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

With no annotations, the description carries the behavioral burden and does disclose the key behaviors: fuzzy matching, cross-snapshot scope, and the returned fields (book_id and bibliographic info). It does not mention ordering, pagination, or potential cost of scanning all snapshots, but these are secondary for a simple lookup tool.

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

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

A single sentence packs the verb, resource, scope, matching mode, and result. There is no filler or redundancy; the important operational details are 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 a simple two-parameter search with no output schema and no annotations, the description adequately states what the tool does and returns. It could be more explicit about result ordering or the structure of '书目信息', but nothing essential for invoking it correctly is missing.

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

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

Schema coverage is 100%: both query ('书名或作者关键词') and limit ('返回条数') are already described in the input schema. The description only restates the query concept and adds no new parameter-level meaning, so the baseline of 3 applies.

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

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

The description states a concrete action ('跨全部快照按书名/作者模糊查找') with the resource and matching mode, and identifies the returned payload (book_id and bibliographic info). This clearly distinguishes it from the sibling tools, which are rankings/stats/trend tools rather than title/author lookup.

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 phrase '按书名/作者模糊查找' provides a clear usage context: use this tool when the agent has a book title or author keyword and needs to locate a book across snapshots. It does not explicitly name alternative sibling tools or say when not to use it, so it stops short of a 5.

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

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

No annotations are provided, so the description carries the full burden. It does disclose a key behavioral trait: results are sorted by total reads ('按在读总量排序') and reflect current conditions ('当前'). However, it does not explain response shape, aggregation granularity, or how the 'new' rank differs, leaving meaningful gaps.

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 entire description is one compact, information-dense sentence. It front-loads the core purpose and the most important sorting behavior without filler or redundancy.

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

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

With three optional parameters, no output schema, and no annotations, the description should explain how to control top N, ranking mode, and channel. It does not, leaving the agent without enough information to use the tool beyond its defaults.

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 0%, and the description only indirectly references the 'read' ranking mode via '按在读总量排序'. The 'top', 'rank', and 'channel' parameters and their enums are not explained, so an agent cannot confidently know how to set them for different needs.

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 aggregates genre heat and identifies currently popular categories ('题材热度聚合', '识别当前吸量赛道'), with a specific sorting criterion. It does not explicitly name or contrast sibling tools, but the genre-heat focus is sufficiently distinct from generic ranks, trends, and hotwords.

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 phrase '识别当前吸量赛道' gives clear context: use this tool to see which genres are attracting reads right now. It does not state when not to use it or name alternatives, but the intended use case is reasonably explicit.

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

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

There are no annotations, so the description carries the full behavioral burden. It does disclose that the tool uses a '套路词表' and performs frequency statistics, which is useful. Yet it omits details about return values, aggregation behavior, or any side effects, leaving important behavior unexplained.

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 compact single sentence with no filler. It front-loads the core function and then adds a usage-oriented summary, making it easy to scan; every part contributes meaning.

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

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

For a tool with no annotations, no output schema, and three undocumented parameters, this description is incomplete. An agent would still be guessing what 'rank' values mean, how 'top' behaves, and whether results differ across channels, so the definition is not sufficient for correct invocation.

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

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

Schema description coverage is 0%, and the description does not explain any of the three parameters: 'top', 'rank', or 'channel'. The enum values like 'read' and 'new' are ambiguous without clarification, and the description does not compensate for the missing schema documentation.

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

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

The description clearly identifies the action ('频次统计' / frequency counting) and target resource ('书名热词' / hot words in book titles). It also specifies the basis ('基于套路词表'), making it fairly specific among sibling tools, though it does not explicitly differentiate itself from them.

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 phrase '快速看当前书名流行词' implies this tool is for quickly viewing currently popular book-title words, giving some usage context. However, it provides no explicit when-to-use or when-not-to-use guidance and does not mention any sibling 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?

With no annotations, the description carries the behavioral burden. It discloses that scores come from a six-dimension formula plus bonuses and explains the serial-mode formula ('连载体量×在读×更新活跃×吸量×套路×金手指'). However, it does not state whether output is sorted, what the score range or format is, or whether there are side effects, which is a notable gap for a tool with no annotations and no output schema.

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

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

Two dense sentences front-load the core purpose and then give the mode variant and intended use. Every sentence adds information, though the slash-separated jargon list ('套路密度/金手指清晰') makes the description slightly harder 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?

Moderate complexity with four optional parameters, no annotations, and no output schema requires more detail about the score breakdown, sorting, and how rank/channel map to the modes. The description explains the 'why' and scoring dimensions, but an agent would still be guessing about the return shape and the meaning of two 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?

Schema description coverage is 50%: top and serial have descriptions, while rank and channel are bare enums. The description adds meaning to serial mode and to the scoring dimensions, and implies female as the default by mentioning male serial mode as a switch, but it does not explain rank (read/new/completed) or channel (female/male). The description compensates partially but not fully.

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

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

The description names a concrete operation ('仿写选书六维评分') and identifies the resource ('在读爆款') and output ('给出每本的分数拆解'), so an agent can understand the purpose. It does not explicitly distinguish itself from sibling tools like fanqie_ranks or fanqie_trend, but the scoring focus is distinctive enough to avoid 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?

It states the intended scenario ('用于在读爆款里筛出最适合仿写的书') and provides a conditional mode switch ('也可切男频连载母本评分'), which gives usable context. It does not name alternatives or say when not to use this tool instead of fanqie_find or fanqie_stats.

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?

无 annotations，描述承担了行为披露责任。它明确列出返回字段（书名、作者、在读、状态、章节数、book_id），并主动说明'不含简介全文与版权图'，让代理知道不会得到哪些内容。若补充数据时效性说明会更完整。

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?

一句话同时包含动作、筛选维度、返回字段和明确排除项，信息密度高且没有冗余。关键信息前置，结构干净。

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?

对于只读榜单查询工具，描述列出的返回字段和排除项配合 100% 参数覆盖的 schema 已足够支撑正确调用。缺少兄弟工具的选择指引，但整体信息完整度良好。

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

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

输入 schema 对 4 个参数的描述覆盖率为 100%，每个参数的含义、默认值和枚举都有说明。描述文本本身没有额外补充参数格式或边界，因此按规则给予基线 3 分。

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

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

描述以'读取最新番茄榜单'明确了动作与资源，并列出可选的频道/榜型/品类维度，功能指向清晰。虽然没有明确对比兄弟工具，但'榜单'、'按频道/榜型/品类'的具体范围足以让代理区分于搜索、趋势、热度等兄弟工具。

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?

描述通过'最新番茄榜单'暗示了适用场景：需要获取榜单数据时使用。但没有明确说明何时不应使用、或与 fanqie_trend、fanqie_genre_heat 等兄弟工具的取舍，属于可用但未充分引导。

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

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

No annotations are provided, so the description carries the full burden. It does disclose the scope of the output (snapshot count, book_id coverage, detected directories), which is useful. However, it does not mention the return format, whether the operation is purely read-only, or any other behavioral traits such as scanning/probing implications.

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

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

The description is a single compact sentence that front-loads the category ('数据概览') and then lists the specific data points it covers. There is 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 zero-parameter, simple stats tool with no output schema, the description names the key pieces of returned information. It is adequate for an agent to understand what invoking this tool will provide, though it could be slightly stronger with an explicit statement of its read-only nature or output structure.

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 tool has zero parameters and the schema is empty, so parameter explanation is not needed. The description adds context about what the tool reports, which is sufficient given there is nothing for the caller to configure.

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

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

The description clearly identifies the tool as a data-overview/stats tool by naming specific metrics: snapshot count, total bibliography count, book_id coverage, and detected data directories. This aligns with the tool name 'fanqie_stats' and distinguishes it from ranking/find/trend siblings in substance, though it does not explicitly name or contrast them.

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

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

There is no guidance about when to choose this tool over the sibling tools such as fanqie_ranks, fanqie_find, or fanqie_trend. The description only implies an overview/statistics use case, with no explicit when-to-use, when-not-to-use, or alternative recommendations.

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

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

With no annotations provided, the description carries the burden of disclosing behavior. It does state the core behavior and the data prerequisite, and it lists the kind of differences computed. However, it does not explain what happens when fewer than two snapshots exist, whether the operation is read-only, or how results are structured.

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 short, dense sentences. The purpose and the key prerequisite are both front-loaded, and there is no filler or repetition of schema 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?

The description gives the high-level output categories and one prerequisite, but with no output schema and no annotations, it leaves open how results are formatted, how errors are surfaced, and how parameters map to the snapshot selection. Adequate for a simple diff tool, but not complete.

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

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

Schema description coverage is only 33%, and the description does not compensate. It never explains the meaning or role of 'top', 'rank', or 'channel' beyond the schema's sparse definitions, leaving two enum parameters with no added semantic guidance. The phrase '同一榜单' hints at snapshot identity but does not clarify how rank/channel select that snapshot.

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

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

The description uses a specific verb ('对比') and a clear resource ('同一榜单最新两份快照') and lists the concrete outputs: new entries, dropped entries, rank changes, read growth. It is clear and meaningful, though it does not explicitly name or contrast sibling tools like fanqie_ranks.

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

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

The description gives a clear context for use — comparing the latest two snapshots of the same ranking to detect trends — and explicitly states the precondition that at least two snapshots must exist under data/. It lacks explicit 'when not to use' or named alternatives, but the context is sufficient for an agent to decide.

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