SupplyGraph.AI

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

The pricing dictionary does disclose that each run consumes a significant number of credits that vary by chapter (e.g., 'Reputation' at 8481 vs 'Cost' at 1386), which is useful cost-transparency beyond what the schema offers. However, the openWorldHint annotation is never explained and no other behavioral traits (rate limits, side effects, report generation timing) are mentioned. The cost data is a genuine but narrow transparency contribution.

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 text is short and parseable, but the raw Python-dict pricing block is structurally noisy and not front-loaded with a useful verb phrase or usage context. A single run-on data dump is the opposite of well-structured descriptive copy. It's compact but not efficiently organized for an agent to consume.

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?

Although an output schema exists and the two parameters are well-documented, the description leaves fundamental questions unanswered—chiefly, what an 'exception' chapter represents and how this tool differs from the dozens of enterprise_change_* siblings that appear to cover similar topics (e.g., enterprise_change_license vs chapter 'License'). The pricing data also doesn't clarify the semantics of openWorldHint or when to bill at the chapter level vs ALL. The description is under-specified for the size and ambiguity of its tool family and simply dumps data instead of explanations.

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

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

Schema coverage is 100%, with a good pid description that includes an example ID and a pointer to search_company_candidates, and a chapter_name enum with a clear default. The description adds above-baseline value by encoding per-chapter pricing, enabling cost-aware parameter selection. This is a case where the overall parameter documentation does the heavy lifting well.

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's core text, 'Enterprise Change Report,' essentially restates the tool name/title and does not explain that this generates a multi-chapter corporate exception report. The remainder is a raw pricing dictionary that implies a paid report but never states what the tool does, when it's used, or what an 'exception' means. It hovers at tautology, forcing the agent to rely on the schema to infer purpose.

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

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

The description provides no when-to-use guidance, exclusions, or alternatives. With roughly 60 sibling tools (enterprise_change_*, due_diligence_report, supply_chain_risk_prediction, etc.), the failure to disambiguate is a critical gap. Only the schema's 'Omit or use ALL for the full corporate exception report' hints at 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?

With only openWorldHint=true in annotations, the description carries full responsibility for behavioral disclosure, but it fails to reveal critical traits: the pricing structure implies per-chapter pagination or selective generation but doesn't explain how responses are structured, whether generation is synchronous or asynchronous, or expected duration. The massive pricing block adds cost data but no behavioral context about the report output 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 dominated by a lengthy pricing block spanning dozens of chapter options with per-run costs, which dwarfs the actual purpose statement. The core utility is stated in one sentence, then buried under pricing noise. This is not conciseness; it's under-specification of intent paired with over-specification of commercial details, making it structurally imbalanced.

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 and good param documentation, the tool is complex (2 params, 43 enum values, interconnected with other tools like search_company_candidates) yet the description provides no information about report output structure, how chapters combine, execution time expectations, or cost strategy guidance (e.g., whether to run ALL vs individual chapters). The presence of an output schema partially compensates, but the description isn't complete enough for reliable agent usage.

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

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

Schema coverage is 100% with well-written parameter descriptions. The pid description explicitly explains it's an internal company ID from search_company_candidates with an example, and chapter_name lists all options with a clear default. The description adds only the pricing context (which is already partially represented in the enum options), providing minimal semantic enhancement beyond the schema baseline of 3.

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

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

The description states it 'Generates comprehensive supplier due diligence reports using global enterprise data,' which identifies the core action (generation) and resource (due diligence reports). However, it lacks specificity about what distinguishes it from sibling tools like corporate_exception_report or the enterprise_change_* suite, and the scope is overly broad ('comprehensive') without clear boundaries.

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 vaguely mentions 'for compliance and procurement decisions' but provides no guidance on when to choose this tool over its many siblings. The only useful usage signal is in the pid parameter description, which explains how to obtain the ID from search_company_candidates. No when-not-to-use or alternative tooling guidance is given.

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

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

Annotations include openWorldHint: true, but the description does not elaborate on this or add any other behavioral context such as side effects, permissions, data freshness, or result format. The description focuses on scope and indicators rather than behavioral traits. Given that annotations exist, the description does not contradict them, but it adds minimal behavioral insight beyond the structured 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 description is well-structured: it starts with the main purpose, then lists detailed indicators, exclusions, and examples. It is front-loaded with the core function. While the list of indicators is extensive, it directly serves to clarify the tool's exact scope and is not extraneous. The description is balanced in length and earns its content.

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

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

The description is comprehensive for a query tool with an output schema present. It covers all relevant indicators, explicitly lists exclusions, and provides multiple example use cases. Since an output schema exists, it does not need to explain return formats. The description addresses the complexity of the tool effectively, leaving no major gaps in understanding what it does and when to use it.

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

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

Both parameters (company_name and country_name) are fully described in the input schema, with examples (e.g., '比亚迪股份有限公司', 'Tesla, Inc.'). The tool description does not add additional semantics beyond the schema, as it only uses the parameters in example questions. Since schema coverage is 100%, the baseline is 3, and the description does not elevate this.

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: it queries periodic changes in business activities regarding off-site branches and subsidiaries, including new establishments, cancellations, and existing volumes. It distinguishes itself from sibling tools by explicitly excluding investment/financing activities and by specifying the scope (off-site branches/subsidiaries). The listing of specific indicators further clarifies exactly what the tool covers, leaving no ambiguity.

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

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

The description explicitly states exclusions: '不用于对外股权投资或融资引入等投融资活动查询' (not for investment/financing queries) and '不包含：非本分类指标；按园区/产业链批量筛企业名单' (does not include non-category indicators or batch screening by park/industry chain). It also provides typical question examples, which illustrate when to use the tool. However, it does not explicitly name alternative sibling tools, only implies them via the exclusions.

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

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

The description expands beyond the openWorldHint annotation by listing specific indicators, typical queries, and exclusions. It implies a read-only query behavior and does not contradict the annotation. However, it doesn't disclose any potential side effects or rate limits, but for a query tool this is acceptable given the output schema 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 structured: purpose, indicators list, exclusions, and typical examples. It is slightly lengthy but every section adds distinct value. It is front-loaded with the primary purpose and clear enough for quick scanning.

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

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

Given the output schema exists, the description fully covers what the tool does, its scope, key indicators, exclusions, and example queries. It is complete for a query tool of this complexity and leaves no major gaps for the agent to infer.

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% for the two parameters, so the baseline is 3. The description adds value by providing concrete examples (e.g., '中国比亚迪股份有限公司', '美国Tesla, Inc.') that clarify expected formats and combination with country names, enriching 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 it queries business strategy-related periodic changes for a specific enterprise, with concrete examples and explicit exclusions (industry-level macro research). It distinguishes itself from the many enterprise_change_* siblings by focusing on strategy and business composition.

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: it is for enterprise-specific queries, not industry-level, and explicitly lists non-included categories (e.g., batch screening). It provides typical query formats with examples, though it doesn't name alternative sibling tools directly. Some implicit guidance exists via the exclusions.

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

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

With only openWorldHint annotation present, the description carries the behavioral burden. It adds valuable context through indicator scope disclosure, exclusion lists, and pricing details. The verb '查询' clearly signals a read-only query operation. Doesn't contradict annotations. Minor gap: doesn't explicitly state read-only side effects, but the query semantics are implied strongly.

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?

Well-structured with clear sections: purpose statement, indicator list, exclusion list, and typical question examples. Front-loaded with purpose, each section serves a distinct function. The trailing pricing dict formatted as Python literal is slightly awkward and could be cleaner, minor deduction.

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

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

With an output schema present, return value explanation isn't required. The description covers purpose, in-scope indicators, out-of-scope use cases, and usage examples — complete for a 2-param query tool. Example patterns with real company names make invocation unambiguous. Could add pagination or regional coverage notes but not essential for this tool type.

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 both parameters (company_name, country_name) already well-documented with format examples. The description's typical questions (中国比亚迪股份有限公司研发投入额度) demonstrate parameter combination patterns, adding marginal value, but does not significantly extend what the schema already provides. Baseline 3 is appropriate.

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

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

The description explicitly states the verb '查询' (query) with a specific resource: capital brand periodic changes by enterprise, enumerating exact indicators (研发投入额度, 专利申报数量, 线上销售占比, 管理数字化程度). It actively distinguishes from siblings by excluding innovation result counts (不用于专利软著持有件数等创新成果数量统计), differentiating it from enterprise_change_innovation and other capital brand siblings.

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

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

Provides explicit when-to-use (基于具体企业名称按企业查询), explicit exclusions and alternatives (不包含非本分类指标、按园区/产业链批量筛企业名单), and concrete typical question patterns showing proper invocation format across different countries and companies. No ambiguity about which scenario this tool serves.

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

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

With only openWorldHint annotation, the description carries the burden of behavioral disclosure. It mentions scope limitations ('不包含：非本分类指标') and the per-company nature, but does not disclose response format, pagination, or behavior with unknown entities. There is no contradiction with annotations, but the description adds only moderate behavioral context.

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

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

The description is structured with clear sections: purpose, exclusions, typical questions, and pricing. It is slightly long but every part adds value, and the key purpose is front-loaded. The pricing information is practical for cost-aware agents.

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 two parameters and an existing output schema, the description adequately covers context: specific indicators, typical usage, and scope boundaries. It does not need to explain return values because the output schema exists. It could mention temporal aspects of '周期变化' more, but overall it is complete for its simplicity.

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

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

The input schema already provides 100% parameter documentation (both company_name and country_name have descriptions with examples). The description reinforces the parameter usage through typical questions but does not add meaning beyond what the schema provides, so the baseline of 3 is appropriate.

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

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

The description clearly states the tool's function: '按企业查询资本品牌方面的周期变化' with specific indicators like '机构持股集中度、机构持股稳定性、公募基金家数、投资者平均持股时间'. It also explicitly distinguishes itself from other enterprise_change tools by listing exclusions such as '非本分类指标' and '按园区/产业链批量筛企业名单'.

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

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

The description provides clear use cases with typical questions (e.g., '中国比亚迪股份有限公司机构持股集中度') and states what the tool is not for (not for compliance evaluation, not for batch screening). It implies when to use it but does not explicitly name alternative sibling tools, leaving some ambiguity among the many similar enterprise_change_* 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?

Beyond the openWorldHint annotation, the description discloses the exact scope of indicators (timeliness, accuracy, truthfulness, media doubts, regulatory penalties) and what is not covered. This adds meaningful context about behavior without contradictions, though it doesn't mention pagination or return format (but output schema 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 well-structured and front-loaded with the main verb and resource. It uses bullet-like lists for included/excluded items and gives clear examples. Some extra pricing metadata is attached but does not confuse the core purpose; it remains efficient overall.

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

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

Given the tool has an output schema, the return format is already defined. The description covers what it does, what it excludes, and provides representative queries, making it fully actionable for a 2-parameter tool. No additional context is needed for selection and invocation.

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

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

Schema coverage is 100% with both parameters well described and examples for country_name. The description reinforces parameter usage by showing complete queries (e.g., '中国比亚迪股份有限公司按时披露'), which helps clarify how country and company combine. This adds value beyond the schema.

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

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

The description clearly states the tool's purpose: querying period changes in capital brand transparency for a specific company, covering information disclosure timeliness, accuracy, truthfulness, media questions, and regulatory inquiries. It explicitly distinguishes from siblings by excluding institutional holdings and note what is not included, with concrete example queries.

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

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

Provides explicit exclusions (not for institutional holdings, not for batch screening by park/industry chain) and typical question formats. While it doesn't name alternative sibling tools, the clear when-not guidance helps the agent decide when to use this tool.

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

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

Annotations only include openWorldHint, so the description carries responsibility for behavioral disclosure. It discloses coverage through a detailed indicator list (ISO certifications, AEO, 等保, construction qualification years, etc.) and explicitly states exclusions. It also mentions 「周期变化」, indicating the tool tracks temporal changes. No contradiction with openWorldHint.

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: core purpose first, then coverage list, exclusions, and examples. Every section earns its place for a complex data domain. The list of indicators is somewhat repetitive (e.g., two similar construction qualification entries) but 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?

With 2 simple parameters, an output schema, and extensive documentation of covered indicators/exclusions/examples, the description is sufficient for an agent to decide when and how to invoke the tool. It lacks a brief note on output shape, but the presence of an output schema mitigates that need.

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% (both company_name and country_name have descriptions). The description adds example values («中国比亚迪股份有限公司», «美国Tesla, Inc.») and clarifies these are company-name/country-name pairs, but does not provide substantial additional parameter semantics beyond the schema.

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

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

The description states a specific verb and resource: 「按企业查询资质认证方面的周期变化」 (query changes in qualifications/certifications by company). It distinguishes itself from siblings by explicitly listing covered domains (高新专精特新, 体系/等保认证, 建筑资质等级) and excluding financial licenses and batch filtering.

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 (querying specific companies' certifications) and when-not-to-use exclusions («不用于按资质标签批量筛选企业名单，也不用于金融牌照查询», «不包含：非本分类指标；按园区/产业链批量筛企业名单»). It lacks explicit mentions of alternative sibling tools, but the exclusions and examples strongly imply the boundaries.

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

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

Annotations only include openWorldHint, so the description carries the behavioral disclosure burden. It describes the data scope (included/excluded indicators), the 'periodic change' (周期变化) nature, and adds pricing info. It implies a read-only query through '查询' but does not explicitly state no side effects; still, the context is quite informative beyond the sparse 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 with clear sections for purpose, included/excluded indicators, and examples. The pricing line is extra but compact. It is front-loaded with the core function and avoids excessive verbosity, though slightly dense with the appended pricing info.

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

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

For a simple query tool with only two parameters and an output schema present, the description covers purpose, scope, exclusions, and usage examples. It does not discuss pagination or authentication, but those are less critical given the read-only intent and existing output schema. The meaning of '周期变化' could be more precise, but overall it is complete enough for an agent to select 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 schema already provides descriptions and examples for both parameters (100% coverage). The description reinforces parameter usage through typical questions (e.g., '中国比亚迪股份有限公司' shows country/company split) but does not add new syntax, constraints, or details beyond what the schema offers. Thus baseline 3 is appropriate.

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

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

The description clearly states the tool queries periodic changes in enterprise charity responsibility, listing specific indicators (donation amount, public welfare investment, beneficiary population). It explicitly distinguishes itself by excluding non-category indicators and government subsidy/fiscal support queries, and provides typical question examples. The verb '查询' and the resource scope are unambiguous.

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

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

The description gives explicit exclusions ('不用于政府补贴或财政支持类查询', '不包含：非本分类指标；按园区/产业链批量筛企业名单') and typical question formats. However, it does not name specific alternative tools, so the agent is not explicitly told which sibling to use instead, but the exclusions provide sufficient guidance for most cases.

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

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

With only openWorldHint:true in annotations, the description carries the burden and delivers: it details the breadth of the open-world data (multiple status values 存续、吊销、注销、迁出, four levels of industry classification, three levels of geography). It sets appropriate expectations about the tool being a read-only, multi-dimensional profile lookup without claiming exhaustiveness of all enterprise 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 description is long but intentionally structured: overview → indicator list (bulleted for scannability) → exclusions → typical questions → pricing. Every section earns its place by constraining tool selection or invocation. Slightly verbose with the full indicator enumeration, but that content is load-bearing rather than filler.

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

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

Given the 2 simple parameters and an existing output schema, the description covers purpose, exclusions, examples, and pricing without redundancy. The explicit '不包含' list preempts common misuse for batch filtering or attribute labeling. For a read-style profile tool with output schema available, only minor additions like rate limits or data freshness could enhance it further.

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 parameters already have clear Chinese descriptions with examples (如「比亚迪股份有限公司」「Tesla, Inc.」). The description adds marginal value through the 典型问法 examples that implicitly demonstrate parameter format (company-name + country pairs), but per policy the baseline of 3 holds when the schema already does the heavy lifting.

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

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

The description uses a specific verb plus resource (基于具体企业名称，按企业查询基本信息) and clearly enumerates the query scope: 经营状态、行业分类、注册地资本、规模融资及集团概况. It distinguishes itself from its many enterprise_change_* siblings by listing the exact indicators covered (企业组织类型、主体类型、经营状态、多级行业分类、多级注册地、成立年限) and including three concrete example questions.

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?

Excellent when/when-not guidance: it explicitly states intended use (用于查询经营状态、行业分类...) and rules out alternatives with specific exclusions (不用于四上/上市/国资等机构属性标签判定；按园区/产业链批量筛企业名单). However, it stops short of naming a specific sibling tool as the recommended alternative, so it doesn't earn a 5.

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

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

Description conveys a query-oriented behavior and covers inclusion/exclusion scope, which helps define behavioral boundaries. The duration, since only 'openWorldHint' is annotated, other safety aspects (read-only/destructive) are not covered by annotations, but description implies read-only via '查询'; no contradictions but lacks fine-grained safety/behavioral 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?

Description is somewhat redundant (the '涉及指标/类型' list repeats the earlier list of '补贴处罚、渠道、新品、技术与定价'), but it is well-ordered and front-loaded with the core purpose. Exclusion section and examples are useful and do not feel wasted.

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

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

The description is complete enough for the tool's complexity and the large sibling set. It includes what it can query, what it explicitly cannot do, typical expected use, pricing is provided, and distinguishes from many sibling enterprise_change_* tools. Given that an output schema exists, return value description is not necessary.

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 description doesn't need to document every parameter, but it adds value by showing combined typical usage ('中国比亚迪股份有限公司... competitors...'), demonstrating how company_name and country_name are used together. It also reinforces that company_name must be a specific enterprise name.

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

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

Description uses specific verb '查询' and resource '企业市场竞争方面的周期变化', listing concrete metric types (补贴、处罚、渠道、新品、技术与定价). Explicitly differentiates from own-enterprise metrics and sibling tools like enterprise_change_product or enterprise_change_business_strategy.

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?

Clearly states when to use (query competitor moves by specific company), when not to use (own company metrics, batch enterprise lists by park/industry), and gives typical example queries. This provides both exclusions and positive examples for 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?

注解仅提供openWorldHint，无readOnlyHint或destructiveHint。描述仅称“查询”，未明确这是只读操作，也未说明返回格式或分页行为。由于注解稀少，描述承担更多责任，但整体透明度一般，给3分。

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

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

描述较长但结构清晰：先功能，再指标列表，再排除项，再典型问法。内容组织合理，无冗余信息，虽稍长但每部分都有价值。

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

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

有输出schema，无需描述返回结构。描述覆盖了功能、范围、示例，但未提及分页、限制或精确企业名称要求。整体完整度较高，但仍有提升空间。

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

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

schema覆盖100%，参数描述已给出名称示例，但描述未额外增加参数格式或约束信息。符合高覆盖率的基线3分，描述没有提升价值。

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于查询企业债务违约、负债概况、征信不良与账户冻结等风险变化，并区分了不包含的内容。虽然目的清晰，但与其他 enterprise_change_* 系列工具缺乏明确区分，未点名替代工具，因此扣1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?

描述了适用的场景（查询企业债务风险），并明确不用于替代完整征信报告、不与违规违法混用，还提供了典型问法。虽未明确说明何时使用其他工具，但足以指导基本选择。

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?

注释仅有openWorldHint，描述未提及任何行为细节（如权限要求、数据来源、更新频率等），也未说明返回格式或限制。描述没有与注释矛盾，但未提供额外行为信息，仅依赖注释，因此给予中等分数。

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

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

描述简洁，包含用途、涵盖范围、排除项和示例，结构清晰，句子精炼，每句话都有信息量。既不过长也不冗余。

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?

鉴于有输出schema和注释（openWorldHint），描述补充了排除项和典型用法，但没有提及返回数据的具体形式（如时间范围、变化方向等）。由于复杂度中等，且描述已提供核心信息，因此整体足够。但缺少对'周期变化'具体含义的解释，以及与其他政策类工具（如国际政策合规）的明确区分，稍有欠缺。

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已包含两个参数（company_name、country_name），且描述中明确提及按企业名称查询，并给出典型问法。但schema覆盖率为100%，描述未添加更多参数语义细节（如参数格式、必填性等），因此基线为3，描述略有补充但不够显著。

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：按企业查询政策合规方面的周期变化，具体涵盖行业、资金、人才、税收和监管新政策。并明确排除补贴查询和批量筛选，与兄弟工具（如policy_fiscal_support）形成区分。动词“查询”+资源“政策合规变化”清晰，目的明确。

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?

提供了典型问法示例，并明确排除非本分类指标和批量筛选场景，帮助用户判断何时不该用。但未显式说明与其他工具（如policy_fiscal_support）的替代选择，仅通过排除暗示，略有不足。

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

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

With only openWorldHint:true annotation, the description carries the burden of behavioral disclosure. It clearly indicates a read-oriented query tool, specifies exactly which metrics are included and excluded, and provides pricing (30 credits per run). It does not mention auth or rate limits, but for a data lookup tool this is acceptable additional 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 organized with clear sections for metrics, exclusions, and examples. The pricing line is slightly extraneous but provides useful cost context. Overall, it is efficient and well-structured for an agent to quickly parse.

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 the tool's scope, exclusions, and examples, which is sufficient for correct selection and invocation. Slight ambiguity around '周期变化' (periodic change) remains, but it does not hinder overall comprehension.

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

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

The schema already covers both parameters with descriptions and 100% coverage, so the baseline is 3. The description adds typical usage examples (e.g., '中国比亚迪股份有限公司员工人均工资') that illustrate valid parameter combinations, but this does not substantially enrich 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 that the tool queries cyclical changes in employer brand metrics for a specific enterprise, specifically employee average salary, benefits, and vacation days. It explicitly distinguishes itself from related tools by listing exclusions such as recruitment dynamics and labor contract metrics, making its purpose unambiguous.

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

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

The description provides clear when-to-use guidance with typical question examples and explicit exclusions (e.g., not for recruitment dynamics, labor contracts, or batch filtering by park/industry chain). It also states the required input style (enterprise name + country), which helps the agent select this tool over the many sibling enterprise_change_* tools.

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

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

Annotations only include openWorldHint, no readOnly/destructive hints. Description implies a read query ('按企业查询'), but does not explicitly state read-only behavior or any side effects. It adds some behavioral context (periodic changes, exclusion list) but lacks explicit safety characterization.

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 comprehensive but somewhat lengthy, mixing scope exclusions, metric list, examples, and pricing. Structured but could be more concise.

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

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

Given no output schema, description provides examples and metric list which aids expectation-setting. It lacks explicit return format info but is reasonably complete for a query tool.

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

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

Schema covers both parameters (100%). Description adds concrete examples and typical query formats, clarifying usage beyond the schema's brief 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 employer brand periodic changes for specific companies, listing exact metrics (training investment, time, promotion rate, turnover rate). It explicitly excludes what it's NOT for (recruitment, satisfaction/engagement evaluations) and provides concrete example queries, making the purpose unmistakable.

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 explicit exclusions ('不用于是否开展招聘', '不用于满意度敬业度等评价结果', '不包含非本分类指标', '不按园区/产业链批量筛选'), which clearly differentiate it from sibling tools like enterprise_change_employee_benefits and enterprise_change_employee_evaluation. The typical query examples also guide usage.

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

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

Annotations are minimal (only openWorldHint: true), but the description adds significant behavioral context: it clarifies the tool focuses on periodic changes in employer brand, excludes certain indicator categories, and includes pricing (30 credits per run) which is a cost disclosure. It does not describe return format or side effects, but for a read-only query tool this is acceptable given the schema and 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?

The description is well-structured: starts with a clear purpose sentence, followed by bullet points for included/excluded indicators, typical examples, and pricing. It is somewhat lengthy but every section contributes meaning. The pricing block is slightly technical but concise. Overall, content is properly front-loaded and efficient.

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

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

With a complete output schema and 100% parameter documentation, the description is comprehensive for its complexity. It clearly defines the tool's scope, exclusions, and usage patterns, and includes examples. No further context is needed for an agent to select and invoke the tool correctly.

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

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

Schema coverage is 100% with clear descriptions for both parameters. The description adds value by stating queries are based on specific enterprise names (not batch) and provides concrete examples (e.g., '中国比亚迪股份有限公司员工满意度') that clarify expected parameter values and how they combine. This goes beyond the schema's basic definitions.

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

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

Description explicitly states the tool queries periodic changes in employer brand metrics (satisfaction, engagement, loyalty) for a specific enterprise. It uses specific verb '按企业查询' (query by enterprise) and clearly distinguishes from development indicators like training/promotion, thus differentiating it from sibling tools such as employee_development.

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 explicit 'when to use' (employer brand periodic changes for satisfaction/engagement/loyalty) and 'when not to use' (not for training/promotion/resignation, not for non-category indicators, not for batch filtering by park/industry chain). Includes typical query examples that clarify expected input formats and reinforce usage context.

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

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

The description implies a read-only operation ('query') but does not explicitly state side-effects, auth requirements, or rate limits. It adds context about included metrics and exclusions, which enhances transparency beyond the sparse annotation (only openWorldHint). However, more behavioral details (e.g., whether it returns historical time series, data freshness) are missing.

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 concise: it starts with the core function, then lists included metrics, exclusions, and typical questions. Each sentence serves a purpose, and the information is front-loaded. No fluff or 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?

The description covers the tool's function, scope (included and excluded metrics), and provides clear examples. Since an output schema exists, return values are not required in the description. It is complete enough for an agent to understand when and how to use this tool effectively.

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

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

The schema already provides descriptions for both parameters with examples ('比亚迪股份有限公司', 'Tesla, Inc.', '中国', '美国'). The tool description does not add additional meaning beyond these examples, so it adds little value. Given schema coverage is 100%, the baseline score of 3 is appropriate.

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

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

The description clearly states the tool's purpose: to query periodic changes in employer brand metrics (education, age, gender, tenure) by company. It also provides explicit examples (BYD, Tesla, Toyota) and distinguishes from entrepreneur image and subjective evaluations, 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 gives clear usage context: it is for querying employee-related metrics, and explicitly excludes entrepreneur image and subjective satisfaction. It also states what is not included (non-categorized metrics, batch filtering by park/industry chain). While it does not reference specific sibling tools, the exclusions effectively guide when not to use it.

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

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

The description discloses that this is a query tool for periodic changes, implying read-only behavior, and mentions pricing. With only 'openWorldHint' annotation, the description adds value by clarifying the scope and what is excluded. However, it does not explicitly state that no data is modified, but the 'query' verb and context imply a safe read operation, which is consistent with 'openWorldHint.'

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

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

The description is structured with clear sections for purpose, included/excluded indicators, and typical queries, with examples. It is not overly long and each sentence contributes value. Minor redundancy in listing included indicators after already stating them, but overall concise and informative.

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

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

Given an output schema exists and the tool has a simple two-parameter query, the description provides sufficient context: purpose, included indicators, exclusions, and usage examples. It could be more explicit about return format, but the output schema handles that. The pricing info is an extra bonus. Overall, the description is complete for the tool's complexity.

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

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

Schema description coverage is 100%, as both parameters have descriptions with examples. The tool description adds typical question formats that illustrate how to use the parameters, but this is marginal beyond the schema. The parameter descriptions are clear but do not add semantics 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 queries employer-brand periodic changes for labor contract signing, overtime, occupational health, and work-related casualties by company, distinguishing it from benefit/wage indicators. It explicitly lists the included indicator types and explicitly excludes other categories and batch filtering, making the scope unambiguous and differentiating from sibling tools like 'enterprise_change_employee_benefits'.

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

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

The description provides explicit usage context by stating what the tool is NOT for benefits and provides typical examples and typical questions, while no explicit alternatives are named. It mentions '不用于人均工资福利等待遇指标' and '不包含：非本分类指标；按园区/产业链批量筛企业名单', which could serve as exclusions but does not point to specific alternative tools. This is adequate 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?

Annotations only include openWorldHint, so the description adds valuable behavioral context by specifying the exact data coverage (highest education, social positions, personal honors) and the exclusion of other categories. However, it does not disclose any side effects or read-only status beyond the word 'query'.

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

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

The description is organized with sections for usage, exclusions, examples, and pricing. It is mostly concise but includes some redundancy (e.g., '基于具体企业名称' and '按企业') and embeds pricing details, which slightly bloats the 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?

For a simple 2-parameter tool with an output schema, the description covers purpose, usage boundaries, parameter examples, and even pricing. It leaves no major gaps for an agent to determine when and how to 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?

Schema descriptions cover both parameters completely, but the description adds useful examples such as 'Tesla, Inc.' and '美国', clarifying accepted formats for company and country names. This goes 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 that this tool queries an entrepreneur's education, social positions, and personal honors based on a specific company name. It distinguishes itself from sibling tools by enumerating its exact metrics and explicitly excluding other categories like executive changes or negative sentiment.

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

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

The description provides explicit when-not-to-use guidance by stating it is not for executive resignation or negative sentiment queries, and further lists what is not included (e.g., non-category metrics, batch screening). It also gives typical question examples to illustrate 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?

There are no safety annotations (readOnlyHint/destructiveHint) provided, but the description explicitly uses the term '查询' (query) and describes retrieving periodic changes, implying a read-only operation. Pricing information is transparently disclosed. No contradictions with annotations exist. The description adequately conveys the tool's behavior without causing surprise.

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

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

The description is well-structured: it starts with the core purpose, lists included metrics, then exclusions, and finishes with typical examples. It is concise despite covering multiple aspects, and every sentence adds value. No redundant or vague phrasing 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 large number of sibling tools (enterprise_change_*), the description thoroughly clarifies the tool's scope: it enumerates the exact metrics included, explicitly states what is not covered, and provides examples. This prevents misuse and ensures the user knows exactly what to expect. No output schema is provided, but the description explains the nature of the result ('周期变化'), which suffices for context.

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

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

The schema covers both parameters with clear descriptions: company_name and country_name, each with example values (比亚迪, Tesla, etc.). The description reinforces these with typical questions, ensuring the meaning is fully understood. While schema coverage is 100%, the description adds contextual examples that clarify expected input formats, supporting a score above 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 purpose: to query periodic changes in environmental responsibility metrics for a specific enterprise. It specifies the exact metrics covered (green investment, carbon emissions, penalties, etc.) and provides concrete examples (比亚迪, Tesla, Toyota), making the tool's function unambiguous. The phrase '按企业查询责任品牌方面的周期变化' clearly differentiates it from other enterprise_change_* 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 explicit exclusions: it is not for certification queries (环保/ISO认证) and not for batch screening by park/industry chain. It also lists typical question formats, which helps users understand appropriate use cases. However, it does not directly compare with sibling tools like enterprise_change_environmental_certification or other related tools, so some ambiguity remains on when to choose this tool over a more specific one.

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

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

With only openWorldHint in annotations, the description carries the transparency burden and does well: it defines the exact indicators covered, states exclusions, clarifies that queries are company-specific, and even includes pricing. It does not contradict the annotation, though it could add more detail about output structure or data freshness.

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

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

The description is well-structured with purpose, exclusions, indicator lists, examples, and pricing. It is somewhat long but each section adds useful context; the pricing block is informative but could arguably be moved out of the description.

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

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

For a two-parameter query tool with an output schema and openWorldHint, the description is largely complete: it covers purpose, scope, exclusions, examples, and cost. It could be improved by explicitly naming sibling tools for alternative use cases, but overall it provides sufficient context for an agent to select 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?

Schema coverage is 100% and both parameters already have clear descriptions with examples. The description adds typical question patterns, but these largely restate the same country_name and company_name semantics rather than introducing new parameter meaning.

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

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

The description clearly states the tool's function: querying personnel-change periodic trends for a specific company, specifically covering core management changes, executive departures, and role transfers. It explicitly excludes negative executive sentiment/scandal queries, which distinguishes it from sibling tools like enterprise_change_executive_sentiment.

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

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

The description provides explicit when-not-to-use guidance, such as '不用于高管负面舆情或丑闻查询' and excludes batch screening by park/industry chain. It also gives typical question formats, but it does not name specific alternative sibling tools to use instead.

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 details the exact data categories covered (executive social anomalies, scandals, negative public opinion), states the query perspective (periodic change), and discloses pricing (30 credits per run). It does not describe pagination or no-result behavior, but the included detail substantially aids agent understanding.

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

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

The description is well-structured with clear sections: purpose, exclusions, covered indicators, exclusions, typical questions, and pricing. It is somewhat verbose due to repeated exclusion statements and detailed example queries, but each section adds valuable information for agent decision-making, so the length is justified.

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 complex context with dozens of similar sibling tools, this description is complete: it defines scope, exclusions, examples, and pricing, while the output schema covers expected return values. An agent can reliably select this tool among its many siblings.

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

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

Both parameters have 100% schema description coverage, so the schema already documents company_name and country_name sufficiently. The description adds example values and typical combined usage, but no additional constraints or format nuances beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly states the tool's function: querying executive sentiment (social anomalies, scandals, negative public opinion) by company name and country. It explicitly distinguishes from sibling tools by excluding executive appointment changes and general enterprise-level public opinion, and includes typical query examples that reinforce the specific verb+resource+scope.

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

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

Explicit usage boundaries are provided: it is not for executive appointment changes, not for general enterprise public opinion, and excludes non-category indicators and batch enterprise list filtering. This gives the agent clear when-to-use and when-not-to-use guidance, with implied alternatives among the many sibling enterprise_change 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 adds behavioral context beyond the openWorldHint annotation: it discloses the per-run cost of 50 credits (Pricing), clarifies that it returns only specific impact indicators rather than policy text, and provides typical examples of accepted input. It does not contradict annotations and gives useful operational 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 well-structured with clear sections: main function, indicator types, exclusions, typical questions, and pricing. It is somewhat lengthy but every part adds value, and the first sentence captures the core purpose. The organization aids skimming, though it could tighten some 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 that an output schema exists and the annotations include openWorldHint, the description provides sufficient context for an agent to select and invoke the tool: it explains scope, exclusions, and example queries. It does not discuss error handling or rate limits, but these are not critical for this query-type tool with a rich 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?

Although the schema already has 100% parameter description coverage, the description adds crucial semantics by resolving the relationship between country_name and company_name through examples (e.g., '中国比亚迪股份有限公司是否受到美国外贸政策事件的影响'), making clear that country_name is the enterprise's country and the policy region is an implicit dimension. This goes beyond the bare 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's function: querying periodic changes in a company's operational activities to assess impact from foreign trade policy events (US/EU/Japan/Korea/Asia/global). It distinguishes itself from sibling tools by explicitly listing the five impact indicator types and by stating what it does NOT cover (policy text, batch enterprise lists).

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

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

The description provides strong usage guidance: it explicitly states when NOT to use the tool ('不用于查询政策原文或解读政策本身') and what is excluded ('非本分类指标；按园区/产业链批量筛企业名单'). It also gives typical question formats that clarify how to frame queries, though it does not name alternative sibling tools explicitly.

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

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

注解仅包含openWorldHint，未声明readOnly或destructive。描述虽暗示为查询操作，但未明确说明副作用、数据范围或限制，透明度不足。

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

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

描述结构清晰，先简述功能，再列举指标，后列排除项和典型问法，但存在轻微冗余（如'经营活动方面的周期变化'与后文重复），整体简洁。

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?

没有输出schema，但工具为查询类，描述提供了足够上下文（用途、排除项），但缺少返回格式、错误处理、分页等交互细节，完整性一般。

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?

两个参数均有描述，且提供了具体示例（如比亚迪、特斯拉），但未说明格式约束（如国家名称的标准写法）、必填性已由schema指定，但缺乏边界条件或取值规则。

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

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

描述明确说明工具用途：基于企业名称查询财务指标的周期变化，涵盖营收、利润、资产负债等，且明确排除非上市企业和完整财务报表，目的清晰无歧义。

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?

描述给出了不适用场景（非上市企业、完整报表），但未说明何时应使用此工具而非兄弟工具（如enterprise_change_profitability等），也未提及前提条件或与其他工具的比较。

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 openWorldHint annotation, the description adds context by specifying the exact types of interactions queried (local and other-region government visits) and the exclusion of fiscal support. It does not elaborate on return format or pagination, but as a read-only query tool, the description provides sufficient behavior context beyond annotations.

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

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

The description is front-loaded with the core purpose, followed by exclusions and examples. It is well-organized and not overly verbose, though the pricing info is appended but not part of the semantic description. Overall, it earns its space.

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 (not provided here), the description need not explain returns. It covers the purpose, exclusions, and typical usage, making it complete for a query tool. It could mention pagination or limits, but the basic usage is fully specified.

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% for both params, but the description enriches them with typical usage examples (e.g., '中国比亚迪股份有限公司' with country '中国'), showing how company_name and country_name combine. This adds practical meaning 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 it queries government-enterprise relations changes for a specific company, focusing on receiving government inspections and visiting external government agencies. It also enumerates specific indicators and explicitly excludes fiscal support queries, distinguishing it from siblings like enterprise_change_policy_fiscal_support.

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

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

The description explicitly says it is NOT for fiscal support queries, excludes non-category indicators and bulk filtering by park/industry chain, and provides typical question formats. This gives clear when-to-use and when-not-to-use guidance relative to alternative tools.

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

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

The description clarifies the query scope and return categories, aiding transparency. However, it does not explicitly state whether the tool is read-only (no readOnlyHint is provided), though 'for querying' implies a read operation. The openWorldHint annotation is present, but the description does not elaborate on potential incompleteness or result structure. Still, the coverage of what it queries and what it omits provides good behavioral clarity.

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

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

The description is well-structured: purpose, included indicators, exclusions, and examples. Every sentence carries essential information for proper tool selection and invocation. Although it is longer than a typical one-liner, it is devoid of fluff and each line earns its place by clarifying scope or 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 the complexity of HR-related enterprise change categories and the large sibling toolset, this description is exceptionally complete. It differentiates this tool from 20+ similar HR tools and covers both what it does and what it doesn't. An output schema is present, so return-value explanation is unnecessary. The description fully compensates for any potential ambiguity in scope.

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

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

Both parameters are fully described in the input schema (100% coverage). The description adds value by stating the query is based on 'specific enterprise name' and directly ties the parameters to the typical questions (e.g., 'China BYD Co., Ltd.' for country_name and company_name). It reinforces parameter semantics but does not introduce new syntactic requirements, hence slightly above baseline.

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

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

The description explicitly states the tool's function: querying enterprise HR changes (new hires, remote recruitment, and specific role types). It lists the exact indicators covered and provides three typical query examples, making the purpose unmistakable. This goes beyond a simple verb+object phrase to fully scope the tool's 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?

The description clearly delineates what the tool is NOT for (compensation, benefits, resignation, promotion, employer brand indicators) and what it excludes (non-classified indicators, batch filtering by park/industry chain). It also provides typical usage patterns (enterprise + country) with real examples, giving the agent actionable guidance on when to invoke this tool over 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=true, so the description carries most transparency burden. It discloses scope and covered indicators, but does not explain open-world behavior, no-match handling, or output format expectations beyond what an output schema presumably provides. No contradiction with annotations.

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

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

The description is compact and well-structured, with a purpose statement, exclusions, indicator list, and examples. The pricing line adds some noise but does not severely hurt clarity.

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

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

Given the tool's complexity, two fully documented parameters, and an output schema, the description provides sufficient context: it defines the subject, scope, indicators, and sample queries. It could be more explicit about behavior when no data is found, but this is a minor 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 both parameters described and example values provided. The description reinforces usage through typical questions, but adds little additional semantic value beyond the schema.

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

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

The description clearly identifies the tool's purpose: querying industry-academia cooperation, R&D cooperation, and joint laboratories by specific company name. It distinguishes itself from sibling enterprise_change_* tools by listing exact indicator types and typical question formats.

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 queries and explicit exclusions ('不用于查询高校或科研机构自身信息', '不包含：非本分类指标；按园区/产业链批量筛企业名单'). It does not name alternative tools explicitly, but the boundaries are strong enough for an agent to decide 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?

Despite only openWorldHint being annotated, the description discloses meaningful behavioral limits: it does not provide patent full text, does not cover non-category indicators, and restricts results to specific patent/software-copyright metric types. It frames the operation as a query, making the read-only nature clear, and does not contradict the 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: purpose, exact supported indicators, exclusions, then example queries. It is somewhat dense and repeats exclusion messages, but each section 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?

With an output schema present, the description does not need to explain return values. It supplies the most important selection context: supported metrics, boundaries, and typical questions. The phrase 周期变化 versus current counts introduces slight ambiguity, but the listed metrics and examples resolve most practical questions.

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

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

The schema already describes both parameters at 100% coverage, but the description adds semantic constraints beyond that: it must be a specific enterprise name rather than a batch/list query, and the typical questions demonstrate valid combinations such as 美国 Tesla, Inc. and 日本丰田自动车株式会社.

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 resource: querying innovation output counts such as patents and software copyrights for a named enterprise. It distinguishes itself from other enterprise-change tools by explicitly excluding R&D investment, online sales share, non-category metrics, and batch/list filtering.

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 clearly states when to use the tool for querying patent and software-copyright innovation outputs and gives explicit negative conditions: not for R&D investment or online sales share, and not for batch screening by park/industry chain. It does not name alternative sibling tools, so it falls just short of a 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?

Annotations only provide openWorldHint, so the description carries most transparency burden. It discloses the query is enterprise-name-specific, lists covered indicators, states exclusions around batch screening, and even includes pricing. It does not describe data freshness, unsupported-name handling, or whether results are time-series, but it is still reasonably transparent for a read-oriented analytics query tool.

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

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

The description is well-structured with a purpose sentence, exclusion line, indicator list, exclusion list, and example questions. It is slightly wordy and repeats '不包含' and '不用于' ideas, but the bullet-like layout and front-loaded purpose make it easy to scan.

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

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

Given the two-parameter schema with 100% coverage and the presence of an output schema, the description covers what is needed: purpose, scope, exclusions, typical usage patterns, and pricing. It is sufficiently complete for an AI agent to decide when to invoke this tool among many enterprise_change_* siblings.

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

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

Input schema already covers 100% of both parameters with clear examples, so the description adds limited parameter-level value. It does reinforce the intended combination of country_name and company_name through typical questions, but it does not introduce new constraints or format details beyond the schema.

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

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

The description clearly states the tool's function: querying international cooperation R&D, multinational team distribution, and technology cooperation countries for a specific enterprise by name. It distinguishes itself from sibling tools by explicitly excluding import/export trade compliance, foreign-trade policy impact checks, and batch screening by park/industry chain, and provides concrete typical questions.

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 when-to-use ('用于查询国际合作研发、跨国团队分布及合作国家地区') and when-not-to-use ('不用于进出口贸易合规或外贸政策冲击排查', '不包含：非本分类指标；按园区/产业链批量筛企业名单'). It also provides three concrete example queries that clarify the expected question format and scope.

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

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

With only openWorldHint in annotations, the description carries most of the behavioral burden. It transparently discloses that the query is scoped to international metrics and excludes domestic metrics and batch filtering. However, it does not clarify the time-window/periodicity of the reported '周期变化', what happens for companies with no international data, or whether the output is raw counts versus aggregated scores. The output schema may cover return structure, but behavior around edge cases is not disclosed.

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

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

The description is efficiently organized with a main statement, a bullet-style indicator list, explicit exclusions, and example questions. Each section earns its place, and the front-loaded first sentence delivers the core purpose immediately. It is slightly long due to enumeration, but the structure enhances scannability.

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

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

For a 2-parameter tool with full schema coverage and an output schema, the description is largely complete: it defines scope, lists supported metrics, states exclusions, and gives natural-language examples. It could be slightly more complete by specifying the time-period/cycle semantics, but the overall context is sufficient for an agent to select and invoke the tool correctly.

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

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

Schema description coverage is 100%: both company_name and country_name already have clear examples in the input schema. The description reinforces parameter usage through typical questions (e.g., '中国比亚迪股份有限公司国际媒体报道数量'), but it does not add meaning beyond the schema, such as name-matching rules, required country-language correspondence, or format constraints. Baseline 3 is appropriate.

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

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

The description clearly states a specific verb+resource: query periodic reputation/brand changes by specific enterprise name, and enumerates concrete international metrics (media reports, research reports, social platform hotspots, credit ratings, awards, public-opinion health). It explicitly distinguishes itself from domestic-only reputation tools and batch enterprise screening, which separates it from many sibling enterprise_change_* 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 explicit when-to-use context (international reputation/brand indicators) and clear exclusions: not for domestic-only awareness/favorability, not for batch/industrial-chain screening. It also provides typical query phrasings. It does not name sibling alternatives explicitly, but the inclusion/exclusion guidance is strong enough for an agent to route correctly.

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:true, so the description carries the transparency burden. It provides substantial behavioral scope: which regional indicators are included, which are excluded, and example phrasings. It does not contradict annotations. Slight deduction for not addressing response size/pagination or auth needs, but strong coverage of scoping behavior 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?

Well-structured with clear labeled sections for purpose, indicators, exclusions, and examples; the example questions earn their keep. Slight redundancy as the three regional indicators are effectively restated three times across intro, indicators section, and examples, which could be trimmed.

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

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

For a two-parameter tool with an output schema present, the description covers purpose, scope, exclusions, and usage examples — a complete package. The main gap is the lack of explicit guidance on how this tool relates to sibling international_coop or external_policy tools, though the 'not for' carve-outs partially cover this. Overall adequate for the tool's modest complexity.

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

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

Schema coverage is 100%, so both parameters are already documented. The description adds modest value through concrete example values (比亚迪 BYD/East Asia, Tesla/Southeast Asia, Toyota/Europe) which hint at acceptable name formats and paired country-company examples. This is slightly above the baseline of 3 but does not reach 4 since the description adds format nuance rather than deep semantic detail.

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 ('查询政策合规方面的周期变化' per enterprise) and clearly delimits geographic scope (East/Southeast Asia, Europe). It explicitly carves out what it is NOT for (domestic compliance, foreign trade impact), which effectively distinguishes it from sibling enterprise_change_domestic_policy_compliance. Concrete example queries ground 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 when-to-use context (policy compliance changes in specified regions) and clear exclusions ('不用于国内政策合规，也不用于外贸政策对企业经营冲击判断', and '不包含' section). It stops short of naming sibling tools explicitly by tool name, though the domestic compliance alternative is strongly 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 full list of indicators (e.g., 是否参与了新的对外股权投资) and explicit non-inclusions (非本分类指标; 按园区/产业链批量筛企业名单) provide behavioral transparency beyond the minimal openWorldHint annotation. It clarifies what the tool does and does not return, effectively mapping its behavior. As a read-style query tool, no side effects are expected, and the description adequately covers its operational scope.

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

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

The description is well-structured with a clear opening purpose, a detailed indicator list, exclusions, and example questions. While longer than minimal, each section serves a purpose: the indicator list disambiguates the scope, and examples illustrate usage. It is front-loaded with the core purpose and remains readable despite its length.

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

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

Given the tool's complexity (many potential indicators, sibling tools, and an output schema), the description is highly complete. It covers the query scope, specific indicators, exclusions, and typical questions, while pricing and parameter requirements are available in metadata and schema. There is no significant missing context for selecting and invoking this tool correctly.

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

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

Both parameters are fully described in the input schema (100% coverage) with examples, so the description does not need to add much. The description's typical questions reinforce usage of company_name and country_name but do not introduce new semantics beyond the schema. Baseline of 3 is appropriate since schema already carries the parameter meaning.

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

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

The description clearly states the tool queries enterprise investment/financing activities (对外投资、新融资引入及与国企上市企业等投融资互动) using a specific company name. It explicitly lists the covered indicators and distinguishes from sibling tools by stating what it is NOT for (融资轮次/阶段等企业概况字段, 分支机构新设注销). This provides a specific verb, resource, and scope that differentiates it from other enterprise_change_* 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 clear usage context by specifying it is for querying investment/financing interactions and explicitly excluding non-related indicators and batch screening. It includes typical question examples (比亚迪, Tesla, Toyota) that demonstrate intended use. It does not name alternative sibling tools directly, but the exclusions effectively guide when not to use this tool.

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

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

描述详细披露了工具的行为范围，包括具体涉及的指标和不包含的类别，还给出了典型问法，透明度高。

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?

描述较长但结构清晰，分块列出用途、指标、不包含内容和典型问法，信息丰富，没有冗余。

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?

在复杂的企业风险查询场景下，描述充分覆盖了工具的核心功能、边界和常见用例，结合输入输出模式，完整性高。

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?

参数描述仅提供名称和示例，未深入解释每个参数的具体语义或格式要求，但示例有助于理解，基本满足需求。

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

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

描述明确说明了工具用途：基于企业名称查询企业风险方面的周期变化，具体列出涉及的指标类型，并区分不包含的内容，清晰定义了功能边界。

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?

明确说明了何时使用（查询法定代表人、控股股东等风险），并指出不适用于企业主体自身的违规排查，提供了典型问法示例，使用场景清晰。

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

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

With only the sparse openWorldHint annotation present, the description carries the full burden and delivers extensively. It enumerates seven concrete risk indicators (non-compete violations, unresolved labor arbitration, litigation losses, penalties in past two years, executive negative history, internal whistleblowing, pending civil/administrative cases), specifies timeframes (近两年), and status qualifiers (未解决/未结案). No contradiction with openWorldHint — it actually supports it by listing exhaustive categories without overclaiming result 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 front-loaded with the core purpose, then flows through exclusions, indicators, and examples in a logical order. The indicator list has some redundancy (labor disputes mentioned 3+ times: 劳动仲裁, 劳动纠纷或仲裁败诉, 未解决的劳动仲裁或集体诉讼), which adds verbosity without new information. However, for a tool with this many sub-dimensions and an enterprise-change family of 50+ siblings, the length is well-justified and each section earns its place.

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

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

For a high-complexity tool (7+ legal risk dimensions, international scope confirmed by CN/US/JP examples, 60+ siblings), the description is notably complete: it covers purpose, exact indicator types, exclusions, and usage examples. With an output schema present, the return format need not be described. The 70-credit pricing is provided for cost-aware decision-making. No critical gaps identified for tool selection and invocation.

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

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

Schema coverage is 100% with both parameters (company_name, country_name) documented with examples. Per the rubric, high coverage sets a baseline of 3. The description's '基于具体企业名称' and the typical question formats confirm the parameters and illustrate country+company usage, but add no new semantic dimensions — no formats, ranges, or relationships beyond what the schema already provides. The typical questions serve as loose few-shot examples, but the schema already uses near-identical example strings.

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?

Uses a specific verb+resource+scope ('按企业查询企业风险方面的周期变化' — query enterprise risk changes by company) and defines the domain precisely: labor arbitration, major litigation penalties, executive compliance, and unresolved litigation. It actively distinguishes itself from sibling categories by explicitly excluding 失信限高, 经营异常, 欠税 (which map to other risk tools), and provides concrete worked examples with real companies (BYD, Tesla, Toyota). Very specific and comprehensive.

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?

Explicit '不用于...' and '不包含...' sections state when NOT to use the tool, clearly delineating it from subject-violation profiling and batch-filtering tools. The typical question examples show the intended query format. However, it doesn't name specific sibling tools directly — it relies on implied mapping from the exclusions (e.g., 欠税 → credit/tax tools) rather than explicit alternatives. Strong context, no named fallbacks.

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

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

Annotations are minimal ({ openWorldHint: true }), leaving the description to carry the transparency burden. The description does disclose scope boundaries clearly (which metrics are in/out, no batch filtering by park/industrial chain) and signals the tool returns periodic trend data via '周期变化' and '诉讼' indicator definitions. However, it does not disclose data freshness, coverage limitations, ambiguity handling for company names, or expected failure/edge behaviors; the transparency is reasonable for a read-query tool but not exceptional.

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 with zero wasted words. Each section earns its place: scoping sentence, explicit inclusion list, explicit exclusion list, concrete examples, and pricing. The line-broken structure with headers (涉及指标, 不包含, 典型问法) aids rapid parsing for an agent, and the phrase '不用于...不包含...' front-loads the critical disambiguation from siblings.

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 high complexity (close ESG sibling competition, need to disambiguate legal/litigation scope, international naming variations), the description is thorough: indicators, exclusions, and multilingual examples are all covered. An output schema exists so return-value documentation isn't needed. It misses only minor operational details like rate limits or data update cadence, which would push this to a 5, but for a scoping-heavy metadata-enrichment tool, this is well above minimal viability.

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

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

Schema coverage is 100% with both parameters (company_name, country_name) already well-described in the input schema with examples. Per the baseline rule, the description doesn't need to add much—and indeed it doesn't elaborate on parameters directly. The typical-query examples do indirectly illustrate how country and company combine in practice, but since the schema already handles this well, the description adds minimal incremental parameter value.

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

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

The description uses a specific verb+resource structure (按企业查询...周期变化) and clearly scopes the tool to litigation-related metrics (诉讼数量、胜率、知产、个保、消保). It goes beyond vague purpose by listing exact included metrics, explicit exclusions (失信限高、经营异常), and three realistic query examples covering domestic and international companies. This firmly distinguishes it from the many sibling enterprise_change_* 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 strong guidance on domain fit: it specifies exactly when to use the tool (litigation queries) and explicitly states what it's NOT for (失信限高、经营异常、非本分类指标、按园区/产业链批量筛选). However, it never names alternative sibling tools directly (e.g., enterprise_change_violation_illegal), which would have made the when-not-to-use guidance fully actionable. The typical query patterns (典型问法) partially compensate for this gap.

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?

While the openWorldHint annotation only hints at open-ended result values, the description adds meaningful behavioral context by enumerating the full span of response content (presence flags for 6 license types, counts of financial institutions, investment institution counts, etc.). It makes the data-return behavior predictable for an LLM, though it could have disclosed response structure or potential empty-result behavior more explicitly.

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 typical but well-organized into clear functional sections: what it queries, included indicators (with lists), exclusions, and concrete example questions. The structure makes the dense domain vocabulary scannable. It could have been tightened, but every line earns its place by defining scope or clarifying deltas from siblings.

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

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

For a 2-parameter lookup tool with an output schema, this description is exceptionally complete: it defines the query scope (financial licenses only), lists the specific license categories and derived metrics, explicitly excludes adjacent use cases (ISO, batch filtering), and gives three realistic multilingual examples. There is little ambiguity left for an agent invoking this tool.

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

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

Schema coverage is 100%: company_name and country_name are both described with Chinese and English examples in the schema descriptions. The tool description adds value by showing multilingual company name examples (Chinese/English/Japanese) and how country_name appears in queries, but this is incremental rather than transformative beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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

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

The description states a specific verb+resource (query periodic changes in financial qualification licenses by company name) and clearly scopes the domain to financial licenses (banking, securities, insurance, trust, futures, leasing). It explicitly excludes non-financial certifications (high-tech, ISO) and provides concrete example queries, strongly distinguishing it from siblings like enterprise_change_certification and enterprise_change_violation_illegal.

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

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

The description explicitly states when to use this tool (querying financial/banking securities/insurance license information by company) and explicitly specifies what is NOT included (non-categorical indicators, batch filtering by park/industry chain). It includes typical question formats and clarifies this is for single-company lookups, which helps agents decide between this and the many sibling tools operating on the same enterprise_change_* family.

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?

注释包含openWorldHint，但描述没有详细披露行为细节，如是否返回周期变化的历史数据、是否涉及实时性等。描述提供了查询范围但未提及输出具体格式或限制。由于有openWorldHint，描述并未与之矛盾，但未增加太多关于行为特性的上下文。

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

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

描述结构清晰，先总述功能，再列出具体指标，然后说明不包含内容，最后给出典型问法。虽然稍长但每部分都有价值，没有冗余。分层列表和示例使信息易消化。

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?

考虑到工具复杂性（涉及多种企业属性），描述提供了详细指标列表和排除项，并给出示例问法，覆盖了用法。但未提及输出格式或返回数据的细节，不过有output_schema存在，可能已涵盖。总体完整。

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?

schema_description_coverage为100%，参数描述已明确company_name和country_name的格式和示例。描述中未额外解释参数，但典型问法提供了用法示例。由于schema已覆盖参数，描述无需额外补充，因此评分3。

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

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

描述明确说明该工具用于基于企业名称按企业查询基本信息中的周期变化，并列举了具体属性类型（四上小微、国资民资等），且与兄弟工具（如enterprise_change_company_profile）区分明显，因为描述了具体查询范围和不包含的内容。典型问法进一步明确了用途。

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?

描述明确说明了不用于经营状态、注册资本等字段，并明确哪些类型属于该工具（列举了具体指标），还指出不包含哪些情况（非本分类指标、按园区/产业链批量筛企业名单）。这提供了清晰的边界，指导何时使用本工具。

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 the responsibility for behavioral disclosure. It specifies the scope of indicators (included and excluded) and clarifies it's a per-enterprise query, not a batch operation. The '周期变化' (periodic changes) phrase reveals that results track changes over time. No contradictions 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 dense but well-structured, front-loading the main purpose in the first sentence, followed by exclusions, indicator lists, and examples. Pricing info is supplementary. While slightly long, every sentence contributes useful context for selecting and using 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?

With a full input schema and output schema present, the description covers selection criteria (specific fiscal support queries), exclusions, and examples. The openWorldHint annotation is given, and no gaps remain for an agent to misuse this 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%, so parameters are documented. The description adds value by giving three realistic example questions (BYD, Tesla, Toyota) that demonstrate acceptable company name and country formats, including bilingual usage. This goes beyond the schema's basic field descriptions.

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

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

The description clearly states the tool queries enterprise-specific government-enterprise relations focusing on R&D funding, subsidies, tax preferences, and special policy support. It explicitly excludes industry-level policy queries and government visit interactions, distinguishing it from siblings like enterprise_change_external_policy and enterprise_change_gov_visit_exchange.

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 when-to-use (specific enterprise fiscal support queries) and when-not-to-use (industry new policies, government visits, non-category indicators, batch screening). However, it does not name alternative sibling tools, so the exclusion guidance is implicit rather than direct.

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 minimal annotations (openWorldHint=true, no readOnly/destructive hints), the description carries the transparency burden. It clearly discloses this is a query operation on cooperation-brand periodic changes, enumerates the indicator categories included and excluded in detail, and clarifies scope limitations like '按园区/产业链批量筛企业名单' not being supported. No error states or rate limits are covered, but none are strictly required for a low-risk query tool.

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

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

Although longer than typical, the description is well-organized into scannable segments: definition, included indicators, exclusions, examples, and pricing. The examples in particular earn their place by disambiguating query patterns in a multi-lingual context. The only minor blemish is the appended 'Pricing' block which appears system-injected rather than intentionally authored.

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

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

For a 2-parameter query tool with an output schema and a taxonomically detailed description, the coverage is comprehensive: the agent knows what it queries, the full indicator list, the exclusions, and the query format. The only minor gap is handling of edge cases like company-country mismatches, but given the output schema covers return shape, this is sufficient for correct invocation.

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

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

Schema coverage is 100% with both parameters (country_name, company_name) documented with example values. The description enriches semantics by demonstrating composed queries ('日本丰田自动车株式会社供货合格率') that show how parameters combine, but it adds no constraints beyond the schema. This meets but does not exceed the baseline for fully-covered schema.

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

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

The description uses a specific verb-resource pairing (查询...合作品牌方面的周期变化) and defines exact scope via six indicator types (合同规范性, 履约及时性, 供货合格率, etc.). It clearly distinguishes itself from the 50+ enterprise_change_* siblings by explicitly listing exclusions ('不用于应付款、付款周期、违约率等合作结果指标'), which points toward the process-vs-result evaluation taxonomy.

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 explicit negative guidance: '不用于应付款、付款周期、违约率等合作结果指标' and '不包含：非本分类指标'. The typical-question formats ('中国比亚迪股份有限公司合同规范性') teach the agent how to phrase queries. However, it never names the natural alternative sibling `enterprise_change_result_evaluation`, requiring the agent to infer that from the exclusions.

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

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

Annotations only include openWorldHint, so the description carries most of the burden. It discloses that it covers periodic changes, lists many indicators, and explicitly states what it does not include, adding useful behavioral context beyond annotations.

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

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

The description is fairly long but each section (purpose, exclusions, indicators, examples) adds value. It is well-structured with clear separations, though the indicator list is extensive and could be condensed without losing meaning.

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 2 parameters and an output schema, the description is very complete. It clarifies scope, gives exclusions, lists covered indicators, and provides typical usage questions, making it fully actionable 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 description coverage is 100%, so the baseline is 3. The description adds typical examples and clarifies that company_name and country_name are used together, but does not provide deeper semantic details beyond what the schema already offers.

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 product-related business activities per enterprise, with a specific verb and resource. It explicitly distinguishes from siblings by stating it's not for searching by product name or replacing competitor dynamics queries, 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?

Provides explicit instructions on when not to use it (not for product-name market-wide search, not for competitor dynamics, not for batch screening) and includes typical question examples, offering clear context and exclusions for alternative tools.

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

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

openWorldHint=true 存在，描述中说明了查询范围（基于企业名称，按近一年时间周期），并列举了7种具体查询类型。但未说明返回格式、分页行为、数据更新时间等额外行为细节。描述与注解无矛盾。

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

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

描述整体结构化，先说明目的和限制，再列指标类型和典型问法。但包含了较多重复性列举（如中标公司、招标公司、参与投标的项目等三类场景），可适当精简。整体信息密度高。

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?

有输出schema，描述提供了查询范围、排除项和典型问法，对于按企业名称查询合作情况的工具来说信息充足。参数简单（2个必填），描述覆盖了主要使用场景。排除项（不查招标文件、不查全市场中标名单）是关键补完。

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 覆盖率为100%，两个参数（company_name, country_name）在schema中已有详细说明。描述中提到了'基于具体企业名称'与参数语义一致，但未添加超出schema的额外格式或示例。每参数有中文示例，但描述本身未重复或补充参数细节。

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的功能是基于企业名称查询经营活动方面的周期变化，并具体阐述了涉及的中标、发标、投标等场景。同时通过与『招标文件』和『全市场中标企业名单』的对比，清晰划分了工具边界，与同类工具（如enterprise_change_business_strategy）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?

明确说明了使用场景（查询企业经营活动中的项目合作情况），给出了不应使用的场景（查询招标文件本身或全市场中标企业名单），并列举了具体示例（中国比亚迪、美国Tesla、日本丰田）说明适用情况。

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

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

Annotations provide only openWorldHint, leaving the description to explain behavioral traits. The description clarifies scope and non-use cases but does not disclose output format, pagination, or potential side effects. It is not misleading and adds some transparency, but could go 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 a single well-structured paragraph in Chinese. It front-loads the purpose, then lists exclusions, then includes typical query examples—all in a concise, scannable format with no wasted words.

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

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

With an output schema present and full schema coverage for parameters, the description is near-complete. It explains the indicator categories, exclusions, and gives examples. It could mention that it returns periodic changes or specify behavior when no data exists, but overall it is sufficient.

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

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

Schema description coverage is 100% with clear parameter descriptions. The description adds value by providing concrete example formats for both company_name and country_name (e.g., '比亚迪股份有限公司', 'Tesla, Inc.', '中国', 'Japan', 'China'), which aids correct formatting.

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

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

The description clearly states the verb (query), resource (enterprise responsibility changes), and specific scope (tax payments, contributions, job creation). It also explicitly lists exclusions and provides concrete examples. This differentiates it from sibling tools like enterprise_change_legal_responsibility or enterprise_change_violation_illegal.

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 exclusions (not for tax arrears, not for batch filtering) and states the intended use (tax payment and job creation). However, it does not name specific alternative tools to use when exclusions apply, only implies they exist.

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 burden. It explains the query behavior and covered indicators, but does not disclose details like historical time range, data freshness, pagination, or rate limits. No contradiction with annotations exists, but behavioral richness is modest.

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 but logically organizes purpose, exclusions, included indicators, typical questions, and pricing. Each segment adds useful information; it could be visually structured with bullets, but nothing is redundant or wasted.

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

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

With an output schema present, the description need not detail return values. It covers what the tool does, what it includes/excludes, how to phrase queries, and pricing. It lacks explicit note on '周期变化' semantics (e.g., time windows), but for a 2-parameter tool this is sufficient.

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

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

Schema description coverage is 100%, so parameters are already documented. The description adds value by providing example values ('中国比亚迪股份有限公司', 'Tesla, Inc.') and typical question patterns, which clarify expected formats and language usage for both 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 states a specific action ('按企业查询声誉品牌方面的周期变化') and enumerates the exact indicators covered. It also explicitly differentiates from sibling tools by stating it is not for '获奖口碑或非负面占比等美誉度评价', which aligns with the sibling enterprise_change_reputation_favorability. This makes the tool's purpose unmistakable.

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 exclusions ('不用于获奖口碑或非负面占比等美誉度评价', '不包含：非本分类指标；按园区/产业链批量筛企业名单') and gives typical question formats. It does not name a specific sibling alternative, but the exclusions are enough to guide selection among the many enterprise_change_* 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?

没有注解说明副作用或只读性，但工具为查询类，描述未明确披露数据来源或潜在风险，仅凭功能推断为只读，透明度一般。

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

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

描述结构紧凑，包含用途、指标、排除项和示例，无冗余，信息密度高。

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?

缺少输出 schema，但描述中列举了具体指标类型，用户可推断输出内容，整体完整度良好但未达满分。

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

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

两个参数均有中文描述并给出示例，覆盖了全部参数，但描述简洁，未深究格式或约束，高于基础但非最佳。

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

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

描述明确说明工具用于按企业查询声誉品牌方面的周期变化，包括获奖数量和非负面口碑占比，并明确排除知名度指标，动词“查询”清晰，与其他工具区分明显。

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

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

描述指出了不用于媒体报道量等知名度指标，并给出了典型问法，隐含了适用场景，但未明确说明何时使用与不使用，略显间接。

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

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

Annotations are minimal (only openWorldHint: true), so the description carries the behavioral disclosure burden. It adds context about the scope of queries and what is excluded but does not mention side effects, permissions, or return characteristics beyond the scope. It implies a read-only query but does not explicitly state that, and no destructive or auth details are disclosed. Adequate but not rich.

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

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

The description is concise and well-structured, with clearly labeled sections for indicators, exclusions, and typical queries. It is front-loaded with the main purpose. The pricing information adds minor noise but is not excessive. Each sentence contributes value, and the structure aids comprehension.

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

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

Given the tool's simplicity (2 parameters, output schema present), the description covers the key aspects: specific purpose, indicators included/excluded, and usage examples. It does not delve into return format or edge cases, but the output schema exists. It differentiates from sibling tools through exclusions, making the context adequate for a specialized 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%, so the baseline is 3. The description adds typical query examples but does not introduce new semantic details beyond what the schema provides for the two parameters (company_name and country_name). The examples are illustrative but not essential for understanding parameter meaning, which is already clear from the schema.

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

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

Description clearly states the tool's purpose: querying periodic changes in cooperation brand aspects for specific companies, covering payables, payment cycles, contract breach rates, and cooperation years. It explicitly distinguishes from process indicators (delivery timeliness, supply qualification), differentiating from sibling tools. The specific verb '查询' and resource '合作品牌方面的周期变化' make it precise.

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 when-to-use context by listing specific indicators and gives typical query examples. It also states exclusions ('不用于' process indicators, batch filtering by park/industry chain), which helps avoid misuse. However, it does not name alternative tools explicitly, relying on exclusions and the extensive sibling list implicitly.

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, and the description does not elaborate on this or disclose other behavioral traits such as rate limits, authentication, or side effects. It is a read-only query (implied by '查询'), but this is not explicitly stated. The pricing info is business-related, not behavioral transparency. Minimal value added beyond annotations.

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

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

The description is structured with purpose, exclusions, included indicators, and typical queries, making it scannable. The introductory sentence about 'cooperative brand periodic changes' is redundant and potentially confusing, wasting a bit of space, but overall it is not verbose and front-loads important uses.

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

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

Given the tool has an output schema, description doesn't need to detail return values. It adequately covers what indicators are included and excluded, and provides examples. However, it fails to explain the 'periodic changes' concept mentioned in the first sentence, and the relationship between that and the listed indicators remains unclear. Also, openWorldHint is not contextualized.

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

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

Input schema covers both parameters fully (company_name and country_name) with descriptive examples. The description adds little beyond what the schema provides, only reinforcing with typical query formats. Since schema coverage is 100%, baseline is 3; no extra semantic enrichment is given.

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 industry status, certification qualifications, and credit rating for a specific company. It distinguishes itself from specialized certification tools by explicitly excluding certification year/brand details. However, the opening phrase about 'cooperative brand periodic changes' is confusing and seems unrelated to the stated indicators, mildly detracting from clarity.

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

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

The description provides explicit exclusions (e.g., not for certification year, not for batch screening by park/industry chain) and gives typical query examples (e.g., '中国比亚迪股份有限公司企业行业地位'). This implies when to use it: for specific company-based queries about these three indicator types. It does not name alternative tools, but the exclusions effectively 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 adds important context beyond annotations: it specifies the metrics included and excluded, and notes a per-run cost of 40 credits. However, it does not disclose response format or potential limitations (e.g., data availability by country). The openWorldHint annotation is present but not contradicted.

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

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

The description is concise and well-structured, with clear sections for purpose, exclusions, and examples. It front-loads the main purpose and includes only relevant details. The pricing info is useful but could be considered extra; still, it's not verbose.

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

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

Given the tool's complexity (querying brand metrics) and having an output schema, the description covers the essentials well: what it does, what it includes/excludes, and examples. It lacks some depth on behavioral specifics (e.g., data granularity), but for a query tool with good annotations and schema, this is adequate.

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

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

Schema description coverage is 100%, so the schema already documents both parameters. The description provides example values in typical queries (e.g., '比亚迪股份有限公司', '中国'), confirming usage but not adding new semantic details beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly states the tool queries brand-related periodic changes for a specific enterprise based on company name, covering market share, ad spend, ad reach, and brand awareness. It explicitly distinguishes from satisfaction/reputation tools by listing exclusions, which helps differentiate from the many 'enterprise_change_*' siblings.

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

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

The description explains when to use (for brand awareness metrics like market share, ad spend) and when not to (satisfaction, complaints, reputation). It also lists typical query phrasings, giving concrete examples of appropriate inputs. This is explicit and practical.

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 and no readOnly/destructive hints, the description carries the transparency burden. It discloses that the tool is a query about periodic changes ('周期变化'), specifies included indicators, and explicitly excludes certain categories. It also includes pricing context. It does not describe return details, but an output schema 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 efficiently structured: purpose statement, included metrics list, exclusions, typical queries, and pricing. Every sentence adds value and the front-loaded purpose makes it immediately clear what the tool does.

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

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

Given the tool's moderate complexity and the presence of an output schema, the description adequately covers purpose, usage boundaries, and examples. It could mention limitations or error scenarios, but the current content is sufficient for an agent to select and invoke the tool correctly.

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

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

The input schema already fully documents both parameters with examples (100% coverage). The description reinforces usage by showing typical query formats like '中国比亚迪股份有限公司客户总体满意度' but adds no substantive new parameter semantics beyond the schema.

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

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

The description clearly states the tool queries periodic changes in user brand satisfaction for a specific enterprise, listing concrete metrics (customer satisfaction, after-sales satisfaction, complaint rate, product safety accident rate). It explicitly excludes awareness metrics like market share and brand awareness, which distinguishes it from sibling tools like enterprise_change_user_brand_awareness.

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

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

The description explicitly states when not to use the tool (e.g., not for market share/brand awareness, not for batch filtering by park/industrial chain) and provides typical query examples. However, it does not name alternative sibling tools directly, only implied through the exclusion categories.

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 thoroughly discloses the tool's scope, including all included indicators and typical question formats. It does not mention side effects or data usage but as a data-query tool, it is implicitly read-only. The absence of an explicit readOnly annotation is slightly offset by the detailed inventory of what is 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-structured and appropriately detailed. It uses bullet-like lists for inclusions/exclusions and examples, which makes it easy to scan without unnecessary verbosity. Every sentence adds value by clarifying scope or giving usage 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?

The description is fully self-contained: it explains what the tool does, what it does not cover, gives concrete example queries, and the input schema is simple and well-documented. Without an output schema, the description still equips an agent to decide when and how to use the tool effectively.

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

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

The schema describes both parameters with examples (company_name and country_name). The tool description also provides typical question forms that implicitly illustrate how the parameters are combined. This adds contextual meaning beyond the bare schema, even though the schema coverage is complete.

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

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

The description clearly states that the tool queries enterprise risk-related periodic changes based on a company name and country, with a comprehensive list of specific risk indicators (e.g., dishonest被执行人, administrative penalties). It also explicitly excludes unrelated categories (individual risks, labor arbitration), making the purpose unambiguous.

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

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

The description provides clear guidance on what the tool is used for and explicitly lists exclusions (e.g., 'not for key natural person risk screening' or 'labor arbitration'), which helps an agent decide when not to use it. However, it does not explicitly reference alternative sibling tools or state a general rule like 'use this when you need enterprise risk change data,' but the specificity compensates.

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

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

The annotation 'openWorldHint' is present, and the description adds valuable behavioral context beyond that: it states that the tool returns 'possible matching records' with 'mapped company IDs for caller-side selection', clarifying that results are candidates and the caller must choose. The pricing info is also disclosed. No contradictions with annotations; the description enriches the understanding of the tool's behavior without conflicting.

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 highly concise, consisting of two sentences. The first sentence conveys the core purpose and output, and the second provides pricing as supplementary info. It is front-loaded with the main functionality, avoids fluff, and every word earns its place. The structure is clean and immediately informative.

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

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

For a tool with a single parameter and an output schema, the description is complete: it explains what the tool does, how input is structured (via the parameter), and what output to expect (matching records with IDs for selection). It does not need to detail return formats since an output schema exists. The pricing is also disclosed. The description covers all essential aspects for an agent to invoke it correctly.

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

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

The schema already provides a thorough description of the 'text' parameter, including examples ('Tesla United States', 'Samsung South Korea', 'Huawei China'), achieving 100% coverage. The tool description merely reiterates the optional country/region filtering, adding no new meaning beyond what the schema states. Therefore, a baseline score of 3 is appropriate as the schema carries the parameter documentation burden.

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: searching company candidates by name, optionally filtered by country/region, and returning matches with mapped IDs for caller-side selection. It uses a specific verb ('search') and resource ('company candidates'), and the mention of returning IDs for selection distinguishes it from a generic search. Among siblings, there is a 'search_region_candidates' tool, and this description makes clear it is company-centric, avoiding confusion.

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

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

The description provides clear context on when to use the tool: when you need to find company candidates by name, optionally with region/country. It explains that matches are returned for caller-side selection, implying a follow-up step. However, it does not explicitly mention alternatives like 'search_region_candidates' or state when not to use this tool, so it lacks explicit exclusion criteria, but the context is unambiguous.

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

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

The description adds some value beyond the 'openWorldHint' annotation by explaining the internal registry lookup and standardized list output. It does not disclose behavior for ambiguous input, no-match cases, or list ordering/ranking, leaving some behavioral uncertainty.

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

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

The core description is two well-structured sentences that front-load the main behavior. However, embedding a raw `Pricing` object in the description adds non-selection-relevant noise, preventing a perfect score for conciseness.

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

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

For a simple single-parameter lookup tool with a rich schema and an output schema present, the description provides enough context to understand the purpose and general output shape. It is slightly incomplete regarding edge cases such as no matches or ambiguous results, but the overall tool complexity is low.

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

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

The single 'text' parameter is already fully described in the input schema with examples like 'China', 'USA', and '中国'. The description mostly restates that same concept, so it adds little semantic value beyond the schema; the high schema coverage justifies 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 uses a specific verb and resource: it 'Resolves natural-language country or region names ... against SupplyGraph’s internal geography registry' and returns 'standardized region names.' This clearly differentiates it from sibling tools like 'search_company_candidates' by focusing on geography rather than companies.

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 intended use case is implied clearly: use when you need to map natural-language country/region input to standardized internal names. However, it does not explicitly state when not to use it, nor does it mention alternative tools like 'search_company_candidates', so there is no direct guidance for choosing 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?

With only openWorldHint:true in annotations, the description carries the behavioral burden. The verb 'analyzes' implies a read-only, non-destructive operation and the cost disclosure (264,590 credits/run) adds decision-relevant context. However, it doesn't clarify side effects, latencies, rate limits, or what the analysis output contains (mitigated by output schema existence). It adds some value but doesn't go beyond the basics.

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 substantive description is a tight, front-loaded two-sentence summary that immediately says what the tool does. The 'Pricing: {'unit': 'credits', 'per_run': 264590}' line is concise and carries meaningful cost context for an agent, though it's machine-formatted. Overall minimal waste, though it could be argued the raw dict dump is slightly noisy.

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

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

Given the tool has an output schema, documented parameters, and a fairly self-contained analysis scope, the description is largely sufficient. It could be improved by clarifying how it differs from sg_visualization (which also sounds like it could handle analysis/reporting) and supply_chain_risk_prediction, but the description is mostly complete for an analysis agent.

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

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

The description provides no parameter info, but schema description coverage is 100% with rich, self-contained parameter descriptions (e.g., pid references search_company_candidates with a Tesla example, region_name references search_region_candidates with country examples). Per rubric baseline rules, this is a solid 3 — the schema does the heavy lifting, and the description adds nothing further.

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 — 'Analyzes multi-tier supply chains to detect single-country concentration and quantify geographic dependency across regions.' This clearly distinguishes it from the sibling tools (which are mostly enterprise_change_* and report/tariff tools), making the agent understand precisely what this agent does versus search_company_candidates or tariff_calc.

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 explicit — the description conveys the tool's domain via the problem it solves (supply-chain geographic concentration), but never states 'use this when' or names alternatives for scenarios this tool is not suited for. Given the long sibling list, there is no explicit disambiguation like the calendar example in the rubric.

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 likely indicates external data access), but the description does not disclose other behavioral traits such as read-only nature, performance considerations, or side effects. The pricing info is a cost factor but not a behavioral disclosure. No contradiction exists, but the description adds minimal transparency beyond annotations.

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

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

The description is a single sentence plus pricing, front-loaded with the core purpose. Every word earns its place; there is no fluff or redundant elaboration.

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 complex tool generating multi-tier graphs, the description is adequate but minimal. It does not explain output interpretation, limitations, or prerequisites beyond the parameter schema. The presence of an output schema reduces the need to detail return values, but the description could still mention that the graph visualizes dependencies and that the operation is heavy (given the high credit cost). Overall, it is not fully complete for proactive agent use.

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

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

The input schema already fully documents the pid parameter (100% coverage), including its origin (search_company_candidates) and an example. The description adds no additional meaning about the parameter, so the baseline of 3 applies as the schema bears the full burden.

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 generates global multi-tier supply-chain graphs, with a specific verb (generates), resource (supply-chain graphs), and scope (global multi-tier). This distinguishes it from sibling tools like enterprise_change_* which focus on updates/reports, and sg_chokepoint or tariff tools which address specific risk/tariff aspects.

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

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

The description implies usage for visualizing enterprise and product dependencies but does not explicitly state when to use it versus alternatives like sg_chokepoint or supply_chain_risk_prediction. It provides no exclusion criteria or contextual cues beyond the high-level purpose.

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 offers minimal behavioral detail beyond the annotation openWorldHint: true. It does not disclose any side effects, data requirements, or limitations. The mention of pricing (264590 credits) is the only extra but does not explain behavior. Since the annotation is sparse, the description carries the burden, and it fails to illuminate how the tool behaves (e.g., what happens with invalid inputs, whether it is stateless). No contradiction with annotations, but insufficient transparency.

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

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

The description is brief and front-loaded, with the core purpose in the first sentence. The second sentence includes pricing, which is not part of the tool's functional description but is still concise. No fluff, but the 'Continuously' phrasing is slightly misleading. Overall, it is compact and easy to scan.

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

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

Given the tool's complexity (nested event_info object, multiple event types, output schema present) and the sparse annotations (only openWorldHint), the description is inadequate. It does not explain how to construct a valid request or what the output looks like, even though the output schema exists. It also lacks guidance on event types or modes. The schema covers parameters, but the description fails to provide high-level context such as the tool's workflow, any rate limits, or typical use cases. This is a gap for an AI agent to use it effectively.

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

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

Schema description coverage is 100%, with each parameter (company_id, event_type, analysis_mode, etc.) having detailed descriptions in the input schema. The tool description adds no additional parameter-level semantics beyond what the schema already provides. It only says 'Continuously monitors...', which does not explain any parameters. Thus, it meets the baseline of 3 for a fully documented schema, but adds no extra value.

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

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

The description clearly states the tool's function: 'monitors global supply chain risk events and evaluates whether, how, and to what extent those events may affect a target company.' This gives a specific action and resource. It distinguishes from sibling tools like enterprise_change_* which focus on company changes, and search tools which are for lookups. However, the word 'Continuously' is misleading for a one-shot prediction tool, so not a perfect 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?

There is no guidance on when to use this tool versus alternatives. The description does not mention any prerequisites, exclusions, or scenarios where another tool would be more appropriate. It only states what it does, leaving the agent to infer usage from the name and schema. No explicit 'use this when' or 'avoid if' is 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 context beyond the sparse annotations by explaining the calculation method and claiming rule-based, transparent outcomes. However, it does not disclose limitations, data source assumptions, or whether any input validation or unpredictable behavior may occur, so transparency is only partial.

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

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

The core description is a single, dense sentence containing the essential mechanism and outcome. The second clause is somewhat promotional, and the pricing line is extra metadata, but overall the description is compact 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?

Given the simple two-parameter schema, an output schema, and a clear calculation purpose, the description is mostly adequate. However, it misses guidance on how this relates to tariff_classification and does not mention any caveats or assumptions, leaving some contextual gaps.

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

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

The schema already provides complete descriptions for both parameters (country_or_region and product_description), so the baseline is 3. The description adds general context about HTS and Chapter 99, but it does not clarify parameter formats, interpretation, or relationships beyond what the schema already states.

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 ('Calculates U.S. customs duties') and a concrete scope ('HTS base rates' with 'Chapter 99 measures'). It conveys the tool's function clearly, though it does not explicitly distinguish itself from the sibling tariff_classification tool.

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

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

No explicit guidance is provided about when to use this tool versus alternatives such as tariff_classification. The context implies its use for duty calculation, but no when-to-use, prerequisites, or exclusion criteria are given.

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