Server Quality Checklist

Tool Scores

• amap_distanceB
  3.4/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It claims to compute 'driving distance and time' but the schema shows multiple travel modes (type 0-3), a direct contradiction. It also omits important behaviors such as coordinate format, maximum of 10 origins, and distance limits for walking/cycling. The description misrepresents the tool's full capabilities.

  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 concise and front-loaded, consisting of two short sentences: '距离测量。计算多个起点到一个终点的驾车距离和时间。' There is no unnecessary wording, making it easy to scan.

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

  Completeness2/5

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

  The tool is simple but the description is incomplete. It fails to mention the 'type' parameter's multiple modes, which is a key feature. It also does not describe output structure or limitations beyond what the schema states. Given no output schema and no annotations, the description should compensate more; it only covers the driving scenario, leaving the broader functionality undocumented.

  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 baseline is 3. The description adds minimal parameter context by mentioning 'multiple origins to one destination' but does not elaborate on the 'type' parameter or coordinate syntax. It provides no additional value 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 the tool measures distance and time from multiple origins to one destination, with the purpose of comparing accessibility of different starting points. It distinguishes itself from sibling direction tools by focusing on multi-origin comparison. However, the qualifier 'driving' is overly specific and misleading because the schema's 'type' parameter supports walking, cycling, and straight-line distance as well.

  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 description gives a clear usage context: '用于比较不同出发点的可达性' (used to compare accessibility of different starting points). This implies when to use the tool, but it does not explicitly mention alternatives or conditions when not to use it. The guidance is clear but not exhaustive.

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

• amap_poi_searchB
  3.4/5.0
  Behavior2/5

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

  No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only mentions '支持城市范围过滤' (supports city range filtering), which largely repeats the citylimit parameter in the schema. It does not disclose what the response contains, pagination behavior, whether results are ordered, or any side effects. For a search tool, this is a significant gap in transparency.

  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 extremely concise, consisting of a single sentence with three clauses. It is front-loaded with 'POI（兴趣点）搜索' which immediately telegraphs the purpose. Every phrase earns its place: purpose, search modes, examples, and a filtering capability. No redundant fluff.

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

  Completeness2/5

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

  With no output schema and no annotations, the description should explain what the tool returns and how it behaves. It does not mention the return format (e.g., a list of POIs with names, addresses, coordinates), nor does it elaborate on pagination or the interplay between keywords and types. The tool has 6 parameters and moderate complexity, but the description stops at a high-level overview, leaving important operational details undocumented.

  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 baseline is 3. The description adds some context by clarifying that search can be done by keyword or type and by providing examples of place categories. However, these examples do not add significant meaning beyond the existing parameter descriptions, which already include similar examples like '「050000」（餐饮）'. The description does not clarify optionality or combination semantics beyond the schema.

  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 begins with 'POI（兴趣点）搜索' which clearly states the tool is for searching points of interest. It specifies the modes: '按关键词或类型搜索' (search by keyword or type) and provides concrete examples like '餐厅、酒店、景点、加油站、停车场等' (restaurants, hotels, attractions, gas stations, parking lots). It also mentions the distinct capability of city range filtering, which differentiates it from sibling tools like amap_poi_around that are location-based.

  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 tool should be used when searching for POIs by keyword or type, and it mentions city filtering as a context. However, it provides no explicit guidance on when to use this tool versus alternatives like amap_poi_around, nor does it state any exclusions. The usage context is clear but not fully delineated.

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

• amap_direction_transitA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description must carry the full burden. It lists the return contents (transfer plan with details) but does not disclose potential caveats like cross-city support (cityd parameter), the effect of strategy, error behavior, or any limitations. The output list is helpful but insufficient.

  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, front-loaded sentence that states the purpose first and then details the return contents. It is concise and free of waste.

  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?

  With 7 parameters and no output schema, the description gives a useful high-level view of the return plan but omits explanations for optional parameters (date, time, cityd, strategy) and potential edge cases. It is adequate but lacks depth for a complex tool.

  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 baseline is 3. The description reiterates the main parameters (origin, destination, city) but adds no additional meaning 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 clearly states it performs bus/subway route planning and returns a transit transfer plan including walking segments, bus/subway lines, transfer count, duration, and fare. This specific verb+resource combination distinguishes it from sibling tools for driving, walking, and bicycling.

  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 usage for transit routing by naming '公交/地铁路径规划', but it does not explicitly state when to use this tool versus alternatives like driving or walking. It mentions required inputs (origin, destination, city) but provides no exclusions or comparisons.

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

• amap_poi_aroundA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description must carry the full burden of behavioral disclosure. It does not mention whether the operation is read-only, any pagination behavior, result formatting, or limitations beyond the basic search action. The description is purely functional and lacks important context about what the agent can expect.

  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, front-loaded sentence that immediately communicates the core action and includes practical examples. Every word earns its place, with no redundancy or fluff.

  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?

  With no output schema and no annotations, the description should provide more context about return values or behavioral details. The parameter names are documented in the schema, but the description is thin for a tool with 6 parameters, lacking any mention of pagination, sorting, or result structure. It is minimally adequate but not rich.

  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 input schema covers all 6 parameters with descriptions, so the baseline is 3. The description adds minimal semantic value by naming 'center point and radius' but does not explain parameters like types, offset, sortrule, or keywords 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 clearly states the tool performs a '周边搜索' (surrounding search) given a center point and radius, with concrete examples like restaurants, parking lots, and banks. This specific verb+resource combination distinguishes it from sibling tools such as amap_poi_search (keyword-based) and amap_poi_detail.

  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 usage when needing POIs near a location via '给定中心点和半径', but it does not explicitly state when to use this tool over alternatives like amap_poi_search or amap_poi_ranking. No direct comparisons or when-not-to-use guidance is provided, so usage context is only implied.

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

• amap_direction_bicyclingA
  3.6/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It does mention the output (route, distance, time, roads), but does not disclose any potential limitations, required input formats, or error scenarios. For a simple read-only query tool, this is adequate but not rich.

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

  Conciseness5/5

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

  The description is a single concise sentence that states the core purpose and output. No wasted words or redundancy.

  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 tool with only two required parameters and no output schema, the description covers the essential purpose and return information. It could mention input formats or limitations, but given the simplicity of the tool, it is reasonably 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 description coverage is 100% (both origin and destination have descriptions, albeit minimal). The description itself adds no parameter-specific meaning, 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 clearly states it performs bicycle route planning ('骑行路径规划') and specifies the return contents (total distance, estimated time, roads). This clearly distinguishes it from sibling direction tools like walking, driving, and transit.

  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?

  The description does not provide any guidance on when to use this tool versus alternatives. It merely describes the tool's function without mentioning conditions or exclusions, such as 'use this for cycling, use driving for motor vehicles.'

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

• amap_direction_walkingA
  3.6/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses that the tool returns total distance, estimated time, and step-by-step directions, which is useful. However, it does not mention whether origin/destination should be addresses, coordinates, or specific formats, nor does it state any safety or side-effect aspects (though none are expected).

  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 sentence that is front-loaded with the purpose and immediately lists the key return items. There is no redundant or filler text.

  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?

  Given that there is no output schema, the description adequately summarizes the main return fields (distance, time, directions). However, it lacks usage guidance and parameter format details, which would be helpful for an agent. Still, for a simple route-planning tool, it is reasonably 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?

  The input schema already describes both parameters ('起点' and '终点') with 100% coverage. The description adds no additional meaning about parameter formats or how to specify locations, so it does not go beyond what the schema 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 clearly states '步行路径规划' (walking route planning) and explicitly lists the return content: total distance, estimated time, and step-by-step directions. This distinguishes it from sibling direction tools like driving, transit, and bicycling by specifying the mode of travel.

  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?

  The description provides no guidance on when to use walking versus the alternative direction tools (driving, transit, bicycling). It only states the function, with no mention of prerequisites, exclusions, or contextual recommendations.

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

• amap_direction_drivingA
  3.9/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It provides substantial transparency by listing return data (total distance, estimated time, steps, tolls, traffic light count) and elaborates on strategy semantics (e.g., strategy 3 means avoid congestion by not taking expressways). However, it does not mention potential side effects, error behavior, or rate limits, but these are less critical for a read-only route planning 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?

  The description is concise: two sentences front-load the core purpose and output, followed by a compact strategy breakdown. Every sentence carries useful information, with no filler or redundant content. It is appropriately scoped for the tool's complexity.

  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?

  Given the tool has 8 parameters and no output schema, the description does a reasonable job explaining the primary inputs (origin/destination) and output fields, but it overlooks secondary parameters like waypoints, avoidroad, and avoidpolygons. These are left entirely to the schema. The description captures the core route planning behavior but doesn't fully cover all use cases or parameter interactions, leaving some gaps for a tool of this complexity.

  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 input schema has 100% parameter coverage with descriptions, so the baseline is 3. The description adds a bit of extra context by re-explaining the strategy codes and noting that origin/destination support coordinates or addresses, but this largely duplicates the schema. It does not introduce new parameter semantics 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 clearly states the tool's purpose as '驾车路径规划' (driving route planning) with a specific verb and resource. It distinguishes itself from sibling tools (walking, transit, bicycling) by explicitly focusing on driving and lists key outputs like distance, time, steps, toll fees, and traffic lights.

  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 usage for driving route planning but does not explicitly contrast it with alternatives such as walking or transit. It mentions input format (coordinates or addresses) and strategy options, but there is no explicit 'when to use' or 'when not to use' guidance. Since the tool name and context signal driving, usage is implied rather than stated.

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

• amap_poi_rankingA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden of disclosing behavior. It mentions the core behavior (search, sort, return top N) but doesn't explicitly state that this is a read-only operation or clarify limitations such as the need for location/city or the max 'top' value. This is sufficient 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.

  Conciseness5/5

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

  The description is two sentences long, front-loads the tool's identity and purpose, includes a helpful analogy, and gives concrete use cases. Every word earns its place with zero redundancy.

  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?

  Given the moderate complexity (8 parameters, no output schema), the description adequately covers the main use case and expected result (top N sorted list). It does not explain edge cases like location+radius interplay or minimum rating, but these are well-captured in the schema, so the description is not critically incomplete.

  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 baseline is 3. The description adds no parameter-specific details beyond what the schema already provides, aside from reinforcing the sorting concept. It does not compensate further or introduce ambiguity.

  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 the tool's function: searching POIs in a specified area/city and returning a sorted top-N list by rating/price. The analogy to '扫街榜' and the use cases ('找好餐厅、好酒吧') make it distinct from sibling tools like amap_poi_search or amap_poi_around.

  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?

  It provides clear context for when to use the tool ('找好餐厅、好酒吧、热门打卡地就用这个'), implying a ranking/exploration use case. However, it does not explicitly state when NOT to use it or name alternative sibling tools, so it misses the 'explicit alternatives' bar for a 5.

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

• amap_weatherA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It does disclose that the tool returns real-time or forecast weather data, which is useful behavioral information. However, it does not explicitly state that the operation is read-only or safe, nor does it mention any rate limits or response characteristics. For a simple query tool, this is adequate but not exhaustive.

  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 two short sentences, front-loaded with '天气查询' (weather query) and immediately followed by the operative detail. Every word earns its place; there is no fluff or repetition of schema content.

  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 is simple with two parameters and no output schema. The description covers the core functionality (real-time or forecast weather for a specified city) and is adequate for an agent to select and invoke it. It lacks explicit mention of return values or units, but given the tool's simplicity and full schema coverage, this is a minor gap. A score of 4 reflects that the description is nearly 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.

  Parameters3/5

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

  The input schema has 100% coverage with descriptions for both 'city' and 'extensions'. The description adds marginal value by echoing the real-time vs forecast distinction already present in the schema, but it does not provide any additional parameter-level details or examples beyond what the schema offers. Baseline 3 is appropriate given full schema coverage.

  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 ('查询' / query) and resource (weather for a specified city), and distinguishes itself from sibling tools by focusing on weather rather than directions, geocoding, or POI search. It also specifies the scope (real-time or future forecast), leaving no ambiguity about what the tool does.

  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 description provides clear context: it is for querying weather for a city. While it does not explicitly list when not to use it or mention alternatives, the sibling set is entirely non-weather, so the usage context is unambiguous. However, it lacks explicit guidance on choosing this tool over another, stopping short of a 5.

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

• amap_geocodeA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It adequately discloses the core behaviors: forward geocoding returns coordinates, reverse geocoding returns a structured address. It also sets expectations about the input/output relationship, though it omits potential edge cases like ambiguous addresses or rate limits.

  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 concise and front-loaded: the first sentence states the core conversion capability, and the second sentence provides a clear usage tip. No wasted words, every sentence adds value.

  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 description covers the essential aspects for a simple 3-parameter tool with no output schema: it explains both directions, mentions the return types, and positions the tool within the broader workflow. It could specify more about return format or failure behavior, but it is sufficiently complete for an agent to use it correctly.

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

  Parameters3/5

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

  Schema descriptions already cover all three parameters at 100% coverage, so the description adds limited extra semantic value. It reinforces which parameter to use for which direction, and adds the contextual note about narrowing city scope, but the schema already provides examples and explanations. Baseline 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 the tool's purpose: converting between addresses and coordinates, with explicit mention of both directions. It distinguishes itself from sibling direction/POI tools by framing itself as a preliminary step for path planning.

  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 description provides clear context on when to use the tool: before any route planning to obtain start/end coordinates. It also explains the two usage modes (address-provided or location-provided), giving practical guidance, though it does not explicitly mention when not to use it or alternative tools.

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

• amap_poi_detailA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. It discloses the type of information returned (score, per-person cost, hours, images) and implies a read-only lookup. It does not discuss error behaviors or rate limits, but for a simple detail retrieval the description is reasonably transparent.

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

  Conciseness5/5

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

  The description is a single sentence that is front-loaded with the tool's purpose, followed by usage context and key fields. There is no redundant wording, making it appropriately concise and well structured.

  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 tool with one parameter and no output schema, the description explains what it does, how to use it, and what kind of data is returned. It could mention potential error cases or response format, but the information provided is sufficient for basic invocation and integration with sibling tools.

  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 provides 100% parameter coverage with 'id' described as 'POI ID，来自搜索结果的 id 字段' (POI ID from the search result's id field). The description adds that this tool is for details using that ID, but it doesn't introduce information beyond the schema's own parameter description, 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 clearly identifies the tool as 'POI 详情查询' (POI detail query) and explains it retrieves detailed information by POI ID, listing specific fields (rating, per capita, business hours, images). This distinguishes it well from sibling tools like search, directions, and geocoding.

  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 description explicitly indicates it is used together with search/ranking tools ('配合搜索/扫街榜使用'), implying the intended workflow (get ID from search, then call this tool for details). It does not list explicit exclusion cases, but the context is clear enough for a single-purpose detail lookup.

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

• amap_ip_locationA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description discloses that the location is approximate and at city level, and that no parameters are needed. This covers the key behavioral traits of this simple read-only 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?

  The description is two short sentences, front-loaded with 'IP 定位', and every sentence adds value with no 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?

  Given the tool has zero parameters and no output schema, the description adequately covers its purpose, behavior, and use case. It could mention the return format, but for a simple location lookup this is sufficient.

  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?

  Since there are no parameters, the schema coverage is 100% and the description reinforces this with '无需任何参数'. The baseline for 0 params is 4.

  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 the tool's function: 'IP 定位' and getting the current network egress's approximate city-level location. It also indicates the use case ('快速确定我在哪'), distinguishing it from geocoding and POI tools.

  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?

  It says when to use this tool: to quickly determine your current location. However, it does not explicitly name alternative tools or give exclusion criteria, but the context is clear enough.

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