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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds value by specifying the return format (CSV text with header), the default limit (2000), and a usage tip. No contradictions; it enriches behavioral context.

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

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

The description is well-structured with a bold lead, bulleted parameters, and a tip. It is front-loaded with the purpose and uses emoji for emphasis. Slightly verbose but effectively organized.

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

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

Given no output schema, the description adequately explains the return value (CSV text). It covers parameters, output format, and usage tips. Missing error handling or performance notes, but sufficient for a read-only export tool.

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

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

Schema coverage is 100%, but the description provides extra clarity with a format example for startTime, enumerates alarmType values, and confirms the limit default. This goes beyond the schema's basic descriptions.

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

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

The description clearly states the tool exports alarm records as CSV text for pasting into Excel, specifying verb (export), resource (alarms), and format (CSV). It distinguishes from sibling 'list_alarms' by emphasizing batch export and Excel compatibility.

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

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

The description provides context for using the tool (copy-paste to Excel) but lacks explicit guidance on when to choose this over alternatives like 'list_alarms' or when not to use it. No exclusions or prerequisites are mentioned.

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

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

Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds context that this returns aggregated data and constrains days to 1-90, which complements the annotations without contradiction.

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

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

The description is concise with an emoji header, sections for parameters, return value, and hint. Every sentence is informative and efficiently structured, with no redundancy.

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

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

For a read-only query tool with 100% schema coverage and no output schema, the description adequately covers input constraints, output format (aggregated daily/by type), and use case. It is sufficient for an agent to select and invoke the tool correctly.

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

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

Schema coverage is 100%; all parameters have descriptions. However, the description adds value by clarifying the default for days (7) and that the output is aggregated by day and type ('按日/按类型聚合'), which goes beyond schema descriptions.

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

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

The description clearly states it is a query for alarm trend statistics by time period, distinguishing it from siblings like list_alarms which lists individual alarms. It uses specific verb '查询' (query) and resource '告警趋势统计' (alarm trend statistics).

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

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

The description indicates suitability for weekly/monthly reports ('适合用于周报/月报分析'), but does not explicitly state when not to use or suggest alternatives. The context is clear enough for an agent to infer appropriate usage.

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

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

Annotations declare readOnly, idempotent, non-destructive. Description adds '数据来自 Java 实时 API' (real-time data from Java API) and lists exact return fields (tag code, binding name, coordinates, entry time), providing excellent behavioral insight beyond annotations.

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

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

Two sentences plus structured bullet for parameters and return. Uses emoji for quick categorization. Every line adds value, no redundancy.

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

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

Simple tool with one required parameter. Description covers purpose, parameter, return values, and data source. Annotations cover safety and idempotency. No gaps given the tool's simplicity.

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

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

Only one parameter (areaId), schema coverage 100%. Description merely restates '区域ID' but adds no extra meaning. Baseline score of 3 is appropriate as schema already documents the parameter well.

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

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

Clearly states '查询某区域内当前的人员' (query current personnel in a specific area). Verb and resource are specific. Distinguishes from siblings like list_personnel (all personnel) and get_personnel_location (single person).

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?

Description explicitly requires areaId parameter and states the tool queries personnel in an area. Implicitly suggests use for area-scoped queries vs. list_personnel for all. No explicit when-not or alternatives, but context is sufficient.

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

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

Annotations readOnlyHint and idempotentHint already indicate safe, idempotent operation. Description adds return structure (coordinates, binding, battery, online status) and performance behavior (batch parallelism), providing useful context beyond annotations.

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

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

Concise and well-structured: introductory sentence, parameter breakdown, return summary, and performance tip. No superfluous text; front-loaded key action.

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

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

Covers parameter, return fields, and performance advantage. Lacks error handling for partial failures, but given read-only nature and annotations, it is sufficiently complete for most use cases.

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 description of tagCodes. The description restates the parameter's required status and max 100 constraint, adding no new meaning. Baseline 3 is appropriate.

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

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

The description clearly states 'batch query multiple tags' real-time location' with a single verb and resource. It differentiates from siblings like get_tag_location (single tag) and list_tags (list only) by emphasizing batch and real-time positions.

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 tip '比逐个查询快5-10倍' implicitly advises using this over single-tag queries when multiple tags are needed. No explicit when-not-to-use or alternatives listed, but the context is clear.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds valuable behavioral details: the return structure (tagCode, area, time, status) and that omitting areaId returns all areas. This enriches transparency beyond annotations.

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

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

The description is concise with a clear bulleted list for parameters. It is front-loaded with a purpose statement, though the emoji is decorative. Every line adds information without redundancy.

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

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

For a read-only query tool with no output schema, the description covers purpose, all parameters, and return fields. It provides enough context for an agent to use the tool correctly, though pagination behavior could be elaborated.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by specifying timeRange format ('YYYY-MM-DD') and explaining that areaId omission returns all areas, which the schema's description does not fully capture.

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

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

The description clearly states the verb '查询' (query) and the resource '进出区域记录' (in/out area records), making it distinct from sibling tools that focus on tags, personnel, or locations. It precisely defines the tool's purpose.

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

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

The description includes a hint about using timeRange to query a specific day, providing some usage context. However, it does not explicitly exclude cases or suggest alternatives among the many sibling tools.

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

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

Annotations already declare readOnly, idempotent, non-destructive. Description adds return fields (code, percentage, binding name, coordinates) and threshold tip (range 1-99), providing useful context beyond metadata.

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?

Clear structure with header, bullet parameters, and tip. Efficient but could be more concise by omitting emoji and redundancies.

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

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

With no output schema, description lists return fields. Covers all parameters and usage hints. Complete for a simple query tool.

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

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

Schema coverage is 100% with descriptions. Description adds default threshold (20), explains threshold meaning, and gives range hint (1-99). Adds value beyond schema.

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

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

The description specifies the action as '筛选低电量标签' (filter low-power tags) by threshold. This clearly distinguishes it from sibling tools like list_tags (all tags) and get_tag_location (single tag location).

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?

Implicitly states to use when needing low-power tags filtered by threshold and optionally by map. Does not explicitly contrast with alternative tools, but context signals and sibling names imply its niche.

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

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

The annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds value by explaining that presence status is determined 'based on entry/exit records + real-time location,' which is behavioral context beyond the annotations. There is no contradiction with annotations.

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

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

The description is concise and well-structured, starting with a clear purpose line, followed by parameters, return value, and a hint. It uses appropriate formatting (emojis and line breaks) for readability. However, the hint could be integrated into the main purpose sentence to avoid redundancy.

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

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

For a read-only diagnostic tool with no output schema, the description adequately covers the return structure (list of areas with name, present count, and person list). It also notes the optional filters. Given the moderate complexity and low parameter count, the description is sufficiently complete. However, it does not mention pagination or limits if the result set is large.

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

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

The input schema describes both parameters (mapId, areaId) with brief descriptions. The tool description repeats these descriptions without adding further meaning (e.g., format, required relationships, defaults). Since schema coverage is 100%, baseline is 3, and the description does not enhance parameter semantics.

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 analyzes personnel distribution across areas and shows the number of people present. It specifies the optional filters (mapId, areaId) and the return structure (area list with names, count, and person list). This distinguishes it from sibling tools like 'list_personnel' which lists all personnel, and 'get_area_personnel' which may focus on a single area. However, it could better differentiate from 'get_area_personnel' explicitly.

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

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

The description explains that parameters are optional and can be used to filter by map or area. It mentions that presence is determined based on entry/exit records and real-time location, implying this tool is for diagnostic purposes. However, it does not provide explicit guidance on when to use this tool versus siblings like 'get_area_personnel' or 'search_personnel', nor does it mention when not to use it.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the tool is a safe read. The description adds value by detailing the return fields (name, coordinates, map, area) and notes internal parallel query behavior, which goes beyond the annotations.

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

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

The description is concise: three lines covering query purpose, parameter specification, return info, and a note. Front-loaded with an emoji and key action, no extraneous words. Every sentence earns its place.

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

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

With one required parameter, full annotations, and no output schema, the description provides a clear set of return fields and a behavioral note. It is complete for a simple query tool, though it could mention error handling or whether multiple names can be queried at once.

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

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

Schema coverage is 100% and the parameter description in the schema already explains the parameter. The tool description repeats the schema info with an example, but adds no extra semantics regarding format, validation, or constraints beyond the example. Baseline 3 is appropriate.

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

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

The description clearly states it queries real-time location by personnel name or ID. It distinguishes from siblings like get_tag_location (by tag), get_area_personnel (by area), and search_personnel (search), making the tool's specific resource and action unambiguous.

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

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

The description implies usage for getting location of a known person but does not explicitly state when to use this tool versus alternatives. No when-not or exclusions are provided, leaving the agent to infer context from sibling names.

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

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

Annotations already indicate read-only and idempotent behavior. The description adds that it calls Java API with retry protection, providing useful information beyond annotations.

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

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

The description is succinct, uses clear sectioning, and front-loads the purpose. Every sentence adds value with no unnecessary words.

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

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

Given the simplicity (no parameters, no output schema), the description fully covers what the tool does, its returns, and its usage context. The retry protection note adds 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?

There are no parameters, and the description confirms this with '无需参数'. The baseline for zero parameters is 4, and the description adds no extra parameter information.

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

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

The description clearly states 'get system statistics overview' and enumerates specific return fields, distinguishing it from sibling tools like list_tags or list_personnel.

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 tip '适合快速了解系统整体状态' (suitable for quickly understanding overall system status) implies the tool is for a quick overview, but does not explicitly state when not to use or list 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?

Annotations (readOnlyHint, idempotentHint, destructiveHint) confirm safe query behavior. The description adds return fields (tagCode, bindName, bindType, bindId), providing useful structure beyond annotations.

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

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

The description uses emojis and line breaks, which adds noise. While clear, it could be more concise without losing information.

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

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

For a simple query tool with one optional parameter and no output schema, the description sufficiently covers behavior and return format. Annotations handle safety context.

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

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

Schema description coverage is 100%, and the description reiterates the same information about tagCode being optional and returning all if omitted. No new semantic meaning is added beyond the schema.

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

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

The description clearly states the verb '查询' (query) and resource '标签与人员/车辆/货物的绑定关系' (tag bindings to personnel/vehicles/goods). It is distinct from sibling tools like bind/unbind tools, making the purpose unambiguous.

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

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

The description includes a hint that omitting tagCode returns all bindings, guiding parameter usage. However, it does not explicitly contrast with sibling tools for creating bindings, though the read-only nature is implied.

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

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

Annotations indicate read-only and idempotent; description adds details on returned fields (coordinates, map, timestamp, battery, bound person, area) and error behavior when tag is offline or missing data.

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

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

Concise, front-loaded purpose, uses emoji and clear sections for parameters, returns, and hints, no redundant sentences.

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

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

With one required parameter, good annotations, and no output schema, the description covers essential return fields and error cases, sufficient for an AI agent to correctly invoke the tool.

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

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

Schema coverage is 100% and description adds an example value 'UWB001', but does not provide additional semantics beyond the schema.

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

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

Description clearly states 'query real-time location by tag code', differentiating from sibling tools like get_personnel_location (query person's location) and get_batch_tag_locations (batch query).

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

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

Description implies use when needing a single tag's location, but does not explicitly state when to use vs alternatives or when not to use.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds context: it queries from location_data table, returns totalCount and pointCount, and explains limit behavior. This goes beyond annotations.

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

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

The description is well-structured with an emoji header, a clear parameter list with formats, return structure, and a practical tip. Every sentence adds value, no redundancy.

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

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

Although no output schema, the description explains return fields (totalCount, pointCount, trajectory points) and includes a pagination hint. This is sufficient for a query tool with moderate complexity.

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

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

Schema coverage is 100%, so the schema already documents parameters. The description reinforces parameter meanings, adds format examples for time strings, and notes limit max 5000. This provides marginal additional value.

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

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

The description clearly states '查询标签的历史位置轨迹' (query tag's historical location trajectory), using a specific verb and resource. It distinguishes from sibling tools like get_tag_location (likely current location) and list_tags (list all tags).

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

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

The description includes a tip about using COUNT before LIMIT and advises to narrow time range or increase limit if totalCount exceeds limit. This provides practical guidance, though it doesn't explicitly state when not to use the tool.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds return field details (tag code, type, time, description) and default limit, but does not disclose potential side effects for a read-only tool. It does not contradict annotations.

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

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

The description is brief, uses an emoji for visibility, and organizes parameters and return info into clear sections. No unnecessary sentences; all content is relevant.

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

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

Given no output schema, the description adequately explains return fields and the filtering condition. It mentions a usage scenario but lacks details on pagination or ordering. For a simple read-only list tool, it is sufficiently complete.

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

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

Schema coverage is 100%, so the schema already describes both parameters fully. The description restates the parameter ranges and defaults, adding minimal extra value beyond the schema.

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

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

The description clearly states the tool queries unread alarm lists (isRead=0), distinguishing it from sibling list_alarms which likely returns all alarms. The verb '查询' and resource '未读告警列表' are specific.

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

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

The description includes a usage hint for security monitoring scenarios, implying when to use it. However, it does not explicitly exclude alternatives like list_alarms for all alarms, lacking explicit when-not guidance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds a useful hint: max 2000 results returned, and outlines return structure (name, type, threshold, controlled period).

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?

Concise, front-loaded with emoji and purpose. Uses bullet points for parameters and return hints. Every sentence adds value; no fluff.

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

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

Given simple tool with 2 optional params, annotations present, and no output schema, the description provides essential info: purpose, filters, return content, and limit. Could mention pagination or sorting, but max 2000 hint helps. Adequate for selection.

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

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

Schema coverage is 100% with parameter descriptions. Description adds minimal value: restates the enum mapping for alarmType (same as schema) and keyword as 'rule name keyword'. No new semantic depth beyond schema.

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

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

Description clearly states '获取告警规则列表' (get alarm rules list) with specific filtering options by type or name. It distinguishes from siblings like list_alarms (events) and mutation tools for rules.

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?

Describes optional filters for alarmType and keyword, giving guidance on how to use. Does not explicitly compare to siblings, but the tool's purpose is distinct enough. Context is clear for listing rules.

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

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds behavioral details: returns a list with fields (type, time, area, content, read status), explains pagination (pageSize defaults to 50, max 500), and parameter formats. No contradiction.

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

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

The description is well-structured with clear sections for parameters and return. Every sentence adds information; no fluff. The emoji and header ('📊 查询') provide visual cue. It is front-loaded and appropriate length.

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

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

For a query-only tool with comprehensive annotations and schema, the description covers all necessary aspects: filters, pagination, return fields. With no output schema, it still lists key return fields. It feels complete for agent decision-making.

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 descriptions for all 6 parameters. The description adds value by providing examples for alarmType (e.g., '超时', '越界'), explicit timeRange format ('YYYY-MM-DD' or range), and a usage tip for isUnread. This goes beyond the schema's basic descriptions.

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

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

The description clearly states the tool queries alarm records with specific filters (tag, type, time range, read status). It uses the verb '查询' (query) and resource '告警记录' (alarm records). Distinguishes from siblings like 'get_unread_alarms' (focused on unread) and 'export_alarm_csv' (export format).

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

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

The description includes a usage tip: '处理告警时设 isUnread=true 只看未读' (when handling alarms, set isUnread=true to see only unread). It provides context for parameter usage but does not explicitly mention alternatives or when not to use this tool, though siblings like 'get_unread_alarms' exist.

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

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

Annotations already declare readOnlyHint true, idempotentHint true, and destructiveHint false, covering safety. The description adds the 2000-item limit, which is useful, but does not mention other behaviors like pagination, ordering, or rate limits. The added value beyond annotations is moderate.

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

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

The description is well-structured with a header, parameter list, return info, and a hint. It is concise and front-loaded, though the emoji header adds little value. Overall efficient and easy to parse.

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

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

For a simple read-only list tool with no output schema, the description sufficiently explains the return fields and a limitation (2000 max). It covers the main aspects, though it lacks details on error handling or prerequisites. Contextually complete given the tool's simplicity.

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

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

Schema descriptions cover 100% of parameters, so the description repeats similar information with examples. It adds minimal value beyond the schema, such as illustrating possible values for status. Baseline 3 is appropriate.

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

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

The description clearly states '获取基站列表' (get anchor list) and the filtering options, identifying the resource (anchors) and action (list). It is distinct from sibling tools like list_maps or list_areas, which serve different resources.

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 listing anchors with optional filters and hints at a 2000-item limit, but lacks explicit guidance on when to use this tool versus alternatives (e.g., creation, update, delete tools exist but not mentioned). Usage context is implied rather than explicitly stated.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral context by stating the maximum return of 2000 records, which is not in annotations, and clarifies the filtering behavior. No contradictions.

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

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

The description is concise, with a clear purpose statement followed by parameter details and return format. Every sentence adds value, and the structure is front-loaded with the intent.

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

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

For a simple list tool with no output schema, the description adequately explains return fields (name, entry/exit base points, fitting method) and the 2000-record limit. It is complete given the tool's complexity and context.

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

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

Schema coverage is 100% with both parameters described. The description repeats this information but adds a hint about the result limit (2000). Since schema already provides meaning, baseline 3 is appropriate; the description adds marginal value.

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

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

The description clearly states the verb '获取' (get) and the resource '区域规则（算法规则）列表' (list of area rules), along with filtering options. It distinguishes itself from sibling tools like list_alarm_rules or list_tags by specifying 'area rules' and the underlying algorithm nature.

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 provide guidance on when to use this tool versus alternatives (e.g., when to use list_area_rules vs. list_areas or other list tools). No conditional usage or exclusions are mentioned.

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

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

Annotations declare readOnly, idempotent, not destructive. Description adds useful behavior: maximum 2000 results and return fields (name, type, mapId). No contradictions.

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?

Concise three sentences with bullet-point parameters. Purpose is front-loaded. No redundant information.

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?

Simple tool with one optional parameter and no output schema. Description explains return fields, filtering, and limit. Fully adequate for usage.

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

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

Description repeats schema description exactly for mapId, adding no new semantics. Schema coverage is 100%, so baseline 3 applies.

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

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

Description clearly states verb '获取' and resource '区域列表', distinguishes from sibling tools like list_tags and list_maps by specifying it returns areas with optional map filtering.

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

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

No guidance on when to use this tool versus alternatives like list_maps or list_alarms. Does not provide criteria for filtering or exclude any use cases.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering safety and idempotency. The description adds context such as pagination defaults and return fields, but does not contradict annotations.

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

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

The description includes a parameter list that largely repeats the schema, reducing conciseness. It is adequately front-loaded with purpose but could be more concise by omitting redundancy.

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

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

For a simple read-only list tool with no output schema, the description covers essential aspects: purpose, filtering, pagination, and return fields. It is complete enough for an agent to understand behavior.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds value by listing defaults (pageSize: 100, page: 1) and providing a hint about keyword fuzzy search, improving parameter understanding beyond the schema.

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

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

The description clearly states the tool retrieves a list of cars with filtering by type, keyword, and binding status. It distinguishes from sibling list tools (list_tags, list_personnel) by focusing on car-specific attributes.

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 versus alternatives like search_personnel. Usage is implied by the tool's function but lacks direct guidance or exclusion criteria.

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

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

Annotations indicate read-only, idempotent, non-destructive behavior. The description adds that it returns up to 2000 records as a nested tree structure, which is useful beyond annotations. No contradictions.

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

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

The description is concise and uses structure (emojis, bullet points). It front-loads the purpose and provides key details without unnecessary verbosity.

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

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

For a simple list tool with one optional parameter and clear return structure described, the description is complete enough. No output schema exists, but the description outlines return fields.

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

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

The single parameter 'keyword' is described in both the schema and description as an optional search term. The description adds context (optional, keyword search) beyond the schema's '按部门名称搜索'.

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 name and description clearly state the tool retrieves a tree structure of departments. The emoji and Chinese text indicate a query operation. It is distinct from sibling tools like list_personnel or list_tags.

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 versus alternatives, but the context of sibling tools suggests it is for department listings. No when-not-to-use guidance is provided.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description repeats '查询' (query) but adds no behavioral details beyond the schema. No contradiction.

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

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

The description is concise, well-structured with bullet points, and front-loaded with a clear purpose. Every sentence adds value.

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

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

Given no output schema, the description mentions return fields (编号、名称、绑定标签). Pagination and filtering are covered. Lacks output format details but sufficient for a list tool.

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

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

Schema coverage is 100% with descriptions for all 4 parameters. The description restates them in user-friendly Chinese, adding marginal value. Baseline is 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 clearly states the tool lists goods/cargos with optional filtering by name or binding status. It uses a verb-noun structure and distinguishes from sibling tools like list_tags and list_personnel.

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

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

The description provides explicit parameter details, default values, and a hint for fuzzy search. While it doesn't explicitly contrast with sibling tools, the context of sibling names makes its use case clear.

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

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

Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds a specific behavioral constraint: maximum 2000 records returned. This is valuable beyond annotations, though it could mention sorting or pagination behavior for completeness.

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 extremely concise: three lines covering purpose, parameters, return fields, and a usage hint. Every sentence adds value, and the emoji front-loads the action. No wasted words.

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

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

Given the tool's simplicity (no parameters, no output schema), the description covers the essential return fields and a max limit. It could add context about whether the list includes all maps or filtered, but it's largely complete for a straightforward list operation.

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?

With 0 parameters, schema coverage is 100%, so baseline is 4. The description reinforces that no parameters are needed ('无需参数'), adding clarity. No additional parameter meaning is required.

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

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

The description clearly states the tool returns a list of maps with code, name, and building. The verb '获取' (get) and resource '地图列表' (map list) are specific, distinguishing it from other list tools like list_areas or list_tags, though it lacks explicit differentiation. Overall purpose is clear and unambiguous.

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

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

The description mentions no parameters and a 2000-record limit, but provides no guidance on when to use this tool versus alternatives like list_areas, list_tags, etc. No explicit context on prerequisites or scenarios, leaving the agent to infer usage without support.

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

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

Annotations already mark the tool as readOnly and idempotent, covering safety. The description adds value by specifying the return format (pagination, fields like name, department, phone, binding tags) and the behavior of filters, which is beyond what annotations provide.

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

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

The description is fairly concise and front-loaded with the purpose. It uses structure (paragraphs, bullet-like list) but includes an emoji that slightly reduces formality. Every sentence adds value, though it redundantly repeats schema info.

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

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

For a simple list tool with no output schema, the description is complete: it clearly states the purpose, all optional parameters with explanations, default values, return format, and a usage hint. No additional context is needed for an agent to invoke it correctly.

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

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

Input schema coverage is 100%, so the baseline is 3. The description repeats parameter descriptions and defaults already present in the schema, adding no new semantic information. The hint about keyword is useful but already implied by the schema description.

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

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

The description clearly states it retrieves a personnel list with optional filters by department or keyword. However, it does not differentiate from the sibling 'search_personnel' tool, which may serve a similar purpose, reducing clarity for an agent deciding between the two.

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 lists parameters and provides a hint about using the keyword for fuzzy search, but it does not explicitly state when to use this tool versus alternatives like 'search_personnel' or when not to use it. Usage context is implied but not explicitly guided.

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

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

注释已提供readOnlyHint、idempotentHint和destructiveHint。描述额外揭示了API端过滤和30秒缓存，提供了超越注释的行为上下文。未发现矛盾。

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

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

描述简洁，包含表情和明确的参数、返回、提示部分。每个句子都有价值，结构合理。

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

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

鉴于只有一个参数、无输出模式、注释充分，描述提供了目的、参数、返回和缓存行为，足够完整。兄弟工具数量较多但未造成混淆。

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

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

输入模式已覆盖100%的参数字段，描述对参数仅重复了示例，未增加超出模式的额外语义。基线为3。

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

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

描述明确使用动词"获取"和资源"实时位置快照"，并指定是给定地图上的所有标签。与兄弟工具如list_tags（仅列出标签）、get_tag_location（单一标签位置）区分清晰。

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

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

描述了必要的参数mapCode，并提示了过滤和缓存行为，但没有明确说明何时使用此工具与替代方案（如get_tag_location或list_tags），也没有排除条件。

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

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

Annotations declare readOnlyHint, idempotentHint, and destructiveHint. The description adds that returning all maps if mapId is omitted, and that response is a paginated list with fields like code, type, status, battery, and binding status. This provides useful context beyond the annotations.

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

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

The description is a short paragraph plus an indented parameter list, which is efficient. It front-loads the purpose and then provides details. However, the parameter list partially duplicates the schema, making it slightly 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?

Despite no output schema, the description specifies that the return is a paginated list with specific fields. It covers all 4 optional parameters and provides usage hints. Given the tool's simplicity, the description is complete and sufficient for an agent.

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

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

Schema coverage is 100%, so the schema already describes all parameters. The description reiterates defaults and filter values but adds little new meaning. According to rules, baseline is 3 when schema coverage is high.

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

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

The description clearly states the verb '获取' (get) and resource '定位标签列表' (list of location tags), with optional filtering by map and type. It distinguishes from siblings like get_tag_location and list_personnel by focusing on listing tags.

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

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

The description provides explicit context: '使用 tagType 和 mapId 缩小范围。适合巡检和批量查看。' (Use tagType and mapId to narrow down. Suitable for inspection and batch viewing.) It explains parameter usage but does not explicitly state when not to use the tool or list 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?

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds key behavioral details: partial updates ('只更新提供的字段'), maximum batch size (500), return value (success count), and the two-step confirmation mechanism via the 'confirm' parameter. No contradictions.

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

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

The description is well-structured with a purpose header, bulleted parameter list, and a tip. It is slightly verbose with emoji, but every sentence adds value. There is some redundancy with schema descriptions, but it remains clear and easy to parse.

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

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

Given the tool's complexity (batch update with nested array), the description covers the return value, partial update behavior, and maximum items. It does not explain error handling or partial-failure scenarios, but for a typical batch update, this is acceptable.

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%, baseline 3. The description adds value by restating parameter meanings in natural language, clarifying the confirm constant, status enum, and the partial-update semantics. It also explains the required 'code' field within each anchor object.

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 '批量更新基站信息' (batch update anchor information) using a specific verb ('batch_update') and resource ('anchors'), distinguishing it from sibling tools like pls_create_anchor, pls_update_anchor, and pls_delete_anchor.

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

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

The description implies usage for batch updating anchor fields (status, IP, model) but does not explicitly state when to prefer this over single-update tools (pls_update_anchor) or provide when-not-to-use guidance. No alternatives are mentioned.

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

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

Annotations already indicate destructiveHint=true, so the description adds value by detailing partial update semantics and the confirm requirement. It also mentions the return value (count of updated tags). No contradictions with annotations.

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

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

The description is well-structured: brief intro, parameter details, return value, and a hint. It uses emojis for visual grouping but is not overly verbose. Could be slightly more concise without the emoji, but overall front-loaded and clear.

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

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

Given no output schema and only 2 parameters, the description covers all needed information: purpose, parameters with constraints, return value, and usage hints. No gaps for an AI agent to invoke correctly.

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

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

Schema coverage is 100%, but the description adds meaning: it explains the confirm constant value ('确认'), lists the optional fields with status enum (0/1), and clarifies the partial update behavior. This helps beyond the raw schema.

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

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

The description clearly states '批量更新标签信息' (batch update tag information) with specific fields (battery, status). Among siblings, it stands out from pls_create_tag, pls_delete_tag, and especially pls_update_tag (single update). The verb 'batch update' and resource 'tags' are explicit.

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

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

The description provides usage guidance: partial update behavior ('只更新提供的字段') and batch size limit (最多支持 500 条). It also specifies a required confirm parameter for safety. However, it does not explicitly contrast with the single-update tool pls_update_tag, leaving the use case partially implied.

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

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

Annotations declare destructiveHint=true and readOnlyHint=false; description adds the confirmation requirement but does not elaborate on side effects like overwriting existing bindings.

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?

Structured with emoji, parameter list, and notes; concise but includes redundant return statement.

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?

Lacks explanation of return values beyond 'operation result', and omits error conditions or prerequisites; incomplete for a destructive operation.

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%; description repeats parameter names and adds brief Chinese explanations, but does not provide new semantic value beyond the schema.

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

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

The description clearly states the tool binds a tag to a car, distinguishing it from sibling tools for binding to persons or goods.

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 on when to use this tool vs. alternatives like pls_bind_tag_to_person; lacks context about prerequisites or scenarios.

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

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

Annotations already indicate destructiveHint=true and idempotentHint=false, signaling a mutation. The description adds the requirement for the 'confirm' parameter as a safety step. However, it does not disclose whether existing bindings are overwritten or any other side effects, leaving some behavioral uncertainty.

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

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

The description is concise and well-structured with clear parameter list and notes. It uses minimal text to convey the core functionality, though some formatting (emojis) is present but not detrimental.

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

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

The description states '返回: 操作结果' (return: operation result) without detailing the exact return format, error conditions, or preconditions (e.g., whether the tag or entity must exist). Given no output schema and a mutation tool, more context is needed for safe use.

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

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

Input schema covers 100% of parameters with clear descriptions (tagId, entityId, confirm). The description repeats the parameter list and emphasizes the confirm constraint, but adds no new semantic information beyond what the schema provides. Baseline of 3 is appropriate.

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

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

The description clearly states '将标签绑定到物品/货物' (bind tag to item/goods) with a specific verb and resource. The tool name also explicitly includes 'goods', distinguishing it from sibling bind tools for persons and cars.

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

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

The description provides a hint to '确认绑定关系后再执行' (confirm binding before execution) but lacks explicit guidance on when to use this tool versus alternatives like pls_bind_tag_to_person or pls_bind_tag_to_car. The differentiation relies on the tool name rather than explicit instructions.

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

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the description adds context about the required confirm parameter as a safety measure. However, it does not disclose what happens if the tag is already bound or other behavioral details, making it adequate but not enhanced.

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

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

The description is structured with Chinese formatting and covers purpose, parameters, return, hints, and notes. It is somewhat verbose but all sentences contribute value; no unnecessary content.

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

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

The description covers parameters, required confirm, and return value. However, it lacks details about conditions (e.g., tag must be unbound, behavior on existing binding) and does not provide additional context beyond basic usage, making it minimally complete for a binding tool.

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

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

Schema coverage is 100%, and the description repeats the parameter requirements (confirm must be '确认', entityId is person ID, tagId is tag ID) without adding new meaning beyond the schema. Baseline of 3 is appropriate.

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

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

The description states '将标签绑定到人员' (bind tag to person), which is a specific verb-resource combination. It clearly distinguishes from sibling tools like pls_unbind_tag_from_person and pls_bind_tag_to_car, which have different resources.

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

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

The description provides a note to confirm the binding before execution and emphasizes that the confirm parameter must be '确认'. While it does not explicitly mention when to use vs alternatives, the context of binding vs unbinding is implied, and the safety guidance is clear.

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

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

The description adds the confirmation requirement ('confirm: 二次确认（必填）') beyond annotations, but does not disclose side effects, permissions, or rate limits. Annotations indicate a non-read, non-destructive write operation, which aligns.

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 three well-structured sentences plus a hint line, with no extraneous content. It front-loads the purpose and parameter notes, but the emoji and formatting could be streamlined.

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?

While the return structure is described, the description lacks information on error scenarios, idempotency (annotations say false), and the exact fields required beyond confirm. For a 6-parameter create tool, more context would help.

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

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

Schema coverage is 100%, so parameters are already documented. The description adds vague guidance ('根据实体类型传入对应字段') and repeats confirm details, without clarifying which fields are actually needed for creation.

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 title and first sentence '【🔧 管理】创建告警规则实体' clearly state the verb (创建) and resource (告警规则实体), distinguishing it from sibling tools like pls_update_alarm_rule and pls_delete_alarm_rule.

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

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

The description provides no explicit guidance on when to use this tool versus alternatives. It hints at '只传必填字段' but does not mention prerequisites, nor does it differentiate from update/delete operations.

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

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

The annotations indicate a write operation (readOnlyHint=false) and non-destructive (destructiveHint=false). The description adds that a confirmation parameter is required and specifies the return format ({success, entity, action}). This confirms the write behavior but does not disclose additional traits beyond the annotations.

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

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

The description is relatively short but includes a redundant parameter list that duplicates schema information. The key action is stated upfront, and the tip is concise. Some redundancy exists, but overall it is efficiently structured.

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

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

With no output schema, the description compensates by stating the return format. However, for a creation tool with 8 parameters, it lacks information about required relationships (e.g., mapId may be needed) and whether coordinates are necessary. The tip 'only pass required fields' could be misleading since only confirm is required. Completeness is adequate but not comprehensive.

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

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

The input schema has 100% coverage with descriptions for all 8 parameters. The description does not add significant new information beyond the schema; it repeats the confirmation requirement and suggests only passing required fields. The baseline of 3 is warranted as the schema carries the 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 '创建基站实体' (create anchor entity), which is a specific verb and resource. It distinguishes this tool from sibling tools like pls_update_anchor and pls_delete_anchor by the create action. However, it does not elaborate on what an anchor is, but the tool name is self-explanatory.

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 offers a tip '确认+只传必填字段' (confirm + only pass required fields), which gives basic guidance. However, it lacks explicit context on when to use this tool versus alternatives like pls_update_anchor or pls_delete_anchor, and does not mention prerequisites or scenarios.

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?

Describes the confirmation requirement and return format, but lacks details on side effects, idempotency, or error conditions beyond what annotations weakly hint at.

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?

Short and structured with sections, but the hint '只传必填字段' may be redundant given the schema.

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?

Covers creation purpose and return, but doesn't clarify which fields are actually required (only confirm per schema) or explain id generation for creation.

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

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

Schema coverage is 100%, so parameters are already documented; the description adds little new meaning except reiterating the confirm requirement.

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

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

The description clearly states it creates area entities, distinguishing it from sibling creation tools for tags, persons, etc.

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 on when to use this tool vs alternatives like pls_update_area or pls_delete_area, nor any prerequisites or context.

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

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

The annotations already indicate this is a write operation (readOnlyHint=false). The description adds the requirement for double confirmation via the confirm parameter and outlines the return format. It does not contradict annotations. However, it omits details like whether the operation is idempotent (already indicated false) or what side effects occur.

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

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

The description is relatively short but includes unnecessary line breaks and formatting. It conveys core information but could be more structured (e.g., bullet points for parameters). It is not overly verbose, but clarity could be improved.

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 create tool with seven parameters, the description lacks completeness. It does not specify which parameters are mandatory for creation (besides confirm), nor does it explain the 'entity type' concept. The return format is simple, but without output schema, more detail on success/error handling would be helpful. The description feels insufficient for an agent to reliably invoke the tool.

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

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

Schema coverage is 100%, so the description adds minimal value beyond what the schema already provides. It only highlights the confirm parameter and vaguely mentions that fields depend on entity type. The baseline score of 3 is appropriate as the description does not significantly enhance parameter understanding.

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

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

The description explicitly states '创建区域规则实体' (create area rule entity), providing a clear verb and resource. The tool name itself is descriptive, and the wrench icon suggests a management action. However, it does not differentiate from sibling tools like pls_update_area_rule or pls_delete_area_rule, though the name makes the purpose unambiguous.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention conditions for creation, prerequisites, or scenarios where update or delete would be more appropriate. The hint about only passing required fields is minimal and does not address usage context.

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

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

Annotations already indicate this is a write operation (readOnlyHint=false). The description adds the need for a confirmation parameter and mentions the return format. However, it does not disclose permissions, side effects, or behavior beyond what is already in the schema. With annotations covering the basic safety profile, a score of 3 is appropriate.

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

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

The description is brief, consisting of a header, parameter note, return format, and a hint. It is front-loaded with the purpose. However, the hint and return format could be better integrated, but overall it is efficient and clear.

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

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

Given the complexity (5 parameters, no output schema), the description is minimal. It does not explain how to use the parameters to create a building, nor does it leverage the openWorldHint annotation. The return structure is vaguely defined. In the context of many siblings, no differentiation is provided, leaving the agent underinformed.

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

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

The input schema has 100% parameter description coverage. The description adds a useful hint about only passing required fields ('确认+只传必填字段') and notes that confirm is mandatory. This provides guidance beyond the schema alone, justifying a score above 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 clearly states the tool's purpose: '创建楼栋实体' (create building entity). The tool name matches, and it avoids tautology. However, it does not distinguish from sibling create tools like pls_create_tag or pls_create_person, so a perfect score is not warranted.

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

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

The description includes a vague hint ('确认+只传必填字段') but provides no explicit guidance on when to use this tool versus alternatives. There are many sibling create tools, and no comparison or context is given. The agent receives no help in choosing this tool over others.

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

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

Annotations indicate readOnlyHint=false (write operation) and destructiveHint=false. The description adds behavioral context by specifying the return format ({success, entity, action}) and the mandatory confirm parameter for write operations. It does not disclose idempotency or side effects beyond the annotation hints.

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

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

The description is concise, using a single sentence, a list, and a tip. It front-loads the emoji and title, making it scannable. However, the phrase '可根据实体类型传入对应字段' is slightly vague but doesn't add undue verbosity.

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

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

For a create tool with no output schema, the description covers the confirm constraint and return format. With 10% schema coverage (actually 100% - note: signal shows 100% coverage, so params are well-documented), the description complements the schema. It provides enough context for the agent to invoke the tool correctly, though it could mention validation behavior.

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

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

Schema coverage is 100%, so the baseline is 3. The description mentions the confirm parameter and hints at passing fields based on entity type, but it does not add meaningful semantic details beyond what the schema already provides (e.g., carType enum values, hasWeightDevice meaning).

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

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

The description states the tool creates car entities, with an emoji and title indicating management. It clearly distinguishes from other CRUD tools like pls_update_car and pls_delete_car. However, it could be more explicit about the car-specific fields being passed, as it uses the generic phrase '根据实体类型传入对应字段'.

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

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

The description provides some usage guidance: it emphasizes the confirm parameter requirement and advises only passing required fields. However, it does not explicitly state when to use this tool vs. other car-related tools (e.g., update, delete) or exclude any scenarios. This is adequate but lacks explicit context.

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

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

Annotations already indicate readOnlyHint=false and destructiveHint=false. Description does not add significant behavioral context beyond what is in the schema (e.g., confirm requirement). No contradiction.

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

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

Concise, front-loads action, but repeats parameter list already in schema. Overall efficient.

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

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

Return format is partially described but vague. No output schema. With openWorldHint=true, more detail on entity type handling would be beneficial.

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 100% with descriptions for all properties. Description adds the vague note '根据实体类型传入对应字段' which does not clarify what entity type means. Baseline 3 is appropriate.

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

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

The description '【🔧 管理】创建物品实体' clearly states the action (create) and resource (goods entity). Distinguishes from sibling tools like pls_update_goods and pls_delete_goods.

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

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

Provides guidance: confirm field required with value '确认', and hints to only pass required fields. Does not explicitly compare to alternatives but implies usage for creation.

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

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

Annotations provide readOnlyHint=false and destructiveHint=false, so description must disclose write behavior. It does so by requiring a confirmation parameter ('confirm'='确认') and specifying the return format (success flag, entity name, action type). This adds value beyond annotations.

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

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

The description is short and front-loaded with the purpose. The inclusion of an emoji and formatting is acceptable. The ambiguous phrase '根据实体类型传入对应字段' slightly detracts from clarity, but overall it is concise.

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

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

The description lacks completeness for a create tool with 5 parameters. It does not explain whether the optional 'id' parameter is used for creation (it is likely auto-generated). The output schema is missing, but the return format is described. The vague entity type comment leaves gaps.

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

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

Schema description coverage is 100%, so each parameter is already documented. The description adds no new semantic information beyond repeating the confirmation requirement. The vague statement about entity types does not improve understanding.

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

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

The description states '创建地图实体' (create map entity), which clearly identifies the action and resource. It distinguishes from sibling CRUD tools for other entities. However, the phrase '根据实体类型传入对应字段' is vague and somewhat confuses the purpose.

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

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

The description provides no guidance on when to use this tool versus alternatives like pls_update_map or pls_delete_map. It only mentions a tip about required fields, but no contextual usage advice.

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

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

Annotations already indicate non-read-only, non-idempotent, non-destructive. The description adds the requirement for secondary confirmation via confirm parameter and specifies return format, which goes beyond annotations. However, it doesn't discuss idempotency or duplicate creation behavior.

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

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

The description is concise with a header, parameter summary, return format, and tip. It uses few words, but the parameter list is somewhat redundant with the schema. Still, it is efficient and front-loaded.

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

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

The tool has 7 parameters and no output schema. The description covers the confirm requirement and basic structure, but lacks context on prerequisites like permissions, entity existence handling, or failure modes. It is adequate but not fully comprehensive.

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

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

Schema coverage is 100% with detailed descriptions for all 7 parameters. The description reiterates the confirm requirement and mentions passing fields based on entity type, but adds no new meaning beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly states '创建人员实体' (create person entity) with a specific verb and resource. It implicitly distinguishes from sibling tools like pls_update_person and pls_delete_person.

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

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

The description includes a tip to only pass required fields and mentions the confirm parameter, but lacks explicit guidance on when to use this tool vs. similar CRUD siblings (e.g., update vs. create). No alternatives or exclusions are provided.

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

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

Annotations indicate a write operation (readOnlyHint=false) and potential side effects (openWorldHint=true), but the description adds no additional context. It does not disclose authentication requirements, reversibility, or consequences of incorrect usage beyond repeating the confirm requirement already in the schema.

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

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

The description is short but includes the purpose, parameter list, return format, and a hint. It is front-loaded with the purpose and avoids unnecessary details. Some formatting (emoji, line breaks) is acceptable but not ideal.

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 10 parameters and no output schema, the description lacks sufficient detail. It does not explain what constitutes a 'tag entity', which fields are required for creation vs. update, or provide examples. The vague instruction '根据实体类型传入对应字段' does not sufficiently guide the agent.

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

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

Schema coverage is 100%, so the base is 3. The description only highlights the confirm parameter and says '根据实体类型传入对应字段' (pass corresponding fields based on entity type), which adds minimal value beyond what the schema already provides.

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

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

The description clearly states '创建标签实体' (create tag entity), using a specific verb and resource. It distinguishes from sibling tools like update, delete, and list, making the purpose unambiguous.

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

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

The description provides no guidance on when to use this tool versus alternatives (e.g., pls_update_tag, pls_delete_tag). There is no mention of prerequisites, conditions, or exclusion criteria. The hint '确认+只传必填字段' is operational, not comparative.

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

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

Annotations already indicate destructiveHint: true, so the description's warning '删除不可撤销！' adds emphasis but not new information. The return structure is provided. No side effects or error behaviors are disclosed. Overall, minimal added value beyond annotations.

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

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

The description is relatively short and front-loaded with the purpose. The emoji and formatting may be seen as clutter, but it's still concise. The vague '根据实体类型传入对应字段' could be removed for 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?

For a destructive action with 7 parameters and no output schema, the description provides the return format and an irreversibility warning. However, it lacks details on error handling, permissions, and what happens to related data. The annotations help, but completeness is adequate but not thorough.

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

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

Schema coverage is 100%, so the schema fully documents all 7 parameters. The description only highlights 'confirm' and 'ids' as required, and vaguely mentions '根据实体类型传入对应字段'. Since the schema already provides descriptions, the description adds marginal semantic value.

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

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

The description clearly states it deletes alarm rule entities. The verb '删除' and resource '告警规则实体' are specific. However, the line '根据实体类型传入对应字段' suggests broader applicability, which may confuse. The tool name reinforces specificity, so it's mostly clear.

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 other delete tools (e.g., pls_delete_tag, pls_delete_person). There is no mention of prerequisites, context, or alternatives. The description assumes the agent already knows when to call it.

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

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

The description adds behavioral context beyond the destructiveHint annotation by stating '删除不可撤销！' (deletion is irreversible) and requiring a confirmation parameter. This provides helpful safety awareness without contradicting annotations.

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

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

The description is concise and front-loaded with the main purpose. Every sentence adds value: purpose, required parameters, return format, and a warning. No redundant or filler 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?

For a delete tool with no output schema, the description covers essential aspects: action, required inputs, return format, and destructiveness. It does not detail error handling or edge cases but is adequate for a straightforward operation.

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?

With 100% schema coverage, the schema already documents all parameters. The description reiterates the confirm constraint and ids requirement but adds limited additional meaning. The vague note about '根据实体类型传入对应字段' adds some context but remains unclear.

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

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

The description explicitly states '删除基站实体' (delete base station entity), clearly identifying the action and resource. The tool name aligns with this purpose, and it distinguishes itself from sibling delete tools like pls_delete_tag or pls_delete_person.

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

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

The description implies usage for deleting base stations but provides no explicit guidance on when to use this tool versus alternatives. There is no mention of prerequisites, conditions, or when not to use it.

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

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

Description adds '删除不可撤销！' (deletion irreversible) and explains confirm parameter for safety, beyond annotations which already mark as destructive and not read-only.

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

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

Description is concise with bullet points, but the line '根据实体类型传入对应字段' is vague and could be more specific.

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?

Covers purpose, confirm, ids, return format, and warning. However, it doesn't specify which fields correspond to entity types, leaving some ambiguity for a destructive operation without output schema.

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

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

Schema coverage is 100%, so description adds limited value. However, it does clarify confirm must be '确认' and hints at entity-type-specific fields, but the hint is vague.

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

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

Description explicitly states '删除区域实体' (delete area entity), with clear verb and resource. It distinguishes from siblings like pls_create_area and pls_update_area.

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

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

No explicit when-to-use or when-not-to-use guidance. While deletion is distinct from siblings, prerequisites (e.g., entity not in use) are not mentioned.

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

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

Annotations already indicate destructiveHint=true and readOnlyHint=false. Description adds crucial context: '删除不可撤销！' (deletion irreversible) and the confirm parameter as a safety mechanism, along with return format. No contradiction.

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

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

Description is concise and front-loaded with purpose. Parameter list is bullet-style but clear. Could be slightly more streamlined, but overall efficient.

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

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

For a delete tool with full schema coverage and annotations, description covers purpose, required params, return format, and irreversibility. No output schema exists, so return format is described. No mention of relationship with other area rule tools, but not essential for a delete operation.

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

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

Schema coverage is 100%, so baseline is 3. The description repeats parameter info from schema (e.g., confirm must be '确认', ids list) without adding new meaning beyond what schema provides.

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

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

The title and description explicitly state '删除区域规则实体' (delete area rule entity), clearly identifying the action and resource. It distinguishes itself from sibling delete tools by specifying 'area rule'.

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?

Description explains required parameters (confirm, ids) and that deletion is irreversible, but does not provide explicit when-to-use or when-not-to-use guidance compared to alternatives. The context is clear for its specific use case.

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

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

Annotations already declare destructiveHint=true. The description adds that deletion is irreversible and requires a confirmation parameter, reinforcing the destructive nature. However, it doesn't mention side effects on related entities or error conditions.

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?

Concise, well-structured with emoji, clear sections for purpose, parameters, return, and tip. Every sentence adds value; no redundancy.

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

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

Moderate completeness: the return format is described, but error handling, relationship between 'id' and 'ids' parameters (both in schema but only 'ids' mentioned), and clarification of vague note are missing. No output schema exists, so description could do more.

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

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

Schema coverage is 100%, so baseline is 3. The description lists confirm and ids but also adds a vague note about passing fields according to entity type. It does not significantly enhance understanding beyond the schema's existing parameter descriptions.

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

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

The description clearly states the tool deletes a building entity ('删除楼栋实体'), with specific verb+resource. It distinguishes from other pls_delete_* tools by naming 'building', but lacks explicit differentiation beyond entity type.

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 on when to use this tool versus alternatives (e.g., other delete tools). No prerequisites, context, or scenarios provided. Only a warning about irreversibility, which is cautionary but not usage advice.

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

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

Annotations already indicate destructiveness (destructiveHint=true), but the description adds value with '删除不可撤销！' and the requirement for a confirmation parameter. It also discloses the return format, going beyond the structured fields.

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

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

The description is compact and well-structured: header, parameter list, return format, hint. Every sentence serves a purpose, though the entity-type note is slightly ambiguous. Overall, it's efficient.

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

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

Given the tool's complexity (9 parameters, no output schema, annotations present), the description covers purpose, required confirmation, return format, and irreversibility. It could mention that the confirm parameter must match exactly, but the schema covers that.

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

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

Schema coverage is 100%, so baseline is 3. The description adds the return format and specifies that confirm must be '确认', which is already in schema. The line '根据实体类型传入对应字段' is somewhat redundant and vague, providing minimal additional meaning.

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

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

The description clearly states '删除车辆实体' (delete car entity), providing a specific verb and resource. It effectively distinguishes from sibling CRUD tools like pls_create_car and pls_update_car.

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

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

The description implies usage for deleting a car but does not provide explicit guidance on when to use this tool versus other delete tools (e.g., pls_delete_person, pls_delete_goods). There are no exclusions or alternative suggestions.

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

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

Annotations already indicate the tool is destructive and not read-only. The description adds that a confirmation string '确认' is required and stresses that deletion cannot be undone, which provides useful behavioral context beyond the annotations.

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

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

The description is relatively concise, with bullet points for parameters and a clear return format. The inclusion of the vague phrase '根据实体类型传入对应字段' slightly detracts but overall it is well-structured and front-loaded.

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

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

Given no output schema, the description provides a return format which is helpful. However, it does not mention the 'id' parameter from the schema, and the entity-specific fields hint is under-specified. This leaves gaps in completeness for a deletion tool with multiple parameters.

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

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

The schema covers all parameters, but the description explains the 'confirm' parameter must be '确认' and lists 'ids' as required. However, the hint about entity-specific fields is unclear and not reflected in the schema, which may mislead. Overall, adds some meaning but introduces ambiguity.

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 deletes item entities (删除物品实体). It also includes a warning that deletion is irreversible, which adds clarity. However, the vague mention of '根据实体类型传入对应字段' could cause confusion.

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

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

The description provides no guidance on when to use this tool versus alternatives like pls_create_goods or other delete tools. There is no mention of prerequisites or conditions for use.

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

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

The description adds value beyond annotations by stating that deletion is irreversible ('删除不可撤销') and by requiring a confirmation parameter ('confirm') that must be set to '确认'. This alerts the agent to the destructive nature and additional safety step. No contradiction with annotations (destructiveHint=true, readOnlyHint=false).

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

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

The description is concise and front-loaded with an emoji and label. It covers key points in four lines. However, it could be more structured (e.g., separate sections for usage and behavior).

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

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

Given the rich schema and annotations, the description is adequate but lacks context on when to use this tool vs similar sibling tools. It does not explain what constitutes a 'map entity' or how to determine the entity type for additional fields. The return format is provided, which is helpful since there is no output schema.

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

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

Schema coverage is 100%, so baseline is 3. The description adds the return format '{success: true/false, entity: 实体名称, action: 操作类型}' which is not in the schema. It also highlights required parameters (confirm, ids). The vague instruction '根据实体类型传入对应字段' could be improved but does add some context about additional fields.

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

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

The description clearly states it deletes a map entity, which matches the tool name and distinguishes it from sibling delete tools for other entities. However, the phrase '地图实体' could be more specific, and the mention of '根据实体类型传入对应字段' introduces slight ambiguity about whether this tool handles types other than maps.

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 like pls_delete_area or pls_delete_tag. There are no prerequisites, exclusions, or context cues to help an agent decide when to invoke this tool.

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

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

Annotations already indicate destructiveHint=true. The description adds value by stating '删除不可撤销' (deletion irreversible) and emphasizing the confirm parameter, which clarifies the need for explicit confirmation. However, it does not disclose potential side effects like cascade deletions or permission requirements.

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

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

The description is moderately concise but includes decorative elements like emojis and brackets (e.g., 【🔧 管理】) that add noise. The parameter list is clear, but the structure could be improved by removing unnecessary formatting. It earns a middle score due to being somewhat efficient but not optimally structured.

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

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

Given the destructive nature (confirm parameter, irreversible) and 8 parameters, the description lacks details on return values (only mentions success/false with entity and action) and error handling. No prerequisites or authorization info is provided. The tool could be better contextualized for an agent to use reliably.

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

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

The input schema has 100% description coverage for parameters. The description reiterates key parameters (confirm, ids) but adds minimal new semantic information beyond '根据实体类型传入对应字段' (pass corresponding fields based on entity type). Baseline 3 is appropriate as schema already explains parameters well.

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

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

The description explicitly states '删除人员实体' (delete person entity), which clearly identifies the action and resource. The tool name also indicates deletion of a person. Among sibling tools, there are many delete operations, but the description differentiates by specifying 'person' entity.

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 provide when to use this tool versus alternative deletion tools like pls_delete_tag or pls_delete_car. No guidance on prerequisites or contraindications is given. The only contextual hint is the confirm parameter requirement, which is a compliance measure rather than usage context.

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

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

The description discloses that the operation is destructive and irreversible (删除不可撤销), which aligns with the destructiveHint annotation. It also explains the return value format and the need for a confirmation parameter, adding context beyond the annotations.

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

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

The description is concise, using a structured bullet-point format that clearly delineates parameters, return value, and warning. Every sentence adds value without redundancy.

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

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

Given the rich input schema, annotations, and lack of output schema, the description covers all essential aspects: what the tool does, required confirmation, return format, and the irreversible nature. It is complete for effective tool selection and invocation.

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

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

Schema coverage is 100%, so the schema already documents all parameters. The description adds minimal extra meaning, such as the requirement for 'confirm' and the hint about passing fields based on entity type. This is adequate but not exceptional.

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

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

The description clearly states the verb 'delete' and the resource 'tag entity' (删除标签实体), distinguishing it from sibling delete tools for other entities like persons, cars, etc.

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

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

The description provides clear prerequisites: the 'confirm' parameter must be set to '确认'. It also warns that deletion is irreversible, guiding the agent to use caution. However, it does not explicitly state when not to use this tool or compare it to 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?

The description adds value beyond annotations by detailing the specific components checked and the return format (status per component, service info, runtime). No contradiction with annotations (readOnly, idempotent, non-destructive).

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