Server Quality Checklist

Tool Scores

• list_regionsB
  3.1/5.0
  Behavior2/5

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

  No annotations are provided, and the description only restates the tool's purpose without disclosing behavioral details such as ordering, scope granularity, data source, or whether results are limited to major regions. Since listing is implied to be read-only, some safety is inferable, but the description itself adds little beyond the name.

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

  Conciseness4/5

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

  The description is a single short sentence with no filler, which is appropriately concise. However, '萌芽体系' is semantically murky and could be clearer or rephrased to communicate the intended scope without ambiguity.

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

  Completeness3/5

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

  For a zero-parameter listing tool, this level of description is close to adequate, but there is no output schema and no clarification of what the returned regions look like or what '萌芽体系' means. An agent can probably invoke it correctly, but it may not know exactly what to expect from the response.

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

  Parameters4/5

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

  The tool has zero parameters and the schema is empty with 100% coverage, so there are no parameter meanings for the description to clarify. The baseline of 4 for zero-parameter tools applies because the schema already exhaustively documents the input surface.

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

  Purpose4/5

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

  The description uses a clear listing verb ('列出') and names a specific resource: China's major whisky-producing regions in an emerging system. It implicitly distinguishes itself from sibling list_distilleries by focusing on regions rather than individual distilleries, though the phrase '萌芽体系' is somewhat awkward and could confuse an agent about exactly what set of items is returned.

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

  Usage Guidelines2/5

  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 siblings such as list_distilleries or get_distillery. The agent must infer selection from the name alone, with no explicit context about when region-level listing is appropriate or when a more specific tool should be chosen.

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

• list_distilleriesA
  3.6/5.0
  Behavior3/5

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

  There are no annotations, so the description carries the safety/behavior burden. '列出...可按产区过滤' accurately conveys a read-style filtering operation, but it doesn't disclose pagination, result shape, or how absent filters behave. These are moderate omissions for a simple list tool.

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

  Conciseness5/5

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

  One compact sentence that front-loads the purpose and appends the filter condition. Every word earns its place; no redundant filler.

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

  Completeness4/5

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

  For a single-optional-parameter list tool with full schema coverage, the description is nearly complete: it states the resource, scope (domestic), and filter mechanism. A brief pointer to list_regions for codes would improve it, but nothing critical is missing for a correct call.

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

  Parameters3/5

  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 region as an industrial-zone code with an example (qionglai). The description mostly repeats this rather than adding new parameter semantics, so the baseline 3 applies.

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

  Purpose4/5

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

  The description names a specific verb ('列出') and resource ('国产威士忌酒厂'), and notes the optional region filter. It is distinct from siblings like get_distillery, though it doesn't explicitly contrast itself with them.

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

  Usage Guidelines3/5

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

  It implies the primary use: list all distilleries, optionally filtered by an industrial-region code. It offers no explicit when-to-use/when-not-to-use guidance and never points to list_regions for obtaining valid codes, though that is inferable.

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

• get_distilleryA
  3.7/5.0
  Behavior3/5

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

  There are no annotations, so the description carries the full burden. It does convey that the tool returns a comprehensive profile with several named content areas, which is useful. It does not disclose output formatting, permissions, or data caveats, but for a simple lookup tool the described behavior is broadly clear.

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

  Conciseness5/5

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

  One compact sentence with the resource and the key content categories front-loaded. Everything earns its place; no redundant filler.

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

  Completeness3/5

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

  The tool has a single documented parameter and no annotations. The description tells the agent what kind of data to expect, but because there is no output schema it leaves the exact return structure unspecified, and it does not point to siblings for routing. This is adequate but not fully complete.

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

  Parameters3/5

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

  Schema coverage is 100%: the single 'id' parameter is already documented with a clear description and examples ('daqin / laizhou'). The tool description adds no extra parameter-level semantics, so the baseline of 3 applies.

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

  Purpose5/5

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

  The description uses a specific verb ('查' / query) and a specific resource ('某家国产威士忌酒厂的完整档案' — a single domestic whisky distillery's complete profile), and enumerates what the profile contains (region, process, terroir, products, credibility). This clearly distinguishes it from siblings like list_distilleries (all distilleries) and get_flavor_profile (one dimension).

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

  Usage Guidelines3/5

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

  The intended use is implied: when an agent needs the complete archive for one distillery rather than a list or a single flavor profile. However, the description gives no explicit guidance on when to prefer sibling tools or exclude alternatives, leaving some routing inference to the agent.

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

• get_flavor_profileA
  3.7/5.0
  Behavior3/5

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

  No annotations are present, so the description carries the behavioral burden. It clearly indicates a read/query operation and usefully discloses that data not yet collected is honestly labeled. It does not mention response formatting, error cases, or access requirements, so coverage is helpful but partial.

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

  Conciseness4/5

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

  The description is a single front-loaded sentence: the target resource comes first, followed by the content details and the honest-labeling behavior. It is compact, though the phrase '含待采集诚实标注' is slightly awkward and could be clearer.

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

  Completeness4/5

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

  For a one-required-parameter read tool with no output schema, the description covers the main return aspects: dominant flavor words, official/community sources, and incomplete-data labeling. It would be stronger with an example of the expected output structure, but the essential information needed to invoke it correctly is present.

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

  Parameters3/5

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

  Schema coverage is 100% since the only parameter, distilleryId, has a description ('酒厂 id'). The tool description merely reinforces that the profile belongs to a specific distillery but adds no additional parameter details beyond what the schema already provides.

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

  Purpose5/5

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

  The description names a specific verb ('查', query) and a clear resource (a distillery's flavor profile), then details what is included: dominant flavor words, official/community sources, and honest labeling of uncollected data. This distinguishes it from siblings like get_distillery and search_whisky.

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

  Usage Guidelines3/5

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

  Usage is implied: this tool is for querying a distillery's flavor profile rather than listing distilleries, products, or recommendations. However, it does not explicitly mention alternatives or state when not to use this tool, so no direct exclusionary guidance is provided.

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

• list_productsA
  3.7/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the behavioral burden. It conveys that the tool returns product line and price-band information, and the verb '查' implies a read-only query. Yet it doesn't disclose details like response format, ordering, pagination, or whether all products are included.

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

  Conciseness5/5

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

  The description is one short, front-loaded sentence with no filler. Every word contributes to conveying the tool's core purpose.

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

  Completeness3/5

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

  For a one-parameter list tool, the description is adequate: it identifies the input and the nature of the output. However, it doesn't explain how the distilleryId should be obtained (e.g., via list_distilleries) or precisely what 'price band' means, and there is no output schema to fill that gap.

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

  Parameters3/5

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

  The schema fully documents the single parameter distilleryId as '酒厂 id', and the description references '某家酒厂' but adds no new meaning beyond that. With 100% schema coverage, the baseline of 3 applies.

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

  Purpose5/5

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

  The description '查某家酒厂的产品线与价格带' states a specific action (query) and resource (a distillery's product line and price band). It clearly distinguishes from siblings like list_distilleries (which lists all distilleries) and get_distillery (which returns distillery details).

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

  Usage Guidelines3/5

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

  The description implies the use case: call it when you need the product lineup and prices for a specific distillery. However, it provides no explicit guidance on when not to use it or how to choose between this and siblings like search_whisky or get_distillery.

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

• search_whiskyA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description carries the full behavioral burden. It usefully discloses which fields the search matches, but it does not say what the tool returns (e.g., a list of whiskies) or how results are ordered or limited, leaving important behavioral context unstated.

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

  Conciseness5/5

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

  The description is a single compact sentence that leads with the action and then immediately specifies the searchable dimensions. Every word earns its place, with no repetition or filler.

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

  Completeness3/5

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

  In the absence of an output schema or annotations, the description should explain what a successful invocation returns and how the query is interpreted (free text, exact match, etc.). It covers the searchable fields but not the output shape or usage nuances, leaving an agent to guess at the result format.

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

  Parameters4/5

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

  The schema already covers the single query parameter at 100%, and the description adds real semantic value by explaining that the query can match distillery names, regions, styles, dominant flavors, and stories. This helps an agent formulate meaningful search terms beyond the bare '检索词'.

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

  Purpose5/5

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

  The description clearly states a specific verb ('检索') and resource ('国威知识库'), and the parenthetical enumerates the matching fields (distillery name, region, style, flavor, story), making it distinct from the more targeted list/get siblings.

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

  Usage Guidelines2/5

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

  No guidance is given on when to use this tool versus alternatives such as list_distilleries, get_distillery, or get_flavor_profile. The description implies a free-text search but does not state that it is the right choice when a user query spans multiple fields, nor when it should not be used.

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

• recommend_whiskyA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description carries the behavioral disclosure burden. It adds a useful behavioral trait: results include credibility and honest declarations ('含可信度与诚实声明'). It does not describe side effects, limitations, or how the knowledge base is consulted, but the tool is clearly a read-only recommender by nature.

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

  Conciseness5/5

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

  One compact, front-loaded sentence that conveys purpose, criteria, source, and output traits without wasted words.

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

  Completeness4/5

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

  For a 3-optional-parameter recommender with no output schema, the description covers the essential information: what it does, the accepted criteria, the knowledge base, and the nature of the output. It omits details like default behavior with no parameters or exact output structure, but these are not critical for correct invocation.

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

  Parameters3/5

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

  Schema description coverage is 100%, so all three parameters are already documented with examples. The description only restates the parameters as selection criteria ('预算+口味+场景') and adds no syntax, constraints, or behavioral detail beyond the schema.

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

  Purpose4/5

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

  The description clearly states a specific action ('推荐酒款'), a resource ('国威知识库'), and the selection criteria ('预算+口味+场景'). It reads as a recommendation tool distinct from the sibling list/search tools, though it does not explicitly name them.

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

  Usage Guidelines4/5

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

  The phrase '按预算+口味+场景' provides clear usage context: the tool is for recommendation based on these three inputs. However, it does not explicitly state when to prefer this over search_whisky or list_products, so no exclusions or alternatives are given.

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

• submit_tasting_noteA
  3.9/5.0
  Behavior3/5

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

  There are no annotations, so the description carries the full burden. It discloses a meaningful behavioral constraint — the data is a non-authoritative funnel ('AI 不据此给任何权威结论') — but does not describe write side effects, idempotency, error handling, or whether a confirmation is returned. Some useful context is added, but not a complete behavioral picture for a mutation tool.

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

  Conciseness5/5

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

  Two short sentences with no filler. The main purpose is front-loaded, and the second sentence adds a meaningful caveat about data provenance. Every phrase earns its place.

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

  Completeness3/5

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

  For an 8-parameter tool with no annotations and no output schema, the description only partially compensates. The schema handles parameter definitions, and the source restriction is useful, but the agent still gets no guidance on required fields (distilleryId), expected return behavior, or any consequences of submitting. It is minimally sufficient for a straightforward submit action but leaves gaps.

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

  Parameters3/5

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

  Schema description coverage is 100%, with every parameter (nose, score, finish, palate, source, taster, product, distilleryId) already labeled. The description adds no parameter-level meaning beyond the schema, so it sits at the baseline 3.

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

  Purpose5/5

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

  States a specific verb and resource: '提交一条品鉴笔记' (submit a tasting note), and adds the '数据漏斗' (data funnel) framing, which clearly sets it apart from the read/list/recommend siblings. The submit action is unique among the sibling tools, so an agent can distinguish it without opening the schema.

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

  Usage Guidelines4/5

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

  Clearly establishes when to use the tool — when there is a tasting note to submit — and adds an explicit source restriction ('仅采信真人来源' – only human sources are accepted). It does not name alternatives such as get_flavor_profile, but the submit-vs-read distinction already provides strong contextual guidance.

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

• generate_contentA
  4/5.0
  Behavior4/5

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

  No annotations are present, so the description carries the full burden. It discloses that output is based on real data from the knowledge base, that it produces a content skeleton rather than final polished content, and that items needing verification are marked. These are meaningful behavioral signals beyond the tool name.

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

  Conciseness5/5

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

  A single dense sentence front-loads the purpose, lists all supported output formats, and adds the important caveat that uncertain items are flagged. There is no filler or redundant repetition of schema information.

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

  Completeness4/5

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

  The tool has moderate complexity with three parameters and no output schema. The description explains what kind of output to expect, the four possible formats, and the verification-marking behavior. It does not describe the exact returned structure, but combined with the complete schema, an agent likely has enough to invoke the tool successfully.

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

  Parameters3/5

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

  Schema coverage is 100%, with each parameter already described and an enum provided for format. The description does not add new parameter-level meaning beyond restating the available formats, so the baseline score of 3 is appropriate.

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

  Purpose5/5

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

  The description clearly states a specific action—generating content from the 国威 knowledge base—and specifies the exact output types: 选题/长文/小红书/短视频口播. It is easily distinguishable from sibling tools like search_whisky and list_distilleries, which are retrieval-oriented rather than content-generation-oriented.

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

  Usage Guidelines3/5

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

  The description implies it is for producing content formats backed by real knowledge-base data, but it does not explicitly state when to use it over alternatives or when not to use it. No sibling tools are named, so the agent must infer the usage context.

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