SupplyGraph.AI (Daasmart)

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

Annotations are minimal (only openWorldHint: true). The description discloses output scope (counts and industry stats, not details) and pricing (100 credits per run), but does not explain potential edge cases like address ambiguity, data freshness, or failure modes. It adds some transparency but not deep 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 long but well-structured in Chinese, with clear paragraphs for purpose, output, exclusions, and examples. It is appropriately sized for the complexity, and each sentence adds meaningful information. Some redundancy (e.g., repeating address format in schema) but overall concise.

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

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

The description covers purpose, scope, constraints, output types, exclusions, typical usage, and pricing. With an output schema available and thorough parameter descriptions, it is highly complete for an address-based statistics query tool. It leaves little ambiguity for an 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?

Schema covers both parameters extensively (city format, address structure), so baseline is 3. The description adds value by reinforcing that the address must be a specific based on examples, and clarifies that city cannot be a district/county. It provides illustrative queries that clarify parameter usage beyond 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 business statistics (counts and industry classification) around a specific Chinese address. It differentiates from siblings like business_surrounding_shop and cbd_surrounding_* by explicitly listing what it returns (statistics, not lists) and typical query examples.

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

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

It provides explicit usage context: valid for specific China addresses (not city/district names, not overseas), and gives examples of typical questions. It also clearly states exclusions (no name lists, no POI stats, no housing/population) which helps agents choose this tool over 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?

Beyond the sparse openWorldHint annotation, the description discloses that the output is an aggregated count statistic rather than a list of names/coordinates, and it explicitly states exclusions such as business/self-employed counts and housing price/population indexes. This gives the agent a clear understanding of what will not be returned.

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 purpose, included category types, explicit exclusions, and typical example questions. It is compact relative to the functionality it covers, though the appended pricing information adds some noise beyond the semantic tool description.

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

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

For a two-parameter query with an output schema and openWorldHint annotation, the description is sufficiently complete: it states the request scope, supported address format, exclusion of disallowed input granularity, and the output statistic style. It does not need to explain the output schema in detail since one is present.

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 parameter semantics are already well documented; the description adds useful example question patterns and reinforces the distinction between city-level and specific-address input. It supplements it slightly, but most parameter meaning still comes directly from the input schema.

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

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

The description clearly states the tool queries aggregate shop statistics near a specific Chinese address, covering categories like dining, shopping, and entertainment. It explicitly distinguishes itself from related sibling tools by excluding company counts, housing prices, and population indices, and by noting it does not return detail lists of shop names or coordinates.

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: it requires a geocodable specific address in China, explicitly rejects city/district names as inputs, excludes overseas addresses, and provides typical example question formats. However, it does not explicitly name alternative sibling tools for the excluded cases, so guidance for alternatives is only implicit.

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

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

With only openWorldHint as annotation, the description carries the disclosure burden. It clearly explains that the tool returns aggregated ratings and indexes rather than raw store/station lists, and explicitly lists excluded content such as housing prices, investment advice, and population counts. This gives the agent a reliable behavioral model 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 longer than average but well-organized: a lead functional sentence, then include/exclude lists, then example queries, then pricing. Every section adds decision-relevant information; there is no filler, though the example list could be trimmed without major loss.

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

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

Despite having no visible output schema, the description compensates thoroughly by listing the exact categories of returned star ratings and indexes, the descriptive fields, exclusions, input constraints, and pricing. An agent can confidently select and invoke the tool while setting correct expectations about the result shape.

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 city and address well. The description adds value by reinforcing address granularity constraints, providing realistic examples, and clarifying that city must be a prefecture-level name without suffix. This goes beyond the schema, though not dramatically.

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

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

The description states a specific verb+resource: querying surrounding amenity analysis for a concrete China-based address. It clearly differentiates from sibling tools like cbd_surrounding_population or housing by enumerating included metrics (education/medical/shopping/transit star ratings and indexes) and explicitly excluding 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 strong usage boundaries: addresses must be specific China-locatable points, not city/district names, and overseas addresses are unsupported. It provides typical question patterns and defines what outputs are and are not included. It does not explicitly name sibling tools as alternatives, but the include/exclude guidance makes appropriate use 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 openWorldHint annotation is minimal, so the description carries most of the behavioral disclosure. It adds significant detail: the tool is read-only, returns aggregate consumption indices rather than raw data, and has geographic constraints (specific points only, support Domestic China). It also states what is excluded (per-capita expenditures, store lists, housing prices). This goes beyond annotations and gives the agent a clear understanding of the tool's nature and limitations.

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

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

The description is moderately long but well-structured, with clear sections for purpose, included metrics, exclusions, and typical questions. It is front-loaded with the core function and uses bullet points for lists, making it easy to scan. While it includes pricing, that's supplementary and doesn't bloat the core description. No superfluous sentences; every part earns its place.

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

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

Given the tool has only 2 parameters, an output schema (present though not shown), and clear limitations, the description is exceptionally complete. It covers the purpose, exact scope of outputs, exclusions, usage examples, and geographic constraints. It even provides typical question phrasings to help the agent map user requests. With sibling tools to differentiate, this description leaves no ambiguity about what the tool returns and when it's appropriate, making it a model of contextual completeness.

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

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

Schema description coverage is 100%—both 'city' and 'address' have detailed descriptions including format and examples. The tool description reiterates the address format and gives typical questions, but adds little beyond the schema's guidance. It emphasizes that the address must be a specific point, which is already implied in the schema's 'must be a locatable address'. Thus, the description provides minimal added value over the schema, warranting a baseline score.

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 consumption analysis (consumption grade index and description) around a specific Chinese address. It explicitly distinguishes from siblings by specifying it's about consumption, not companies, shops, amenities, housing, or population, and lists exclusions like transaction details and POI lists. The verb 'query' plus resource and scope make it highly 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 question examples that map to this tool, and gives constraints: must be a specific locatable point, not city/district names, and within China. It implicitly guides usage by listing what it does not include, which hints at alternatives, but does not explicitly name sibling tools like business_surrounding_shop or cbd_surrounding_amenity. Still, the context is clear enough for an agent to infer when 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?

annotations 只有 openWorldHint，没有 readOnlyHint 或 destructiveHint，因此描述承担了主要行为说明责任。它清楚说明工具返回的是聚合型指标与投居建议而不是明细列表，并交代了地址粒度的限制和排除范围。整体透明度良好，只是未涉及鉴权、调用限制或更高层的 API 行为。

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?

描述先在第一句点明用途，再用涵盖范围、排除项和典型问法组织信息，结构清晰且前置信息有效。虽然列表和示例使文本较长，但每一部分都在为工具选择和调用成功服务，没有明显冗余。

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?

该工具只有 2 个参数且都有完整 schema 说明，同时存在 output schema，因此不需要额外解释返回结构。描述已经覆盖输入校验规则、返回内容边界、非目标内容、典型示例和地理限制，对代理正确选工具和构造调用足够完整。

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

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

输入 schema 对 city 和 address 两个参数的覆盖率是 100%，因此基线为 3。描述额外补充了可接收的具体地址类型范围，如门牌、地标、路名、小区名、园区出入口，并明确禁止使用市名或区县名本身，这为参数取值提供了 schema 之外的实际语义帮助。

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?

描述以明确动词和资源说明工具用途：基于中国境内具体地址查询周边房价与投资分析，并清楚说明这是关于均价、行情、走势和好卖好租指数的分析，而不是成交明细或挂牌列表。这使其能明显区别于 cbd_surrounding_consumption、cbd_surrounding_population、cbd_surrounding_amenity 等同族工具。

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

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

描述给出了明确的使用边界：地址必须是中国境内可定位的具体点，不能用市名或区县名，不支持境外地址，并明确说明不返回成交明细或挂牌列表。典型问法也增强了适用场景判断；但没有显式点名在不符合条件时应换用哪个替代工具，因此未达到最高分。

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 discloses behavioral traits beyond the openWorldHint annotation: it clarifies the tool returns population structure/density indices and descriptions, not detailed census data (explicitly states '不是户籍统计明细或人口名单'). It also defines the address format requirements and what it does not support (overseas, city names). No contradiction with annotations. While it doesn't mention side effects (read-only implied), it adds valuable context about output scope and limitations.

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

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

The description is somewhat lengthy but well-structured: it states the core function first, then lists included metrics, then exclusions, and ends with example queries. Every section adds useful information. It could be slightly more concise by grouping related constraints, but it is not verbose or repetitive. The examples at the end are helpful for the agent.

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

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

Given the tool is of moderate complexity (2 required params), has a complete schema, and has an output schema, the description provides all necessary context: address constraints, supported indicators, exclusions, and usage examples. It doesn't mention error cases or special handling, but that is not required given the output schema exists. The description is complete enough for an agent to select and invoke the tool correctly.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds significant value: it explains the city parameter must be a prefecture-level city name without '市' suffix, and the address parameter must be a structured Chinese address with examples (北京市朝阳区阜通东大街6号). It also clarifies the acceptable address types (门牌, 地标, 路名, etc.) and the exclusion of city/county names. This goes beyond the schema descriptions.

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

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

The description explicitly states the purpose: query population analysis (structure/density indices and descriptions) around a specific address in China. It uses specific verbs (查询/返回) and clearly scopes to Chinese locatable points, excluding city/county names and overseas addresses. It also lists included metrics (人口结构指数, 居住密度指数, 商务密度指数) and excluded data (户籍数量, POI details), distinguishing it from sibling tools like cbd_surrounding_amenity or business_surrounding_shop.

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

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

The description provides clear usage context: it specifies the geographic constraints (specific address not city names), lists what is included and excluded, and gives typical example queries that indicate when to use this tool (e.g., asking about population structure around a specific address). It doesn't explicitly name alternative tools, but the domain boundaries are clear enough to differentiate from other cbd_surrounding_* siblings.

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

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

With no readOnly/destructive annotations and openWorldHint=true, the description clearly states this is a list-returning query tool, explicitly noting '仅返回数量不返回名单' is excluded here. It does not document pagination or limits, but as a read-style query, the annotation gap is less critical.

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 query purpose between parentheses, then details exclusions, and ends with examples. The pricing block in the description field is metadata noise that doesn't belong. Exclamation marks and list-style formatting are acceptable but the pricing info is redundant.

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 list query with 2 required parameters and an optional year. The description fully covers what it returns (merged list of A-level taxpayer company types), what it excludes, pricing, and example queries. No output schema was provided but the description clarifies the merged text return format.

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

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

The schema describes region and chain_name with examples)Skip year is described as optional. The description adds typical query patterns but does not explain what 'region' should look like (e.g., is 成都 a city or province?) or chain_name depth. However, schema coverage is 100% for parameters, and the description gives example values that disambiguate somewhat.

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 provides a specific verb + resource (查询 A级纳税人企业列表) with clear scoping (by specific region and industry chain). It explicitly lists the four return categories (总/生产型/销售型/依赖型) and excludes others. Example queries clarify expected usage patterns.

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 the context (region + chain name) and provides three concrete example queries. It states what is not returned (other business classifications, and only counts without lists via the num variant). However, it doesn't explicitly differentiate from the many sibling 'chain_*_list' tools or mention when to choose this over others, though the A-taxpayer scope is 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 only openWorldHint as annotation, the description carries the burden of explaining behavior. It discloses that the output is a merged text containing total, production-type, sales-type, and dependency-type counts, and clarifies what is not included. This is useful behavioral context beyond the schema and annotations.

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

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

The description is well-structured and front-loaded with the core purpose, followed by included metrics, exclusions, and examples. The pricing line is extra but harmless, and the overall length is reasonable for the level of detail 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?

The tool is simple with 3 parameters and an output schema, and the description covers purpose, scope, exclusions, and example queries. It is complete enough for an agent to understand when and how to invoke it, though it could more explicitly direct users to the sibling list tool for company-level details.

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

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

Schema coverage is 100%, with every parameter already described. The description reiterates region levels and chain-name examples, adding only minor illustrative value through typical questions. It does not significantly enhance the parameter semantics 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 the tool queries A-level taxpayer enterprise counts based on a specific region and industry chain name. It explicitly distinguishes itself from list-type siblings by saying it returns aggregated counts and excluding enterprise list details.

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

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

The description provides typical usage examples and explicitly states exclusions (other enterprise classifications and company list details), which helps differentiate from the corresponding list tool and other numeric chain tools. It does not explicitly name alternative tools, but the context and examples strongly imply 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?

The description discloses useful behavioral boundaries: it returns a merged text with totals/types and does not return counts alone. However, with only openWorldHint in annotations and no readOnly/destructive hints, the safety profile is not explicitly stated, though the word '查询' implies read-only 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 well-structured with clear sections for metrics, exclusions, typical questions, and pricing. It is somewhat long, but every section contributes useful context for selecting and invoking the tool correctly.

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, typical queries, output composition, and exclusions, and an output schema exists. The main gap is that the optional year parameter's default behavior when omitted is not clarified, but overall the tool is sufficiently well-specified for an 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?

Schema coverage is 100%, so the baseline is 3. The description adds value by giving region granularity ('国家，省份，城市，区县') and concrete examples that map year, region, and chain_name parameters, going slightly beyond the schema descriptions.

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

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

The description clearly states the tool queries the list of companies closed in a given year for a specific region and industry chain, and specifies that it returns a merged text of total/production/sales/dependent types. It also explicitly excludes count-only results, distinguishing it from sibling count tools like chain_close_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?

Typical question examples ('2024年全国集成电路当年注销的企业名单') provide concrete usage context. The '不包含：其他企业分类的统计；仅返回数量不返回名单' line clarifies when not to use this tool, though it does not explicitly name alternative sibling tools.

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

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

注释仅含openWorldHint，无readOnly或destructive声明，描述未提及操作副作用或权限要求，但作为查询工具风险较低，未与注释矛盾。

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?

描述仅三句话，简洁明了，包含用途、排除项和典型问法，无冗余信息，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?

有输入schema但无输出schema，描述虽提及返回总量/生产型/销售型/依赖型文本，但未明确具体返回结构或示例，对调用方理解输出仍有不足，但比最低标准好。

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中每个参数都有描述，覆盖100%，描述未额外增加参数细节（如region格式），但描述了返回内容的合并类型，与参数关联有限，因此维持基线3分。

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

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

描述明确说明了工具用途是查询当年注销的企业数量，并具体提到了返回总量、生产型、销售型、依赖型的合并文本，典型问法提供了清晰示例，与兄弟工具（如chain_new_start_company_num）形成区分。

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

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

描述通过'不包含其他企业分类的统计'和典型问法给出了使用场景，但未明确与其他数量查询工具（如chain_new_start_company_num）的对比条件，不过基本使用时机已隐含。

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, leaving the description to disclose behaviors. The description mentions it returns text and lists, but does not disclose potential side effects, external data access, rate limits, or authentication requirements. For a query tool with minimal annotations, this is a significant gap.

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: a main sentence, a bullet list of included types, exclusions, and typical questions. The pricing note is extra but not detracting. It is front-loaded with the core action.

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

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

For a list-query tool with an output schema present, the description covers the main use cases, inclusions/exclusions, and parameter semantics adequately. It does not specify pagination or result limits, but the output schema might handle that. Overall, it is complete enough for an agent to use 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 provides detailed descriptions and examples for all three parameters (100% coverage), so the description adds little beyond clarifying that region can be country/province/city/district and that results are aggregated. The baseline of 3 is appropriate; it enhances but does not compensate for any lack.

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 enterprise lists based on specific region and industry chain name, with a breakdown into total/production/sales/dependent types. It distinguishes from siblings like chain_company_num by explicitly stating it returns lists, and includes typical queries to clarify intent.

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

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

It provides explicit inclusion/exclusion criteria (e.g., not including other enterprise categories, not returning only counts) and gives typical question examples. However, it does not name specific alternative tools, though it implies numbers-only queries belong to the _num siblings.

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 usefully explains that the tool returns a merged text count covering total, production, sales, and dependent types, and sets expectations by excluding other classifications and lists. This adds meaningful non-obvious behavior beyond the schema/annotation, though it does not discuss year-default behavior or exact response details (covered by output 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?

Description is compact and well-structured using lines for included metrics, exclusions, and examples; no filler. The pricing block adds operational cost context, and the example questions earn their place by disambiguating parameter usage.

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 an output schema and many sibling tools, the description is largely sufficient: it covers purpose, parameter usage, output scope, and exclusions. The only minor gap is absence of explicit sibling tool names for list/category-specific alternatives, but the exclusions and sibling list make this recoverable.

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 100% of parameters with individual descriptions, establishing baseline 3; the description strengthens this by giving region granularity ('国家，省份，城市，区县') and realistic value examples for chain_name and year. It doesn't repeat schema definitions, but adds practical usage context for 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?

States '基于具体地区...产业链名称企业数量查询' — a specific verb (query) and resource (enterprise counts by chain and region). It distinguishes itself from sibling list tools and category-specific count tools by noting the merged return of 总量/生产型/销售型/依赖型 and explicitly excluding other classifications and list details.

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

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

Provides clear context with typical questions ('2024年全国集成电路企业有多少' etc.) and explicit exclusions ('不包含：其他企业分类的统计；企业名单明细'), which tells the agent not to use this for lists or other specialized categories. It does not name specific sibling tools as alternatives, so it stops short of full when/when-not guidance.

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

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

With only openWorldHint as an annotation, the description carries the behavioral burden and discloses that the tool returns merged text for total/production/sales/dependent lists and explicitly excludes other classifications and count-only output. This adds useful context beyond annotations, though it does not mention pagination or data-source details.

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

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

The description is somewhat dense but well-organized with bullet points for types, exclusions, and examples. The pricing note is extra but not distracting. Every section contributes to understanding tool behavior and selection.

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

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

Given the full schema descriptions and the presence of an output schema, the description adequately covers the tool's core behavior, exclusions, and typical usage scenarios. It leaves no major 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 schema already provides 100% coverage with parameter descriptions. The description enriches this by giving typical questions that demonstrate how year, region, and chain_name combine, and clarifies that region can be at country/province/city/district level. This goes beyond the schema baseline.

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

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

The description clearly defines the tool as querying discredited company lists by specific region and industry chain, and explicitly lists the included subtypes (total/production/sales/dependent). It also distinguishes itself from count-only tools by stating '不包含：仅返回数量不返回名单', and the typical question examples 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 provides typical question patterns and states exclusions ('其他企业分类的统计', '仅返回数量不返回名单'), which implies when to use this tool versus count-oriented siblings. However, it does not explicitly name the alternative tool such as chain_discredited_company_num, leaving the comparison implicit.

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 the openWorldHint annotation present, the description takes on the burden of disclosing behavior. It details that the result merges total/production/sales/dependent counts and specifies exclusions, adding useful context beyond the annotation. No contradiction exists, but more depth on output format or edge cases could elevate transparency further.

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 a main definition, an include/exclude list, and examples. It is slightly verbose due to the metric list repetition, but every sentence earns its place by clarifying scope and usage.

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 and annotations are minimal, the description adequately covers the tool's purpose, metric breakdown, exclusions, and example queries. It is complete for a count-based tool, with no major gaps noted, though it could explicitly note that results are aggregated at the provided region level.

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 descriptive examples for region and chain_name. The description adds value by showing how to express queries for region and chain together via typical questions, reinforcing parameter semantics without introducing new constraints. This goes slightly beyond the baseline 3 by aiding correct parameter mapping for LLMs.

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

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

The description clearly states the tool queries the count of discredited enterprises ('失信人企业数量') by region and industrial chain, using specific verb+resource+scope. It distinguishes itself from the sibling list visualization by explicitly focusing on counts and listing the four metric types included while excluding company lists and other classifications.

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 when-to-use context via '典型问法' examples 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 alternative sibling tools (e.g., chain_discredited_company_list), instead relying on implicit differentiation, which warrants a 4 rather than 5.

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

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

The description discloses meaningful behavioral details beyond the schema: it returns a merged result across total/production/sales/dependency categories, and explicitly excludes other classifications and count-only output. The openWorldHint annotation does not conflict, and no safety annotation is present, so the description carries the burden well.

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, followed by useful structured details and examples. The pricing line is extraneous metadata, but the rest of the text is efficient and each line contributes to understanding the tool.

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 three simple parameters and an output schema, the description adequately covers selection and invocation by providing scope, returned categories, exclusions, and examples. An explicit pointer to the count-only sibling would improve it, but it is not necessary for correct use.

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

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

Schema coverage is 100%, so parameters are already documented. The description adds extra value by specifying region granularity (country, province, city, district), giving realistic chain_name examples, and showing year usage through typical questions.

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 lists of companies with software copyrights (软著) filtered by region and chain name, and enumerates the specific list types returned. This distinguishes it from sibling tools like chain_have_copyright_company_num (count-only) and other chain_*_company_list tools.

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

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

The description gives typical example questions and explicit exclusions ('不包含：其他企业分类的统计；仅返回数量不返回名单'), making it clear this is for list retrieval rather than count-only queries. It does not explicitly name alternative sibling tools, but the usage 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?

The description provides useful behavioral context beyond the single openWorldHint annotation: it clarifies that the output is aggregated count text covering total/production/sales/support-dependent types, not a company list. It also discloses pricing in credits per run. It could mention empty-results or error behavior, but it is largely transparent for a 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 organized into overview, metric types, exclusions, example questions, and pricing. It is somewhat long and includes pricing details, but each section adds useful guidance and the examples make it easy to understand invocation patterns.

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 and well-documented parameters, so the description only needs to add context about semantics. It does this by explaining the exact metric types, excluded outputs, and canonical query phrasings. For a three-parameter aggregate count tool, this is sufficiently complete.

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

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

Schema coverage is 100%, so parameters are already described. The description adds contextual meaning by specifying region levels such as country/province/city/district and giving realistic example mappings for both region and chain_name. This helps the agent choose appropriate inputs beyond simply echoing 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 the count of companies with software copyrights (拥有软著的企业数量) for a specified region and industrial chain. The metric categories (总量/生产型/销售型/依赖型) are explicitly listed, and the description distinguishes this as a count tool rather than a list tool, especially via the exclusion of 企业名单明细.

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 explicit boundaries: it returns only aggregate counts for the named classification types and excludes other categories and company lists. It also provides typical queries showing when to use it. However, it does not name specific sibling alternatives such as chain_have_copyright_company_list, though the exclusion of company lists helps guide selection.

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

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

The description discloses that the result merges total/production/sales/dependent-type text and excludes other classification stats. While annotations already include openWorldHint, the description adds useful behavioral context about the return composition and boundaries 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 reasonably concise and front-loaded with the core purpose, followed by exclusions and examples. The pricing information adds minor extra length but is still useful context. It could be slightly tighter by trimming redundant indicator lists.

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 moderate-complexity tool with an output schema, the description covers the key usage context, exclusions, and typical queries. It does not over-explain return values, which is acceptable given the output schema, and the openWorldHint annotation handles data completeness caveats.

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 value by providing concrete examples for region ('全国', '成都', '北京市海淀区'), chain_name ('集成电路', '新能源', '人工智能'), and year (2024), which helps the agent map natural language queries 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 the tool queries a list of companies without patents based on specific regions and industry chain names. It differentiates from sibling tools by explicitly excluding count-only returns and other classification statistics, which aligns with chain_have_no_patent_company_num and patent-related list tools.

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

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

The description provides typical question examples showing when to use the tool and 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 tells the agent not to use this tool when only counts are needed. However, it does not explicitly name the alternative sibling tool for counts.

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

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

描述清楚说明返回的是合并后的总量及生产型/销售型/依赖型文本，并声明统计不包含其他企业分类和名单明细。开放世界标注未在描述中展开，但描述本身没有与注解冲突，且行为边界基本清楚。

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?

描述先给主要用途，再给出指标范围、排除项与典型问法，信息密度合理；Pricing 信息属于计费元数据，可独立展示但不严重干扰阅读。

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?

在已有输出 schema 情况下，描述覆盖了查询维度、返回指标和排除内容，并给出多个地域层级例子；对于一次聚合查询类工具而言已较完整。

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

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

输入 schema 对 region、chain_name、year 均有描述，覆盖率 100%，描述未明显增加参数格式、默认值或约束。描述中的典型问法对 year 的示例提供了补充，但总体未超出 schema 已有信息。

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?

描述以明确的动词+宾语说明功能：基于地区和产业求没有专利的企业数量；同时列明了具体统计口径（生产型/销售型/依赖型），并与链上其他“有专利数量”“无专利名单”等兄弟工具形成有效区分。

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?

描述给出了典型问法、适用地区和产业类型，并明确“不包含”企业名单明细及其他企业分类，能帮助判断不做名单明细查询。但未直接点名推荐的兄弟工具（如 chain_have_no_patent_company_list），排他性和替代方案说明仍可更明确。

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

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

Beyond the minimal annotation (openWorldHint), the description reveals important behavioral traits: it returns a merged text containing total/production/sales/dependent types, and it does not return counts alone or other classification statistics. It also discloses pricing (100 credits per run). This adds meaningful context beyond what annotations provide, though it does not elaborate on the open-world nature of 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 well-organized: a clear purpose statement, followed by included indicators, exclusions, typical questions, and pricing. Each component contributes to understanding without redundancy. It is somewhat dense, but no unnecessary filler is 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 the tool's moderate complexity (3 simple parameters, no nested objects, output schema present), the description provides sufficient context: purpose, expected inputs, output format (merged text list), exclusions, and pricing. Typical questions further anchor usage. It is complete for an agent to select and invoke the tool correctly.

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

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

The input schema already covers all three parameters with descriptions (100% coverage). The description adds value by showing concrete usage patterns for region and chain_name, and clarifying that year is optional. It also clarifies the scope of 'region' by mentioning country/province/city/district, which enriches 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 companies with patents based on a specific region and industry chain name. It specifies the included subcategories (production, sales, dependent) and explicitly excludes other classifications or count-only results, distinguishing it from sibling tools like chain_have_patent_company_num and other chain_*_list variants.

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

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

The description provides typical question examples that illustrate when to use the tool (e.g., "2024年全国集成电路拥有专利的企业名单") and what inputs are expected. It also explicitly states what is not included (other classifications, count-only results), offering useful exclusions. However, it does not explicitly name alternative tools, so the guidance is clear but not exhaustive.

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

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

The description discloses that the result merges total, production, sales, and dependent counts into text form, and it explicitly scopes out other company classifications and list details. The openWorldHint annotation is not contradicted; the description adds useful 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?

The description is well-structured and front-loaded with the core purpose. It has slight redundancy between the first sentence and the '涉及指标/类型' line, but the exclusions and typical questions earn their place.

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

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

For a three-parameter count tool with an output schema, the description covers input scope, metrics, exclusions, and examples. It is adequate for an agent to decide and invoke the tool, though it could explicitly mention when to prefer it over related chain_*_num 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?

The input schema already describes all three parameters with 100% coverage and relevant examples. The description adds region granularity (country/province/city/district) and real query phrasings, but these largely reinforce rather than substantially extend schema information.

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 action and resource: counting companies with patents by region and industry chain. It clearly distinguishes itself from sibling list tools and other chain_*_num tools by specifying '拥有专利的企业数量' and explicitly excluding company list details and other classification stats.

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 clarifies required context (specific region and chain name). The '不包含' line indicates what the tool does not cover, helping an agent decide when not to use it, though it does not explicitly name alternative sibling tools.

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

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

The description discloses that the tool merges and returns text combining total and category-specific lists, and clarifies it does not only return counts. However, it lacks details on output format, pagination, or any limitations (e.g., maximum results). With only openWorldHint annotation, the description carries some burden; it provides partial behavioral info but not comprehensive 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 somewhat verbose, including pricing information and a somewhat confusing exclusion statement ('仅返回数量不返回名单' could mislead). The core purpose is front-loaded, but the extra details make it less crisp. It could be tightened by removing the pricing line and clarifying the exclusion phrasing.

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

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

Given that the tool has an output schema (not provided), the description adequately explains the query scope and return text, but it does not specify pagination, result limits, or error behavior. For a list tool, these details might be important. The examples help, but overall it is sufficient yet not 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?

Schema coverage is 100% with clear descriptions for region ('全国','成都','北京市海淀区') and chain_name ('集成电路','新能源'). The description adds examples and clarifies region granularity, but these largely mirror the schema. It does not add significant new constraints or format details beyond what 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 it queries high-tech enterprise lists based on region and industry chain, listing specific types (total/production/sales/dependent). It distinguishes from sibling 'num' tools by explicitly saying it returns lists, and provides concrete example questions. The verb '查询' and resource '高新技术企业列表' are 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 includes typical usage examples and explicit exclusions ('不包含' section), which helps the agent understand scope. However, it does not explicitly name any alternative tools or state when not to use this tool versus other chain_list variants (e.g., chain_company_list), so it falls short of full 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 the aggregate return format (total/production/sales/dependent text) and clarifies what is not covered. There is no contradiction with annotations. It does not mention any side effects, but as a query tool, no such expectations are needed.

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

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

The description is well-structured with a purpose sentence, metrics list, exclusions, and examples, which is informative. The inclusion of pricing details is extra metadata that slightly lengthens the description but does not severely impact readability.

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, the description fully covers the input scope, return metrics, exclusions, and usage examples. An output schema exists, so return value details are not needed. The description is complete for an agent to decide on and 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 input schema already provides exhaustive descriptions for all three parameters (year, region, chain_name), so schema coverage is 100%. The description adds example queries but no new parameter-level semantics beyond what the schema offers, keeping it at the baseline.

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

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

The description clearly states the tool's function: querying high-tech enterprise counts by specific region (country/province/city/district) and industry chain. It explicitly lists the return indicators (total/production/sales/dependent) and excludes other classifications and company lists, distinguishing it from sibling list tools like chain_high_tech_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 example questions and explicitly states exclusions ('不包含：其他企业分类的统计；企业名单明细'), signaling when not to use the tool. However, it does not name alternative sibling tools explicitly, though the '企业名单明细' exclusion implies the list variant.

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 meaningful behavioral context beyond the openWorldHint annotation: it discloses that results are merged text across total/production/sales/dependent types, that only lists (not counts) are returned, and that other business classifications are excluded. It does not contradict 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 first sentence front-loads the core purpose clearly. The rest enumerates included metrics and gives examples, which is helpful but somewhat repetitive because each metric repeats the same '近两年有对外投资的企业列表' phrasing. The embedded pricing block adds noise but does not destroy readability.

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 explain return values. It sufficiently covers the query scope, included categories, exclusions, and typical user phrasings. Minor gaps include no mention of pagination or list size limits, but overall it is complete for effective tool selection.

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

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

Schema coverage is 100%, but the description adds semantic value by clarifying region granularity (country/province/city/district), showing concrete examples for chain_name, and providing typical natural-language queries that map to parameters. It could further clarify the year vs. 'last two years' relationship, so not 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 and resource: it queries companies with external investment in the last two years by region and industry chain. It also distinguishes itself from sibling tools like chain_invest_company_num (count-only) and chain_invested_company_list (companies being invested, not investing) by explicitly stating it returns lists and covers '对外投资' (outbound investment).

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 list results of companies with recent external investment in a specific region/chain. It also 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 implies the count-only sibling should be used for numbers. However, it does not explicitly name alternative tools, so it stops short of full 5.

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

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

With no readOnlyHint/destructiveHint annotations provided, the description carries the full disclosure burden and mostly delivers: it discloses the aggregation behavior (merged total/production/sales/dependent types), the two-year time window, exclusions, and even pricing (100 credits/run). It aligns with the openWorldHint annotation by using open-ended 'such as' examples for region and chain_name. Minor gaps: no discussion of empty-result behavior, though the presence of an output schema mitigates this.

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

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

The description is well-structured with clear sections (purpose, metrics, exclusions, examples, pricing), front-loaded with the core meaning. It is dense but organized. Loses one point for slight redundancy — the typical questions restate the metrics and the default time window '近两年' is repeated three times.

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, 100%-schema-coverage count tool with an output schema and openWorldHint annotation, the description covers all essential aspects: what it does, what it returns, what it excludes, cost, and examples. The only real omission is guidance on which sibling to use when the user needs complementary data (e.g., invested-company counts or detailed lists), which is a moderate 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 coverage is 100% with good examples for all three parameters (region: 全国/成都/北京市海淀区; chain_name: 集成电路/新能源/人工智能), so the baseline is 3 per the rubric. The description adds moderate value by clarifying the 'past two years' temporal scoping of the optional year parameter and the four-type breakdown, but does not significantly extend parameter understanding beyond what the 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 a specific verb+resource+scope: querying the count of companies with outbound investments in the past two years, filtered by region and industrial chain name. It explicitly enumerates the four return metrics (total/production/sales/dependent types), lists exclusions (other classifications, list details), and provides three concrete example questions. It implicitly distinguishes from its near-twin sibling chain_invested_company_num via the phrase '有对外投资' (has outbound investments).

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 through typical question formats and explicit exclusions (does not include other classifications or list details). However, it never explicitly names alternatives like chain_invest_company_list for lists or chain_invested_company_num for invested companies — differentiation relies on the user connecting the exclusion of '企业名单明细' to the list sibling. Usage is implied rather than stated, falling short of explicit when-to-use/when-not-to-use 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 provide openWorldHint with no readOnly/destructive hints, so the description must disclose behavior. It fails to clearly state whether the tool returns a list or only a count—the phrase '仅返回数量不返回名单' (only returns count, not list) contradicts the tool's name and purpose. No mention of side effects, permissions, or rate limits, leaving critical 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 a single block of text, reasonably sized with typical queries, but the inclusion of '仅返回数量不返回名单' introduces confusion and detracts from clarity. It is not poorly structured but could be more concise with explicit separation of purpose and exclusions.

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

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

Despite having an output schema, the description leaves a fundamental ambiguity about whether the tool returns a name list or just a count. The merged return text for subtypes is mentioned, but the contradictory '仅返回数量不返回名单' undermines completeness. For a tool with 3 parameters and multiple output aspects, this is a significant 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 covers all parameters at 100%. The description adds meaningful context: region can be country/province/city/district, year is optional reference year, and 'last two years' is inherent. This goes beyond schema, though it does not elaborate on value formats or edge 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 the tool queries companies with external financing in the last two years for a specific region and industrial chain. It lists the subtypes (total, production, sales, dependent) and typical query examples, effectively distinguishing it from sibling tools like chain_invested_company_num (count) and chain_invest_company_list (companies making investments).

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 formats and an exclusion clause ('does not include other classifications; only returns count, not list') provide some usage context, but no explicit guidance on when to use this tool versus alternatives like the count-only sibling 'chain_invested_company_num'. The examples imply usage but do not clarify the list vs count ambiguity.

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 of total/production/sales/dependent counts and that other classifications and company lists are excluded, adding context beyond the openWorldHint annotation. No contradiction with annotations was found.

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

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

The description is structured into function, included metrics, exclusions, and example queries, with the main purpose front-loaded. It is somewhat repetitive in the metrics section and includes a pricing block, but each section contributes useful selection context.

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 and only three parameters, the description is largely complete: it defines the count type, the region/chain dimensions, the returned breakdown categories, and typical phrasings. Minor gaps remain around the meaning of omitting 'year' and the slight mismatch between '产业链名称' in the description and '产业链或节点名称' in the schema.

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

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

The schema already documents all three parameters, so the baseline is 3; the description adds useful value examples ('全国', '成都', '北京市海淀区', '集成电路', '新能源', '人工智能', '2024') and region granularity. It still leaves the optional year's default behavior implicit.

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

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

The description opens with a specific action and scope: querying the count of companies that had external financing in the past two years by region and industry chain. It enumerates the exact metrics returned and explicitly excludes company-list details, making it clearly distinguishable from sibling count/list tools.

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

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

The description gives typical question phrasings and explicit exclusions ('不包含：其他企业分类的统计；企业名单明细'), which signal when not to use it. It does not name alternative sibling tools or contrast with chain_invest_company_num, so it just misses the top score.

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 rich behavioral context beyond the sparse openWorldHint annotation: the merged text return covering four subtype lists, the hardcoded two-year time window, and explicit exclusions of other enterprise categories and count-only results. This is significant value beyond the annotation.

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

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

The description is front-loaded with the core purpose and well-structured with sections for included indicators, exclusions, and examples. It is slightly bulky due to the embedded pricing block, which belongs in metadata rather than the description, and three example queries that are somewhat redundant.

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 and rich examples, the description is nearly complete. The main ambiguity is the interaction between the optional 'year' parameter and the stated '近两年' (past two years) window—whether year anchors the window or filters the statistical year is not fully explicit. Otherwise, exclusions, scope, and pricing are covered.

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 value by specifying region granularity (country/province/city/district), clarifying chain_name as an industry chain/node, and demonstrating parameter usage through realistic example queries like '海淀区人工智能近两年发起过招标的企业有哪些'.

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 that initiated tenders in the past two years, scoped by region (country/province/city/district) and industry chain name. It names the specific verb '查询', enumerates the four included list types (total/production/sales/dependent), and distinguishes from siblings like chain_participated_tender_company_list by specifying '发起过招标' (initiated tenders).

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 ('不包含：其他企业分类的统计；仅返回数量不返回名单') clarifying this returns lists, not counts, and gives three typical question examples showing when to use it. However, it does not explicitly name alternative sibling tools (e.g., chain_issued_tender_company_num for counts), leaving differentiation to the tool name.

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 most of the transparency burden. It discloses that the tool returns a combined text of total/production/sales/dependent counts, specifies the two-year scope, lists exclusions, and even shows the per-run credit cost. It could clarify how the optional year interacts with the 'last two years' window, but the behavior is largely transparent.

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

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

The description is front-loaded with the core purpose, then uses line breaks, an indicator list, exclusions, and typical questions to organize details efficiently. It is longer than minimal, but each section adds decision-relevant context and no significant redundancy is 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?

For a three-parameter count tool with many sibling list/count variants, the description covers region semantics, metrics, exclusions, cost, and example phrasings; since an output schema exists, detailed return-value explanation is unnecessary. A minor gap is the lack of explicit explanation for how the optional year relates to the 'last two years' window, but overall the description is sufficiently complete.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds useful meaning beyond the schema. It clarifies acceptable region granularity (country, province, city, district), gives concrete chain-name examples, and demonstrates year usage through typical questions, which helps the agent map user intent to 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 opens with a clear query action and resource: querying the number of companies that issued tenders within the last two years by region and industry chain. It explicitly lists the returned metrics and states that company-name details are excluded, which distinguishes this count tool from the sibling list tool chain_issued_tender_company_list.

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

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

The description provides clear usage context through typical questions and explicit exclusions, such as not including other enterprise classifications or company name lists. However, it does not explicitly name alternative sibling tools like chain_issued_tender_company_list or chain_participated_tender_company_num, so it stops short of full when-not/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 important behavioral details beyond the openWorldHint annotation: it returns merged text containing total/production/sales/dependent types, and explicitly excludes other classification statistics or count-only results. This adds meaningful context about the output composition, though it does not describe pagination or other possible side effects.

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

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

The description is well-structured with clear sections (included indicators, exclusions, typical questions) and is relatively concise for the amount of information conveyed. It includes pricing info, which is not directly functional but may be pertinent for cost-aware agents. Slightly busy 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?

Given the tool's moderate complexity (3 params, output schema exists), the description is sufficiently complete: it states what is returned (list of listed companies with type breakdowns), what is excluded, and provides use-case examples. The openWorldHint annotation further clarifies that results may not be exhaustive. The only minor gap is not mentioning any result limit or pagination behavior, but that is acceptable for a list-query tool with an output schema.

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

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

Schema coverage is 100% and all parameters have descriptions, but the description adds valuable semantic context beyond the schema: it explains region can be country/province/city/district (with examples like '成都市' and '北京市海淀区'), and gives concrete chain_name examples ('集成电路', '新能源'). This enriches the understanding of parameter values beyond the schema's generic descriptions.

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

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

The description clearly states the tool's function: querying listed company lists by region and industry chain name, with a specific verb '查询' and resource '上市企业列表'. It explicitly differentiates from sibling count tools by stating '不包含：仅返回数量不返回名单', making its scope 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 questions ('典型问法') that illustrate when to use the tool, and states exclusions ('不包含') to clarify boundaries. However, it does not explicitly name alternative sibling tools (e.g., chain_listed_company_num), so the guidance is clear but not fully explicit about 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 an openWorldHint: true annotation present, the description adds useful context: pricing details, merged text output, and exclusions. However, it fails to address the open-world data caveat that the hint flags—i.e., that counts might be incomplete—which is notable given the count-type nature of the tool. 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 information-dense yet efficiently organized with a main clause, metric list, exclusions, examples, and pricing. It's on the longer side but each sentence earns its place, covering exclusion and cost information without unnecessary fluff.

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

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

For a tool with a simple flat schema (3 params, no nesting) and a count-based output (output schema present), the description covers purpose, return format, exclusions, examples, and even billing. The only real gap is not addressing the openWorldHint data-quality implication, but the description is otherwise complete for its complexity.

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

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

Schema description coverage is 100%, so the schema already documents year, region, and chain_name with examples. The description's example questions subtly reinforce how natural-language queries map to parameters but add no format or syntax detail beyond the schema, justifying only the baseline score.

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: querying the count of listed companies (上市企业数量) by region and industry chain. It further details the merged return types and provides concrete example questions. This distinguishes it from sibling list/count tools by emphasizing the 'listed' (上市) qualifier and count-type return.

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 what's included, excludes other company classifications and company lists (不包含), and gives typical query examples. However, it does not explicitly name alternative sibling tools (e.g., 'use chain_listed_company_list for details'), so it lands 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 tool returns a merged text output across four company types and excludes certain data, which adds behavioral context. Annotations only provide openWorldHint (no readOnly/destructive hints), so the description carries the burden; it names the types and what is not included, but doesn't detail response structure or any data freshness limits. No contradiction found.

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 relatively compact, with a clear opening line, a list of involved indicators, a 'not included' line, and three typical questions. It's slightly verbose but well-structured with bullet-like formatting, making it easy to scan. No fluff.

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

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

The tool is moderately complex with 3 parameters and an output schema, but the description covers the essential query context (region, chain, year), what types are returned, and exclusions. It lacks details on output format (though output schema exists) and any limitations (e.g., data availability by year), but given the schema support, it's adequately 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 description coverage is 100%, covering all three parameters with clear descriptions and examples. The description reinforces region and chain_name semantics via examples but doesn't add significant meaning beyond the schema, so a baseline of 3 is appropriate.

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

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

The description clearly states the tool's purpose: to query newly added companies in a specific region and industry chain for a given year, returning merged text for total/production/sales/dependent types. It distinguishes from siblings by focusing on 'new start' (chain_new_start_company_list) versus other company metrics, and the typical question examples clarify 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 question examples and states what is not included (other classifications, count-only returns), which gives some usage context. However, it doesn't explicitly contrast with the sibling 'chain_new_start_company_num' (which returns counts) or other 'chain_*_company_list' tools, so the when-to-use guidance is implied rather than explicit.

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

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

The description discloses that the result is a merged text containing total/production/sales/dependent counts and explicitly excludes company list details. However, annotations only include openWorldHint and do not declare read-only or destructive behavior, and the description does not clarify default-year behavior or limitations.

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

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

The description is front-loaded with the core purpose, followed by metric breakdowns, exclusions, and examples. The metrics list partially restates the first sentence, and the pricing block adds bulk, but the overall structure is organized and useful.

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 an output schema and many sibling count/list tools, this description is largely complete: it covers scope, return composition, exclusions, and typical phrasing. The main gap is the lack of explicit guidance on the optional year parameter's default 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 coverage is already 100%, and the description adds useful semantics beyond the schema by specifying regional granularity (country/province/city/district) and giving typical chain name examples. It does not clarify what happens when the optional year is omitted, so full credit is not warranted.

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

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

The description clearly states that this tool queries the count of newly established companies for a specific region and industry chain, returning merged totals for production, sales, and dependent types. It explicitly excludes company list details, distinguishing it from sibling list tools like chain_new_start_company_list.

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

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

Typical question examples provide clear usage context, and the '不包含' line rules out list requests and unrelated classification stats. It does not explicitly name sibling count tools or state when to prefer them, but the intended scenarios are easy to infer.

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 responsibility for behavioral disclosure. It reveals that the tool returns merged text for total/production/sales/dependent subcategories, that it excludes other categories, and that it returns lists rather than counts. It also includes pricing, which adds operational transparency. It does not discuss pagination or limits, but the output schema exists to cover return structure.

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

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

The description is moderately detailed but every sentence serves a purpose: the first defines the core function, the second enumerates returned subcategories, the third clarifies exclusions, and the fourth provides examples. The pricing block is structured and compact. Slightly verbose due to repeated phrases, but overall well-organized and front-loaded.

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

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

For a three-parameter tool with an output schema and many closely related siblings, the description provides a solid picture: what it returns, what it excludes, example phrasings, and cost. It does not elaborate on the meaning of '近两年' relative to year or define the subcategories, but the output schema and examples sufficiently disambiguate the core 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 coverage is 100%, so the baseline is 3. The description adds value by explaining region granularity (country, province, city, district), giving concrete examples for chain_name, and showing realistic combinations of year with region and chain in typical questions. This helps agents map natural-language expressions 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 a query for a list of companies that participated in tenders within the past two years, filtered by specific region (country/province/city/district) and industry chain name. It also explicitly distinguishes from count-only tools by noting it returns lists and merges total/production/sales/dependent types, making it distinct from siblings like chain_participated_tender_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 through typical user questions and explicitly states exclusions: it does not include other company categories and does not return only counts. While it does not explicitly name the sibling count tool, the phrase '仅返回数量不返回名单' strongly signals that users wanting counts should use a different tool, so usage context is clear but alternatives are not explicitly named.

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?

描述明确说明返回的是合并后的文本型数量结果，并列出含哪些指标、不含哪些内容，避免误以为返回名单或全分类。虽然缺少显式的非破坏性/只读声明，但“查询”语义清晰，pricing 额外提供了每次运行的信用成本。

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?

描述分块清晰，先讲核心能力，再列指标，再排除内容，最后给典型问法，信息密度合理。缺点是“近两年参与过投标的企业数量”在指标列表中重复了四次，稍微冗余，但整体仍易于快速理解。

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

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

结合输入 schema 和输出 schema，描述已经覆盖了地区、产业链、统计方式、指标类型及排除项，对简单计数类查询而言足够完整。主要遗留是 year 参数可选时如何与“近两年”关联、以及是否需要明确区分链“发布招标”和“参加投标”的兄弟工具。

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

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

输入 schema 已对 region、chain_name、year 提供完整描述，覆盖率为100%，因此基线为3。描述中的典型问法补充了地区、产业链名和可选的年份使用场景，但并未在 schema 之外对参数语义做更深入说明，例如 year 与“近两年”的关系。

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是基于具体地区和产业链名称查询“近两年参与过投标的企业数量”，并有“合并返回总量/生产型/销售型/依赖型文本”的清晰说明。与同名 _list 系列工具形成明显区分，动词、对象、统计粒度都很明确。

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

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

描述通过“不包含：其他企业分类的统计；企业名单明细”和典型问法给出了使用边界，能帮助确认该工具适合获取汇总数量而非明细列表。但没有显式提及当需要名单时改用 chain_participated_tender_company_list，因此未完全达到最高分。

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

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

With only openWorldHint as an annotation, the description carries the burden of behavioral disclosure. It explains that the tool returns a combined text with totals and breakdowns, and clarifies exclusions. It does not mention side effects or limitations, but the read-only nature is implied. The description adds context beyond the minimal 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 a clear flow: main purpose, included types, exclusions, and examples. The inclusion of pricing information is extraneous but not too distracting. It earns its space without excessive 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?

Given the presence of an output schema and full parameter coverage, the description adequately contextualizes the tool's usage. It explains the breakdown of returned data and typical queries. It lacks explicit mention of edge cases or prerequisites, but these are covered by the schema and examples, making it sufficiently complete.

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

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

The input schema has 100% coverage for all three parameters with clear descriptions. The description gives example values for region and chain_name, reinforcing the schema, but does not add significant new information beyond what the schema already provides. Baseline of 3 is appropriate.

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

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

The description clearly states the tool's function: querying specialized companies (专精特新) by region and industry chain, with a breakdown of types. It explicitly distinguishes from sibling tools by focusing on the 'specialized' category and listing what it includes and excludes, making it uniquely identifiable.

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

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

The description provides typical query examples and states what the tool does NOT include, giving context for when to use it. However, it does not explicitly name alternative tools (e.g., chain_specialized_company_num for counts), so guidance is implicit rather than explicit.

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

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

Beyond the annotations, the description discloses that the result is a merged text containing four count types and states what is not included. It does not detail error or missing-data behavior, but for a query/count tool with an output schema, the coverage is adequate and no annotation contradiction exists.

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

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

The description is front-loaded with the core purpose, followed by metric types, exclusions, and examples. It is well structured and informative, though the pricing block adds extra context not strictly needed for tool selection or invocation.

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

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

For a relatively simple count-query tool, the description covers scope, return metrics, exclusions, and realistic example queries. Since an output schema is present, detailed return-value description is less necessary; only a named list-tool alternative would make it fully 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 documents all three parameters with examples and 100% coverage. The description adds typical question phrasing and region-level guidance, but it provides little additional parameter semantics beyond what the schema already contains.

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

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

The description clearly specifies the resource (专精特新企业数量), the required dimensions (region and industrial chain), and the return type (merged text of total/production/sales/dependent counts). It also distinguishes this tool from list-style siblings by explicitly excluding company list details and other classification statistics.

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 when-to-use context: only for specialized-company counts by specific region and chain, with typical question examples. It explicitly lists exclusions (other company categories and company name lists), but it does not explicitly name alternative tools such as chain_specialized_company_list or chain_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?

Beyond the openWorldHint annotation, the description discloses important behavioral details: it returns merged text for total/production/sales/dependent SME lists, excludes other statistic types, and is a list-returning tool rather than a count-only tool. It also includes pricing information. It does not mention pagination or result limits, but the output schema helps cover the return structure.

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

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

The description is compact and well-structured: it leads with core purpose, then lists included types, exclusions, and example queries. The metric list is slightly repetitive and the Pricing block is metadata-like noise, but overall it remains scannable and every section contributes useful context.

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 sufficiently complete. It gives the region/chain prerequisite, output category text, exclusions, and user-style examples, so the agent can select and populate the tool correctly with normal user input.

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, and the description adds value with concrete input granularity (国家/省份/城市/区县), example regions (全国, 成都市, 北京市海淀区), and example chain names (集成电路, 新能源, 人工智能). This helps the agent map natural-language user requests to the right 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 identifies the query resource: 按地区和产业链查询科技型中小型企业列表, and lists its specific sub-types (总量/生产型/销售型/依赖型). It also gives concrete typical questions showing the expected user intent, distinguishing this list tool from count-only or generic company-list tools.

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

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

The '不包含' section explicitly states what is not covered (其他企业分类统计, 仅返回数量不返回名单), so the agent knows when this tool is inappropriate. Typical question examples provide clear usage context. It does not explicitly name an alternative tool like chain_tech_oriented_company_num, but the intended usage and exclusions are 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 discloses that output is a merged text of total/production/sales/dependent counts and excludes other categories and list details, adding context beyond the minimal openWorldHint annotation. It does not explain optional-year default behavior, but the query semantics and output categories are reasonably transparent.

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

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

The description is compact and well-structured: one core query statement, an indicator list, an exclusion list, and example questions. Every sentence adds useful information 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 output schema and full schema descriptions, the description adequately covers purpose, input semantics, result categories, and exclusions for a straightforward count query. The main gap is that optional year behavior is left to the schema's '可选' field rather than explained in the description.

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 region granularity ('国家，省份，城市，区县'), chain-name examples, and natural-language query mappings. This goes beyond the schema's basic parameter descriptions.

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

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

The description clearly specifies the action: query counts of tech-oriented SMEs by region and industry chain. It enumerates the exact returned indicators (总量/生产型/销售型/依赖型) and explicitly excludes list details, distinguishing it from sibling list tools.

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

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

Typical question examples ('2024年全国集成电路科技型中小型企业有多少') provide clear usage context, and the '不包含' line states what is not covered. However, it does not explicitly name an alternative tool such as chain_tech_oriented_company_list for getting company lists.

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

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

Beyond the openWorldHint annotation, the description discloses important behavior: it merges and returns text for four company-list categories, and it excludes count-only and other classification statistics. It does not clarify the interaction between optional 'year' and the recent-two-years range, but the output schema and annotation mitigate some 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 largely concise and front-loaded with the core purpose. The excluded-includes examples and the "典型问法" examples are useful. Minor redundancy exists between the parenthetical categories and the detailed 涉及指标/类型 list, but this is 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 simple list-query tool, the description covers the key selection signs: required region and chain name, optional year, output categories, exclusions, and common question patterns. Together with an output schema and the existing annotations. This is sufficient for an agent to select and invoke the tool correctly in most contexts.

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 practical value by showing region granularity (country/province/city/district), realistic example queries with year, region, and chain_name values, and clarifying that the output is a list rather than a count.

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 concrete action: query company lists that won tenders in the last two years by region and industry chain. It enumerates the categories returned (total/production/sales/service) and explicitly excludes count-only results, which clearly differentiates it from sibling count tools like chain_won_tender_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 usage context with typical question examples and explicitly states what is not included: other enterprise classifications and count-only results. However, it does not explicitly name an alternative tool for count-only queries, so it falls slightly short of full when-to-use guidance.

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

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

The description discloses that the tool returns a merged text of aggregate counts by company type, excludes list details and other classifications, and is scoped to a two-year window. This adds meaningful behavioral context beyond the minimal openWorldHint annotation, though it does not clarify how the optional year anchors the 'near two years' window.

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

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

The core purpose is front-loaded, and the exclusions plus typical questions are useful. The repeated indicator list is slightly verbose and the embedded pricing dict is machine-oriented, but overall the description remains compact and well organized.

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

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

Given a simple 3-parameter query and the presence of an output schema, the description covers purpose, metric categories, exclusions, and example questions. The main gap is the ambiguous relationship between the optional 'year' parameter and the 'last two years' time window.

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 (country/province/city/district), providing chain_name examples, and showing typical year usage, which goes beyond the generic schema property 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 opens with a specific verb+resource statement: querying the number of companies that won tenders in the last two years by region and chain name. It clearly enumerates the returned metric categories and explicitly excludes company list details, distinguishing it from the sibling list tool chain_won_tender_company_list.

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

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

Typical questions and explicit exclusions ('不包含：其他企业分类的统计；企业名单明细') give clear context for when to use this aggregate count tool rather than a list tool. However, it does not explicitly name the alternative tool, so the guidance is strong but not fully explicit.

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

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

The description discloses that the tool merges and returns text for total/production/sales/dependent types and clarifies it does not include other categories or count-only results. With only openWorldHint annotation (no readOnlyHint or destructiveHint), the description partially carries the burden. It does not mention side effects, pagination, or authorization requirements, which is a gap for a query tool, but the key behavioral aspects are 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 organized into clear sections: purpose, indicators, exclusions, and typical questions. It is front-loaded with the primary purpose and uses bullet-like line breaks for readability. While slightly verbose with the indicator enumeration, each part serves a clear function and avoids extraneous detail.

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 and the schema descriptions cover all parameters, the description provides adequate context for typical use. It explains the main output intended (combined text of types) and explicitly states what is not included, helping to set expectations. Minor omissions like pagination or ordering are not addressed, but these are likely captured in the output schema, so the completeness is solid.

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 descriptions are comprehensive (100% coverage) and align with the examples in the description (e.g., region='北京市海淀区', chain_name='人工智能'). The description adds typical question patterns that illustrate parameter values, but this is largely redundant with the schema descriptions. No new semantics are introduced, 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 returns a list of companies surviving 5+ years within a specified region and industry chain, and explicitly enumerates the included types (total, production, sales, dependent). This distinguishes it from sibling tools like chain_year5_company_num (which returns counts only) and chain_company_list (which lacks the year filter). Typical question examples further cement 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 gives explicit examples of when to use the tool (e.g., '2024年全国集成电路存续5年以上的企业名单') and states what is excluded ('仅返回数量不返回名单'), implying that for counts one should use the count sibling. However, it does not explicitly name alternative tools or specify scenarios where other chain list tools are more appropriate, so guidance is good but not fully 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?

Annotations only include openWorldHint=true, so the description must carry the behavioral burden. It discloses that the return is merged text ('合并返回总量/生产型/销售型/依赖型文本') and excludes lists, but it does not explicitly declare read-only/safety behavior or mention any side effects. The verb '查询' implies a read operation, but this is not explicit.

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

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

The description is well-structured and front-loaded with the core purpose, followed by metrics, exclusions, and examples. It is somewhat lengthy due to listing all metric types and including pricing, but every sentence adds useful information. Not overly redundant.

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 values. It adequately covers metrics returned, exclusions, and typical usage scenarios, and differentiates sufficiently from the many sibling chain tools. Missing details like parameter constraints are already covered by the schema.

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

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

Schema coverage is 100%, providing baseline 3. The description adds value by specifying region hierarchy ('国家，省份，城市，区县') and giving concrete examples for both parameters, which helps the agent construct valid inputs beyond the schema's generic 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 states a specific verb ('查询') and resource ('存续5年以上的企业数量') with clear scope (based on region and chain name). It distinguishes from sibling chain count tools by focusing on 5+ year survival and explicitly excluding other categories and list details, as seen in '不包含：其他企业分类的统计；企业名单明细'.

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 ('2024年全国集成电路存续5年以上的企业有多少') that imply when to use it. It also states what it does not include, helping avoid misuse for list or other-category queries. However, it does not explicitly name alternative tools, 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?

No annotations are present, so the description carries the full burden. It states the tool queries data but does not disclose side effects, permissions, or limitations (e.g., whether it is read-only). The description is straightforward but lacks behavioral details like data freshness or potential errors.

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 no redundant information. It front-loads the core function and lists output fields efficiently.

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 input schema is fully described, but the output schema is not provided, which limits completeness. However, the description mentions the output fields (project name, type, etc.) giving some context. Slight deduction for missing explicit output structure.

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

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

All three parameters (company_name, page, limit) have clear descriptions with examples and purpose. The schema coverage is 100%, and the description adds value by clarifying the meaning of page and limit.

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 approved subsidies for a specified company, with specific output fields listed. It distinguishes from sibling tools that focus on other data types (e.g., company basic info, financing).

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 explicitly mention when to use this tool versus alternatives, but the clear purpose and parameter requirements imply it is for retrieving subsidy data. No explicit exclusions or alternative recommendations are provided.

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

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

The description adds useful context: the company name must be explicitly/full-name specified, and it discloses pricing (0.2 credits per run), which is valuable cost-awareness for an agent. The '查询' phrasing implies a read-only operation and does not contradict the provided 'openWorldHint' annotation. However, it doesn't disclose error behavior, empty-result handling, rate limits, or external API dependencies, so it's 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 a single efficient sentence that front-loads the core behavior and returns summary. The appended pricing block is useful metadata. It's compact and skimmable; slight formatting awkwardness with the inline price dict prevents a 5, but it remains appropriately short.

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, 1-required-field tool with an output schema present, the description covers the key bases: what it does, what's returned (app name, category, intro), and the exact-name input requirement. The pricing disclosure is a bonus. Minor gaps like pagination semantics and empty-result behavior exist, but the provided output schema and clear purpose make this 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?

Schema description coverage is 100%, with all parameters (company_name, page, limit) documented including default values, max constraints, and an example for company_name. Per the rubric, the baseline is 3. The description adds minor value by clarifying the required input format (exact full enterprise name) and indicating the returned fields, but doesn't substantially extend 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 a specific verb and resource: query APP information (including name, category, intro) for a given enterprise name. It's immediately clear what the tool does. However, it does not explicitly differentiate itself from the many sibling company_* tools or state why an agent should pick this over a sibling like company_basic_info, so it stops short of a 5.

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

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

Usage context is implied rather than stated: the reader must infer this tool is for looking up a company's developed apps. There is no explicit when-to-use, when-not-to-use, prerequisites, or alternative tool mention. The phrase '明确指定的企业名称' hints at the exact-name matching requirement, but no exclusions or alternatives are given, so guidance is only implied.

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 includes pricing information (credits per run) which adds transparency beyond the annotations. However, it does not explicitly state that the operation is read-only or mention any side effects. The annotation openWorldHint is ambiguous and does not clarify behavior, so the description falls short of fully disclosing implications.

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 long list of return fields, which is informative but not concise. It could be summarized more efficiently, yet the enumeration is necessary to convey the breadth of data. The structure is a single block of text with no formatting, making it readable but not optimally organized.

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

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

The description lists all the fields that will be returned, covering the output scope effectively. However, it lacks information about error handling, empty results, or behavior when the company is not found. Given there is no output schema, this extra context would improve completeness, but the current description is adequate for basic usage.

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

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

The schema covers the only parameter 'company_name' with a description and example. The description redundantly restates that the query is based on an explicitly specified name but adds no new detail about the parameter's format, constraints, or usage. Since schema coverage is 100%, the baseline is met; no extra value is added.

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

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

The description clearly states the tool's function: '查询该企业的基本信息' (query basic information of the enterprise), followed by a comprehensive list of return fields. It is specific and differentiates from sibling tools by focusing on general company data rather than specialized subsets like patents, branches, or tenders.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention conditions, exclusions, or comparisons with sibling tools for specialized queries. The only instruction is that a company name must be specified, which is already in the schema.

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

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

The description discloses that the tool returns branches nationwide, includes branches (分公司), and lists included fields such as person in charge and establishment date. It also adds pricing information not encoded in annotations. The openWorldHint annotation does not create a contradiction.

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

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

The description is a single focused sentence plus a short pricing note. It is front-loaded, with no redundant filler or repetition of schema details.

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

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

Given that all three parameters are fully described in the schema, an output schema exists, and the tool is a straightforward filtered query, the description is sufficiently complete for an agent to understand when to call the tool and what to expect in return.

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 description coverage is 100%: company_name, page, and limit are all described in the input schema itself. The description adds only that the enterprise name should be precisely specified, which is already implied by the schema's required flag and 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 that, given a specified enterprise name, it queries all branches/sub-branches nationwide and lists returned fields (name, principal, establishment date, business status). This distinguishes it from sibling tools by naming the specific resource (branch info) and action (query).

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 sets a clear condition of use: when an exact and explicitly specified company name is available and branch information is needed. It does not explicitly state exclusions or alternatives among the large sibling list, but the intended scenario is 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=true, so the description carries most of the burden. It adds value by disclosing the cost structure (0.2 credits per run in the Pricing block) and the return fields, plus the requirement that the company name be explicitly specified. However, it doesn't mention behavioral traits like rate limits, auth requirements, or pagination behavior beyond what the schema provides — 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 a compact single Chinese sentence front-loading the core action followed by the pricing metadata. Every sentence earns its place, though the raw Python-dict-style pricing block is slightly verbose for a description field and could arguably be moved to structured metadata.

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 and 100% parameter documentation, the description's job is lighter. It adequately covers the tool's purpose and return fields. The notable gap is the lack of differentiation from the sibling company_acquired_subsidy, which would materially help an agent disambiguate when choosing between the two subsidy-related 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. All three parameters (page, limit, company_name) are documented in the input schema with defaults and examples. The description adds minimal extra meaning beyond re-emphasizing that the company name must be explicit and hinting at return fields, but it doesn't materially enhance 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 action — query policy subsidy information a company can apply for, listing return fields (project name, type, policy rewards). The verb '查询' (query) plus the specific resource makes it unambiguous, and the '可申领' (can apply) framing differentiates it from sibling company_acquired_subsidy. However, it doesn't explicitly call out this distinction, which costs it a full 5.

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

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

No guidance is provided on when to use this tool versus alternatives. A closely related sibling, company_acquired_subsidy, exists, but the description never explains that this tool covers prospective/applicable subsidies rather than already-received ones. The distinction is only implied by the tool name, not 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?

The description adds value by disclosing the exact certificate fields returned, and it discloses a per-run cost (0.2 credits), which is useful operational context. However, it doesn't contradict the openWorldHint annotation and provides no information on data freshness, source, or update frequency, which would be valuable given the annotation signals dynamic data.

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

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

The main purpose is front-loaded in a single, information-dense sentence that efficiently lists all relevant certificate fields before the pricing note. The description is lean and earns its place, though it could arguably be trimmed to remove the raw Python dictionary serialization of the pricing block.

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

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

For a simple, single-resource lookup tool with only three parameters, all covered by schema docs, and an output schema present to document return structure, the description is nearly complete. It meets most agent needs, with the only gap being the absence of explicit guidance on when to choose this over closely related siblings like company_licensing.

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

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

Schema description coverage is 100% — all three parameters (page, limit, company_name) are already documented in the schema with helpful detail including a concrete example for company_name. Per the rubric, high coverage warrants a baseline of 3, and the description neither needs to nor does it add parameter-level information beyond that 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 uses a specific verb and resource (查询...资质证书信息 — query qualification certificate info) for a precisely scoped target (explicit enterprise name) and enumerates concrete return fields (证书编号, 证书类型, 发证日期, certificate status, etc.). The term '资质证书' (qualification certificate) clearly differentiates it from sibling tools like company_licensing, company_patent, and company_trademark.

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

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

The phrase '基于明确指定的企业名称' (based on an explicitly specified enterprise name) implies this tool is for lookups when an exact, unambiguous company name is known, implying not for fuzzy/ambiguous queries. However, it does not explicitly state when not to use it, nor does it name alternatives among the large sibling set.

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 does not disclose behavioral details such as whether it requires authentication, handles pagination (though schema does), or any rate limits. It also does not clarify that results are returned as a list or that the tool is read-only. With sparse annotations, the description should bear more responsibility for transparency, but it only describes the basic purpose without additional 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 concise and front-loaded: it states the core function in the first sentence and provides helpful examples in the second. The pricing line is extra but relevant. No wasteful words; it is appropriately sized for the tool's simplicity.

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 straightforward: query change records by company name with optional pagination. The description covers the essential purpose and required parameter, and the schema covers pagination. An output schema exists, so return values need not be explained. The only minor gap is lack of guidance on when to use this vs. analytical enterprise_change_* tools, but for a direct data retrieval tool, the description is sufficiently complete.

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

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

Schema description coverage is 100%, with each parameter already well-described (company_name with example, page and limit with defaults/max). The description adds no new parameter-specific semantics; it only reinforces the overall purpose. Since the schema does the heavy lifting, the baseline of 3 is appropriate, but the description does not enhance 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 the tool queries enterprise change records based on a specified company name, with explicit examples of change types (legal representative, registered capital, business scope). This distinguishes it from sibling tools like company_basic_info or company_shareholder, which serve different purposes. The verb 'query' and resource 'change records' are specific and unambiguous.

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

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

The description implies usage: it requires a precisely specified company name and provides example use cases. However, it does not explicitly state when not to use this tool or mention alternatives (e.g., enterprise_change_* tools for analytical insights). The guidance is implicit rather than explicit, so an agent might need to infer the appropriate 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?

The annotations only provide openWorldHint, so the description carries most of the behavioral transparency burden. It accurately describes the returned data types but does not disclose behaviors such as exact-match requirements, absence-of-record handling, or pagination behavior beyond what the schema already documents.

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

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

The description is one clear, front-loaded sentence followed by a compact pricing line. The pricing metadata is somewhat extraneous for tool selection but does not meaningfully hurt clarity or 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?

For a relatively simple 3-parameter lookup tool with a complete input schema and an output schema, the description covers the main action and response fields. It lacks explicit guidance on edge cases like no matching company or empty results, but this is a minor gap given the structured 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%, so the baseline is 3. The description adds minimal parameter-level meaning beyond the schema, though it reinforces that company_name must be explicitly specified, which aligns with the required parameter.

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

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

The description clearly states the tool queries chattel mortgage information based on a specified company name, lists the main returned fields (registration date, status, secured claim amount, registration authority, registration number), and is distinct from related sibling tools like company_equity_pledge or company_equity_freeze.

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 establishes a clear use case: query chattel mortgage records when an exact company name is provided. It does not explicitly mention alternatives or exclusions, but the context is sufficiently clear to distinguish it from other company-information 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 openWorldHint annotation suggests the tool may have external side effects, but the description does not clarify what these are. The description adds basic utility (returns competitor info) but no additional behavioral detail beyond the annotation, such as data freshness or formatting.

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 the returned fields and pricing. The pricing info might be better in a structured field, but is not overly 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?

The description explains enough to use the tool effectively but does not mention pagination details (though the schema does), nor does it clarify the meaning of openWorldHint. It omits potential limitations like data coverage or update frequency.

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

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

The schema covers 100% of parameters with clear descriptionscars, and the description adds context about what data is returned for each company_name. Provides a good example for the key parameter.

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

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

The description clearly states the tool queries competitor information for a specified company name torch-Mark; explicitly lists the fields returned. It distinguishes itself from the many sibling tools by focusing specifically on competitors, though it does not name an alternative for broader company searches.

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

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

The description implies when to use (when you need competitor data for a company) but offers no guidance on when not to use it or what alternatives exist. Given the abundance of sibling tools, explicit differentiation would be valuable.

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 sparse openWorldHint annotation by enumerating the key output fields (registration number, software name, version, dates, owner, nationality, etc.) and clearly framing the operation as a query. It does not deeply discuss exact-match behavior or edge cases, but for this simple query tool the disclosure 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 a single, well-structured sentence that front-loads the main purpose and lists the return fields, followed by pricing. There is no wasteful repetition of schema details.

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

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

The tool is simple with one required parameter, full input schema coverage, and an output schema present. The description sufficiently covers intent, scope, and expected result content; no additional behavioral details are essential.

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

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

Schema description coverage is 100%, and each parameter already has a meaningful description. The tool description adds little beyond restating that the company name must be explicitly specified, which is already captured in the schema.

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

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

The description clearly states a specific verb ('查询') and resource ('软件著作权信息'), scoped to an explicitly named enterprise. It also lists the main returned fields, which distinguishes it from sibling tools like company_patent and company_trademark.

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

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

The description clearly implies when to use the tool: when you have a specific enterprise name and need its software copyright records. It does not explicitly mention alternatives or exclusions, but the resource scope is unambiguous enough for selection among siblings.

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 adds some behavioral context by listing output fields and pricing. It does not state read-only behavior or pagination specifics, but these are partly covered by the schema and the query nature of the tool. 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 a single, focused sentence followed by a pricing line. It is front-loaded with the core purpose and contains no filler or 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?

The description covers the tool's purpose, required input, and expected output fields, and an output schema exists. It is adequate for a simple lookup tool, though it could briefly mention how this relates to other company data tools for completeness.

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

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

Schema description coverage is 100%, so all parameters already have meaningful descriptions. The tool description adds no additional parameter semantics beyond what the schema provides; it only restates the role of company_name in the main sentence.

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

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

The description uses a specific verb '查询' (query) with a clear resource '信用评级信息' (credit rating information), and enumerates the fields returned (subject rating, outlook, agency, time). This clearly distinguishes it from sibling company-related 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?

The description states a precondition: the company name must be explicitly specified ('明确指定的企业名称'), which implies the user should have a precise name. However, it does not explicitly mention when to use this tool versus alternatives or provide exclusions.

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