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

No annotations are provided, so the description carries the full disclosure burden. It adds API-version context (POI 2.0, v5) and makes clear this is a read/search operation, but it does not mention result shape, pagination, or how optional parameters interact.

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

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

The description is one front-loaded sentence that states the core operation first. The parenthetical API version is useful but slightly secondary; it is concise overall with no 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?

It is minimally viable: core semantics and schema coverage enable a correct call, but with 10 parameters, no annotations, and no output schema, the description alone leaves gaps around return values and when to set region/city_limit/sortrule.

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 each parameter and its defaults. The description adds no extra semantic value for the parameters, which warrants the baseline 3.

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

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

The description names a concrete operation: search POIs centered on a coordinate within a radius. It clearly distinguishes this from siblings like maps_text_search or maps_geo by the geospatial 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?

It supplies clear context: use when the user has a center coordinate and wants nearby POIs within a radius. It does not explicitly name alternatives or exclusions, but the coordinate-scoped framing makes the intended use obvious.

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

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

No annotations are provided, so the description carries the behavioral disclosure burden. It usefully adds that one-way streets and road closures are considered, which is real algorithmic behavior. But it does not mention return behavior, whether the operation is read-only, response format, or any rate/usage constraints.

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

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

The description is one short sentence and front-loaded with the main purpose. The parenthetical '路径规划 2.0，v5 接口' is internal version detail that adds little for an agent, but overall there is minimal waste.

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 four-parameter tool with full schema coverage, the description is mostly sufficient. However, with no annotations and no output schema, it would be stronger if it indicated what the tool returns and gave any guidance about how alternatives or route fields behave.

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

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

Schema description coverage is 100%, so the schema already documents all four parameters and their formats. The description adds no parameter-level meaning beyond the schema, which is acceptable but not an improvement.

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 operation: 骑行路径规划 (cycling route planning), with a specific resource and mode. The "骑行" qualifier distinguishes it from sibling driving/walking/transit route tools, so there is no ambiguity about what this tool is for.

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 riding mode and '路径规划' imply the tool is for bicycle route queries, so the usage context is inferable. However, it does not explicitly say when to prefer this over maps_direction_driving/walking/transit, nor does it name alternative tools or exclusion conditions.

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

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

No annotations are provided, so the description carries the full burden. It lists supported features (waypoints, strategy, plate avoidance, avoidance areas) but these merely restate what the schema already documents. It does not disclose expected behavior like what is returned, error conditions, or any constraints or side effects of the driving route calculation.

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

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

The description is a single concise sentence, front-loaded with the core purpose and then enumerating the most relevant capabilities. It wastes no words, though '等' is a slight filler that leaves the list open-ended.

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 12 parameters and no output schema, the description is adequate but not complete. It conveys the main purpose and key features, but it does not describe what the response contains, and it provides no usage context relative to the sibling direction tools. The rich schema compensates for parameter-level completeness.

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

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

Input schema coverage is 100%, so the schema describes every parameter, including formats and option values. The description adds little semantics beyond listing four feature categories already visible in the schema, 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.

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

The description clearly states '驾车路径规划' (driving route planning), identifying both the specific action and the resource. The '驾车' qualifier distinguishes it from sibling tools like maps_direction_walking, maps_bicycling, and maps_direction_transit_integrated without 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 does not explicitly state when to use this tool over alternatives. It implies driving use from the name and description, but provides no guidance such as 'use walking/bicycling/transit tools for non-driving routes' or any conditions that would select 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals what transport modes are covered but omits other behavioral traits such as response format, required cross-city parameter handling, rate limits, or any operational caveats. For a route-planning API, this is a meaningful gap.

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

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

The description is one short, front-loaded sentence that conveys the core purpose and coverage. There is no redundant or filler content, and every phrase 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?

This is a complex tool with 14 parameters, no output schema, and no annotations, yet the description only provides a high-level overview. It does not explain cross-city requirements, default behaviors, return structure, or how the many optional parameters interact. The description is too thin to fully support correct invocation 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.

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

Schema description coverage is 100%, so every parameter already has a meaningful description in the schema. The tool description does not add parameter-level semantics beyond noting the cross-city scope, which is the expected baseline when the schema is thorough.

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: public transit route planning, spanning bus, subway, train, and cross-city travel. This distinguishes it from sibling direction tools like driving, walking, and bicycling. The resource and scope are specific and immediately understandable.

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

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

The description makes clear that this tool is for transit and cross-city route planning, giving an agent strong contextual guidance on when to select it. It does not explicitly name sibling alternatives or state when not to use it, but the transit coverage is explicit enough to route selection 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?

No annotations are provided, so the description carries the full burden. It discloses two behavioral traits: indoor routing support and returning multiple alternative routes, but it does not state that the operation is read-only or describe response behavior, errors, or limitations. These are meaningful additions, though coverage is 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 description is short and front-loaded with the core operation, followed by capability highlights. The version parenthetical '路径规划 2.0，v5 接口' is technical noise for an AI agent, but the overall size is appropriate and there is no repetition of schema 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?

All seven parameters are documented in the schema, and the description supplies the operation mode plus the two notable optional capabilities. No output schema is present, but route-planning intent and the show_fields parameter make the expected response reasonably clear; a note on returned route data would make it fully complete.

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

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

Schema description coverage is 100%, so the baseline is 3 even without parameter details in the description. The description's 'indoor routing' and 'multiple alternative routes' map to isindoor and alternative_route, reinforcing tool-level intent but adding no syntax 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 identifies a walking route planning operation and distinguishes it from sibling tools for driving, bicycling, and transit by specifying '步行'. It also adds capability context with indoor routing and multiple alternatives, so an agent can tell this tool apart 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.

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

The walking mode is stated, implying use when a pedestrian route is needed, but the description gives no explicit when-to-use/when-not-to-use guidance or mention of alternative sibling tools. An agent must infer usage from the tool name and sibling list.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It reveals that the tool computes straight-line, driving, or walking distance and notes support for multiple origins, but it does not describe output format, units, or behavior for multiple origins. This is adequate but not richly transparent.

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

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

The description is a single, efficient sentence with no filler. The core purpose is front-loaded, and every word adds value. It is concise without sacrificing 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?

The parameters are well documented and the tool is simple, but there is no output schema and the description does not explain return format, units, or how multiple origins affect the result. It also does not distinguish itself from the sibling direction tools, leaving some practical gaps 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 parameters are already fully documented. The description adds no meaning beyond the schema; it only restates the general purpose. The baseline of 3 applies since 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 action ('measure distance') and the resource (origin to destination), and lists the distance types. It is distinct from the direction-related siblings by focusing on distance, but it does not explicitly name or contrast those alternatives.

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

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

The description implies that the tool is for measuring distance, but it provides no explicit guidance on when to use this tool versus the many sibling direction tools, nor any exclusions. An agent must infer the appropriate context from the tool name alone.

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?

没有任何注解，描述需承担行为披露的全部责任。虽然提到了GCJ-02坐标系这一有效细节，但未说明返回格式、请求限制、认证要求或错误处理行为。对于无注解工具，信息量不足以让代理预知调用后的结果和边界情况。

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?

描述用一句话完成：动词、资源、坐标系和语言范围都已包含，信息密度高且无冗余。结构上先给出核心功能，再补充输入支持范围，简洁有效。

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，描述未说明返回坐标的结构或数据格式；也未提到地理编码失败时的行为、无法解析地址的处理或精度限制。参数虽少但缺少返回与边界信息，对于无注解的简单工具仍显不完整。

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描述覆盖率为100%，两个参数在schema中已有清晰说明。描述额外补充'支持中文地址、地标名称'，扩展了address参数的输入语义，但整体未超出schema太多，符合覆盖率高的基线评分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?

描述以'地理编码'开头，明确说明将结构化地址转换为高德经纬度坐标（GCJ-02），动词和资源具体清晰。虽然未直接与兄弟工具对比，但'地理编码'与'maps_regeocode'、'maps_ip_location'的语义天然区分，代理能够理解其用途。

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?

描述未说明何时应使用此工具而非maps_regeocode或maps_ip_location，也没有提供排除条件或替代场景。仅通过'地理编码'这一行为隐含了'有地址需要坐标时使用'的上下文，缺少显式路由指引。

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

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

No annotations are provided, so the description carries the behavioral burden. It discloses the approximate nature of the result ('大致范围') and the output type (city), which is basic but useful. It does not mention possible precision limits, response format, or handling of invalid IPs.

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

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

The description is one short, focused sentence that front-loads the action and output. Every word earns its place, and nothing is redundant.

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

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

For a single-parameter, low-complexity tool, the description adequately states what the agent needs to know: what to pass (IP) and what to expect (city and approximate range). There is no output schema, but the description names the return concept clearly enough.

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 fully describes the single 'ip' parameter as an IPv4 address (100% coverage). The description adds no new semantic detail beyond confirming that the IP is the subject of the lookup.

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

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

The description uses a specific verb ('查询') and clearly identifies the resource ('IP地址') and output ('所在城市及大致范围'). This makes it easy to distinguish from sibling tools like maps_geo or maps_regeocode, which handle different location lookups.

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 usage context is implied: call this tool when you have an IP address and need a city-level location. However, there is no explicit guidance about when not to use it or how it compares to alternatives such as maps_geo for coordinate-based lookups.

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

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

With no annotations provided, the description carries the full burden. It adds useful behavioral context by specifying the GCJ-02 coordinate system and the output type, but it does not disclose potential failure modes, coordinate validation rules, authentication needs, 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.

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

The description is a single, front-loaded sentence with no filler. It communicates the operation, input, and output efficiently.

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

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

For a one-parameter, low-complexity tool, the description provides the essential context: input coordinate system, conversion direction, and output content. The schema fully documents the parameter, though a small amount of sibling routing or return-format detail could make it more complete.

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

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

Schema description coverage is 100%, and the single parameter location already includes a clear format and example. The description adds no parameter-level meaning beyond the schema, 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.

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

The description states a specific operation and resource: reverse geocoding converts GCJ-02 coordinates into structured address and administrative-division information. This clearly distinguishes it from forward geocoding siblings like maps_geo.

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

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

The description clearly implies the use case: use it when you have Gaode coordinates and need a structured address. However, it does not explicitly mention when not to use it or name alternatives such as maps_geo, maps_around_search, or maps_ip_location.

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

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

No annotations are provided, so the description carries the full burden. It discloses batch support, the API version, and the read-only nature via '查询', but it does not mention behavior for invalid IDs, default vs optional response fields, rate limits, or response structure.

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

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

The description is two short, information-dense sentences with no filler. It front-loads the primary action and result categories, then adds batch capability and version context.

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

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

For a simple two-parameter lookup with no output schema, the description plus highly detailed schema covers what an agent needs to call it correctly. It could add response-format or error-handling details, but the current coverage is strong 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 coverage is 100% with detailed parameter descriptions: id explains source, delimiter, and max count, while show_fields lists all acceptable values. The description adds little beyond repeating a few field examples, so 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 clearly states the action: query detailed POI information by POI ID, and lists the kinds of details returned (address, phone, hours, photos). This makes it reasonably distinct from sibling search/direction tools, though it never explicitly names or differentiates a sibling.

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 id parameter description explains that IDs come from keyword search or around search, which implies this tool is the follow-up detail lookup after searching. It provides clear context but does not explicitly state when not to use it versus direction or geocoding 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?

No annotations are present, so the description carries the full behavioral disclosure burden. It only appends an API version note ('搜索POI 2.0，v5接口') and does not disclose response format, pagination/ranking behavior, or the fact that region merely increases recall weight rather than restricting results — all of which an agent would need to know before invoking.

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 entry is a single short sentence with the core action front-loaded before the trailing API version parenthetical. It is efficient, though the version note ('搜索POI 2.0，v5接口') is of marginal value to an AI agent.

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

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

For a 7-parameter tool with no annotations and no output schema, the description is too thin: it does not help the agent decide between this and maps_around_search/maps_search_detail, gives no sense of return contents, and lacks behavioral caveats. The complete schema compensates for parameter understanding but not for tool selection or output expectations.

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

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

Schema description coverage is 100%, so all 7 parameters are already documented in the input schema and the baseline is 3. The description's POI examples (餐厅、加油站、景点) add mild illustration for what can go in 'keywords' but provide no semantics 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 clear action ('根据关键词搜索' / keyword search) and a specific resource (POI 兴趣点) with concrete examples (餐厅、加油站、景点). It conveys the keyword-driven nature that separates it from location-based siblings like maps_around_search, though it does not explicitly name or contrast any sibling.

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

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

No guidance is provided on when to use this tool versus alternatives such as maps_around_search (nearby/location-based search) or maps_search_detail (POI detail lookup). The '根据关键词' phrasing only implies a keyword-based use case; it never states it or excludes the alternatives.

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

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

No annotations are provided, so the description carries the full behavioral burden. '查询' implies a read-only operation and the forecast scope is stated, but the description does not mention response format, units, or how city name versus adcode is handled. Adequate for a simple query tool but not richly transparent.

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

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

The description is a single, front-loaded sentence with no filler. It efficiently conveys the operation, resource, and temporal scope without unnecessary details.

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

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

For a simple one-parameter tool with no output schema, the description plus input schema are sufficient to make a correct first call. Minor gaps like units or forecast length are not critical given the tool's low complexity.

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

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

Schema description coverage is 100%, so the single parameter is already documented by the schema. The description adds the 'next few days' time scope but provides no additional semantics about the city parameter 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 verb and resource: '查询' (query) the weather forecast for a specified city over the next few days. It is clearly distinct from the sibling geocoding, search, and direction tools, so an agent can immediately identify what this tool does.

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 usage is clear: use this tool when a weather forecast for a city is needed. No explicit when-not or alternative conditions are stated, but no sibling tool offers weather functionality, so routing is unambiguous.

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