate for a count tool with an output schema. However, it lacks explicit differentiation from general chain_company_num and does not state the default behavior when 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?

The schema already documents all three parameters with 100% coverage. The description adds typical question examples and region granularity, but these largely overlap with schema descriptions, providing minimal additional meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool queries the number of enterprises surviving over 5 years based on region and chain name. It explicitly lists the included metrics (total/production/sales/dependent) and excludes list details, distinguishing it from the sibling chain_year5_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 question examples and explicit exclusions ('不包含：其他企业分类的统计；企业名单明细'), indicating when not to use the tool. However, it does not explicitly name alternative tools for those cases, so it lacks explicit alternatives.

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

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

Annotations include openWorldHint: true, so the agent knows output may have extra fields. The description adds value by listing concrete output fields, but it does not disclose any other behavioral traits such as pagination limits (though schema covers that), rate limits, or side effects. It does not contradict 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 a single, clear sentence stating the tool's purpose and output fields, followed by a pricing line. It is front-loaded and contains no unnecessary words. The pricing note is brief and relevant for cost awareness.

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 parameters and a high schema coverage, the description provides the essential purpose and output fields. It does not mention any special conditions or limitations beyond what the schema covers, but given the presence of an output schema and the tool's simplicity, it is reasonably complete. It could explicitly state that it is read-only, but that is minor.

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 (page, limit, company_name) are described in the schema. The description adds minimal extra parameter meaning; it reiterates the company_name requirement but provides no additional syntax or format details 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 approved policy subsidies for a company, listing specific fields (project name, type, level, reward, year). It distinguishes from siblings like company_can_apply_subsidy by explicitly mentioning '已获批' (already approved), though it does not 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?

No guidance is provided on when to use this tool versus alternatives. It does not state when not to use it, nor does it mention related tools like company_can_apply_subsidy. The description simply states the tool's function without usage context.

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: true in annotations, the description carries the behavioral burden but only discloses what's returned (app name, category, intro) and the pricing model. It adds the transparency of per-run credit pricing, but doesn't disclose details like pagination limits (though page/limit are in schema), data freshness, or error behavior. 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 lead sentence efficiently communicates the function in one clause, and the pricing block is structurally separated for easy parsing. No fluff—each element serves a purpose, though additional behavioral context could have been added without bloat.

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 a well-documented schema and an output schema present, the description is reasonably complete but leaves gaps: it doesn't describe the response structure, whether the result includes all apps or just the first batch, or any rate limits. The expense disclosure via pricing is a nice touch, but overall it's barely adequate for an agent to invoke confidently.

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 of 3 applies. The description adds semantic context that company_name must be an explicitly specified enterprise name and lists what's returned, but doesn't elaborate on parameter behavior beyond the schema, such as the format of the page/limit parameters or interaction between them. The schema itself documents each parameter clearly with an example.

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 a specific verb+resource+scope: query APP information (app name, category, introduction) developed by an explicitly specified enterprise. It's distinct from the many chain_*/park_* siblings in that it targets company-developed apps specifically, though it doesn't explicitly name a sibling alternative.

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 no guidance on when to use this tool versus alternatives or when not to use it. It implies usage through the description of what it does, but there's no mention of prerequisites, exclusion criteria, or related tools, such as when one might need to resolve a company name first with search_company_candidates.

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?

Since annotations only include openWorldHint=true with no readOnlyHint or destructiveHint, the description's use of '查询' and its listing of output fields help signal that this is a read-only, information-retrieval tool. However, it does not disclose how exact-name matching failures are handled, whether optional fields may be missing, or any operational constraints beyond the pricing note.

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 effectively, but then becomes a very long single sentence enumerating dozens of output fields plus pricing. Much of this field-level detail is likely present in the output schema, making the description more verbose than necessary while still being readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with only one parameter and an existing output schema, the description is nearly complete: it states the required input, the broad information scope, and the per-run cost. It lacks guidance on fuzzy-name resolution or exact-match caveats, but those concerns are more about tool selection and are not critical gaps for this simple tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers 100% of the parameters, with a clear description and example for company_name. The description adds no additional parameter-level semantics beyond restating that the company name must be explicitly specified.

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 begins with a clear, specific statement: '基于明确指定的企业名称，查询该企业的基本信息' — query the basic info of an enterprise by its exact name. It then enumerates the returned dimensions (e.g., 注册地址, 经营状态, 法定代表人), which distinguishes it from sibling tools like company_shareholder or company_patent that target specific data categories rather than a general company profile.

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 the usage context: call this tool when you have a clearly specified enterprise name and need its comprehensive basic information. However, it does not explicitly state when not to use it or mention alternatives for fuzzy/uncertain company names, such as search_company_candidates or company_data_search.

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 goes beyond the minimal annotation by clarifying that this is a read-oriented query, listing the returned data fields, and adding pricing information. It does not address the openWorldHint annotation or edge cases like no results, but it provides meaningful behavioral context for a simple 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 core description is one concise sentence that front-loads purpose, scope, and output fields, followed by a compact pricing note. Every part serves a clear function with no redundant 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?

The tool is a straightforward query with an output schema and well-documented parameters. The description covers purpose, required input type, scope, and pricing, leaving little ambiguity for a tool of this complexity. It could mention pagination behavior explicitly, but the schema already documents page/limit.

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 description adds the nuance of '明确指定的企业名称', but this is already implied by the schema's '必填' and the example. It does not add significant meaning beyond the parameter descriptions already present.

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 ('查询') and resource ('该企业在全国各地的分支机构'), with clear scope and output fields (分支名称、负责人、成立日期、经营状态). It also distinguishes itself from sibling tools by explicitly focusing on branch information and including '包含分公司'.

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 indicates that a specific, exact company name is required, providing usage context. However, it does not mention alternatives or explicitly state when not to use this tool, so it falls 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 does not contradict the openWorldHint annotation. It adds some informational context (returned fields) but does not disclose any behavioral nuances beyond what the annotation already hints at (e.g., non-deterministic results, potential variations). Since annotations are present, the description's extra value is limited, but it is not misleading.

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 concise sentence that front-loads the purpose. However, it includes extraneous pricing information that is not functional guidance. This is a minor deduction, as the core description is efficient and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description does not need to detail return structure. It clearly states the main returned fields (project name, type, policy rewards) and the required input. It is sufficient for a query tool but could include a note about pagination or result limits, though these are covered by the schema and parameters. Overall, it is adequate for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for all 3 parameters (page, limit, company_name). The description adds minimal extra meaning beyond reiterating that company_name is required and emphasizing the need for an explicitly specified name. Baseline for high coverage is 3, and the description does not significantly enrich parameter 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 clearly states it queries policy subsidy information a specified company can apply for, listing returned fields (project name, type, policy rewards). It distinguishes from the sibling tool 'company_acquired_subsidy' (acquired vs. can apply). The verb '查询' and specific resource 'policy subsidy' 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 states the need for an explicitly specified company name but does not provide explicit guidance on when to use this tool versus alternatives like 'company_acquired_subsidy'. It lacks any 'when not to use' or explicit alternative pointers, so usage context is implied but not fully articulated.

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, which the description does not elaborate on. No mention of pagination behavior, data freshness, potential incompleteness, or any side effects. As a query tool, it lacks disclosure of operational nuances beyond the schema's basic parameters.

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 main description is a single clear sentence, but the appended pricing line is irrelevant to tool selection or invocation, adding noise. Structure is front-loaded with the purpose, but the extra pricing metadata detracts from conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Has an output schema, so return values are covered elsewhere. The description lists key fields returned and includes pagination parameters from schema. It is adequate for a straightforward query tool, though it does not mention error conditions or data scope limitations.

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 covers all parameters (100% coverage), so description adds minimal extra meaning. It emphasizes '明确指定的企业名称' (clearly specified company name) which reinforces the required parameter but does not go beyond schema details for page/limit. Baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool queries qualification certificates for a specified company, listing specific fields returned (certificate number, type, dates, status, details). This distinguishes it from sibling tools like company_licensing or company_basic_info, as it is specifically about certificates.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide any guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites beyond requiring a company name. It simply states the action without contextualizing its place among many company-related 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?

The only behavioral trait mentioned is the per-run cost in the pricing line. The description does not state whether the operation is read-only, what the output format is, or any side effects. Since annotations are minimal (only openWorldHint), the description carries the burden but provides little beyond the function name.

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 a clear main statement followed by examples. The pricing information is included separately and does not clutter the core explanation. Slightly redundant phrasing ('基于明确的企业名称') but overall 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?

The description adequately explains what the tool does and gives concrete examples, which is sufficient for understanding purpose. It does not describe the return structure or any edge cases, but given the absence of an output schema, it is reasonably complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already describes all parameters (company_name required, page and limit with defaults and maximums). The tool description only repeats that company_name is needed and does not add additional semantic meaning or constraints 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 that the tool queries a company's change records, including specific examples like legal representative, registered capital, and business scope changes. The verb '查询' (query) and resource '变更记录' are specific and distinguish this tool from sibling tools that handle other types of company data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides example use cases (e.g., legal representative change, registered capital change) which implicitly communicate when this tool is appropriate. However, it does not explicitly compare with alternative tools or state when not to use it.

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

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

The annotation openWorldHint=true is present, and the description does not contradict it. The description adds context about the data fields returned but does not disclose pagination behavior, potential absence of data, or any rate limits. With only one annotation, the description carries moderate burden but provides limited behavioral detail beyond the schema.

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

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

The description is concise, one sentence that states the purpose and lists key data fields. It is front-loaded with the core function. The pricing information is included but is structured data, not prose. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has an output schema, so return values are covered. The description covers the core purpose and data fields. However, it does not mention pagination behavior (though the schema covers page/limit), nor does it clarify what happens if no mortgage data exists. For a query tool with good schema coverage, this is adequate but not exceptional.

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 (company_name, page, limit) with clear descriptions. The tool description adds no additional parameter semantics beyond what the schema provides, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool queries chattel mortgage information for a specified company, listing the fields returned (registration date, status, secured amount, registration authority, registration number). It distinguishes from siblings by focusing on '动产抵押' (chattel mortgage) specifically, which is a distinct data type among the many company-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 implies usage when a company's chattel mortgage information is needed, but does not explicitly state when to use this tool versus alternatives like company_equity_pledge or company_equity_freeze. No exclusions or alternative tool names are provided, though the specific data type (动产抵押) makes the context 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 clearly states it queries competitor information by company name. There's no mention of call cost in the description (though the cost is noted separately), rate limits, or what happens when no competitors are found. The description is clear about the operation type but doesn't reveal mutation vs. read-only behavior explicitly – though the openWorldHint annotation suggests broad result sets are possible.

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 focused paragraph listing the data fields returned. It's concise but does include the pricing block inline, which might be better placed elsewhere, but it's short and doesn't add much noise. Overall, 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?

The description clearly states the purpose, lists the key fields returned, and mentions required parameter. However, it doesn't explain pagination or how many results are typically returned. But with a good input schema and output schema (present), this is quite complete. Also, the pricing info is embedded, which is extra but not harmful.

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 high (all 3 parameters have descriptions). The description adds company_name's purpose and example, page/limit pagination semantics are explained in schema. Description doesn't add value beyond schema for 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 competitor information (竞品信息) for a specified company name, and enumerates the exact fields returned (project name, funding round, founding date, location, etc.). The verb '查询' (query) with the specific resource '企业竞品信息' (company competitor info) makes the purpose unambiguous and distinguishes it from sibling tools like company_basic_info or company_data_search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description specifies the required input (company_name) and lists output fields, but provides no guidance on when to use this tool versus alternatives. Among many sibling tools, there's no mention of when querying competitors would be more appropriate than, say, company_data_search, or whether prerequisites apply (e.g., company must exist in database).

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 pricing information (0.2 credits per run) which is useful behavioral context. However, it does not mention auth requirements, rate limits, or pagination behavior. The annotation only provides openWorldHint, so the description adds some value but remains incomplete for a data 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 a single paragraph, concise, and front-loaded with the key purpose. The pricing info is embedded at the end, which is slightly unusual but does not detract much. Every sentence adds value, though the pricing could be in a metadata field.

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 returns a specific set of fields described in the output schemahola, so the description need not repeat them. The description focuses on the core use case and parameters. Given the rich schema and annotations, the description is adequately complete for a targeted query tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already provides full parameter descriptions (company_name with example, page, limit). The description adds no additional parameter guidance beyond explicitly stating the company name must be specific. With 100% schema coverage, baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool queries software copyright information for a specified company, listing the specific data fields returned (登记号, 软件全称, 版本号, etc.). This is a specific verb+resource combination that distinguishes it from generic company data 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 indicates it requires a specific company name ('基于明确的企业名称') and explains the purpose, but does not explicitly discuss when to use this tool versus alternatives like company_patent or company_trademark. No prerequisites or exclusions are mentioned, so the guidance is adequate but not 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?

Only annotation is openWorldHint; no readOnlyHint or destructiveHint. Description implies a read operation ('查询') but does not explicitly state side-effects or permissions, and no additional behavioral details are provided beyond the basic query intent.

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

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

Description is a single concise sentence with no redundant content, clearly conveying 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?

No output schema is provided, and the description does not explain return structure or pagination behavior. While the query purpose is clear, the lack of output details makes the description incomplete for a full understanding of expected results.

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?

All three parameters have schema descriptions with 100% coverage. However, the descriptions add no extra meaning beyond the parameter names and basic types; page/limit are typical pagination fields and company_name is self-explanatory.

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 queries credit rating information for a specified company, listing specific fields like subject rating, outlook, agency, and time, which clearly distinguishes it from sibling tools like company_basic_info.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool vs alternatives. It only describes the action, but lacks context on scenarios or comparisons with other company-related tools.

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