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

With no annotations, the description carries the full burden. It indicates a read-only viewing action ('查看') and a legacy compatibility nature, which implies no side effects. Still, it does not disclose response format, whether the queue can be modified, or any operational details beyond availability.

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

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

The description is short and front-loaded with the core purpose, followed by bracketed availability metadata. The duplicated '可用性: 可用性:' is a minor typo, but the structure is otherwise efficient and each part contributes useful 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 zero-parameter, no-annotation view tool, the description covers the core purpose and availability. There is no output schema, and the description does not characterize the expected return data beyond naming the 'pending action queue,' leaving some ambiguity about what the agent will actually receive.

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 zero parameters, so there is no parameter documentation burden. The description does not need to explain parameter semantics; the baseline for zero-parameter tools is 4.

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

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

The description uses a specific verb, '查看' (view), and identifies a specific resource: the pending action queue left over from the old version. The phrase '兼容接口' (compatibility interface) helps distinguish it from current agent-run tools, though it does not explicitly name a sibling alternative.

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 some context: this is a compatibility tool for viewing legacy leftover pending actions, and it includes availability constraints for roles and platforms. However, it does not explicitly state when to prefer this tool over siblings, nor does it mention any exclusions or alternatives.

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

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

No annotations are provided, so the description carries the full behavioral disclosure burden. The word 查看 (view) implies a read-only operation, and the availability line gives access context. However, it does not disclose the return shape, pagination, ordering, or any side effects. This is minimal behavioral disclosure for a simple view 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?

The description is a single compact sentence that front-loads the compatibility context, which is good. However, it contains a redundant '可用性: 可用性:' duplication and a cluttered nested availability block. It is concise in length but not cleanly 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 zero parameters, no output schema, and no annotations, the description is minimally sufficient to identify what resource is being viewed. It does not explain what the queue view returns or how it relates to the approve/reject/pending siblings, leaving a modest but not severe gap for a zero-parameter read 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?

The input schema has zero parameters and schema description coverage is 100%, so there is no parameter ambiguity. With zero parameters, the baseline is 4; the description's availability constraints add useful context even though they are not parameter definitions.

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

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

The description states a specific verb and resource: 查看 (view) the 旧版本遗留的人工复核队列 (legacy manual review queue). It also identifies itself as a compatibility interface, which hints it is distinct from newer siblings, though it does not explicitly name them. This is clear but only weakly differentiates from sibling review-related tools.

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 explicit availability constraints (roles=candidate, recruiter; candidate_platforms=zhipin; recruiter_platforms=zhilian, zhipin), providing clear calling context. However, it does not state when to prefer this tool over alternatives like boss_agent_review_approve, boss_agent_review_reject, or boss_agent_pending, nor does it mention exclusions. The usage context is implied by the wording 'legacy manual review queue' rather than explicitly contrasted with siblings.

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

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

No annotations are present, so the description carries the full behavioral disclosure burden. It mentions writing to the pending queue, which implies a state change, but it does not explain idempotency, permissions, reversibility, side effects, or what the response contains.

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 front-loaded with the core action, but it contains a duplicated '可用性: 可用性:' typo and a trailing availability block that adds noise. It is not overly verbose, but the redundancy and formatting issues keep it from being well-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?

The tool is simple (one required parameter, no output schema), but the description leaves important context unexplained: what 'old-version review items' are, what the pending queue represents, what the invocation returns, and when this compatibility interface should be chosen. No annotations compensate for these 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?

The schema already documents the single `id` parameter with the description 'review item id', giving 100% schema coverage. The description does not add further meaning about the parameter, so the baseline score of 3 is appropriate.

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

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

The description states a specific action: process old-version review items and write them to the pending queue. This is clear enough to distinguish the tool from generic operations, and the name reinforces the approve/review-domain role. However, it does not explicitly contrast itself with sibling tools like boss_agent_review_reject.

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 about when to use this tool versus alternatives such as boss_agent_review or boss_agent_review_reject. The availability note restricts roles/platforms but does not explain the conditions under which an agent should call this specific approval/compatibility tool.

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

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

No annotations are provided, so the description carries the full burden. It does disclose a meaningful behavioral trait—that rejecting an old-version review item also records a skip event—which goes beyond the tool name. However, it does not describe permission requirements, reversibility, or the effect on the underlying review item, so transparency is partial.

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

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

The core sentence is compact and front-loaded with the primary action. However, the availability annotation contains a duplicated '可用性: 可用性:' prefix and the overall text mixes product label, behavior, and availability tags in a somewhat cluttered way.

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

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

For a simple two-parameter action with fully described schema parameters, the description gives usable availability context and the core effect. But with no annotations and no output schema, it still leaves the agent to infer broader results or side effects beyond the logged skip event.

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

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

Schema description coverage is 100%, so the schema already documents id as 'review item id' and reason as '拒绝原因'. The description adds no additional parameter context, which matches the baseline expectation when the schema fully covers 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 uses the specific verb '拒绝' (reject) with a concrete resource '旧版本复核项' (old-version review item) and adds the side effect '记录跳过事件' (record skip event). It clearly identifies what the tool does, and the '旧版本' qualifier hints at its role relative to approve/review siblings, though it does not explicitly name them.

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

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

There is no guidance on when to use this tool versus the adjacent siblings boss_agent_review_approve or boss_agent_review. The availability tag (roles/platforms) describes who can use it, not which situations call for rejection versus approval, leaving the agent to infer the routing.

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

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

With no annotations provided, the description carries the full burden of disclosing side effects and runtime behavior. It mentions '执行' (execution), implying real actions, but does not state what those actions are, whether they are irreversible, what systems may be affected, or what thresholds control. The dry_run parameter exists in the schema but the tool description itself does not explain the safety tradeoff beyond the structured 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 core description is a single concise sentence and is front-loaded with the primary purpose. However, it contains a duplicated '可用性: 可用性:' typo and interleaves availability metadata that would be better placed in annotations or structured fields, slightly reducing clarity and polish.

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

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

This is a complex automation tool that orchestrates scanning, decision-making, execution, and lead generation, yet there is no output schema or return-value description. The definition does not explain what the caller receives after the run completes, what 'threshold control' refers to, or how limit and dry_run affect the overall run. This leaves significant gaps for an agent deciding whether and how to invoke it.

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

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

Schema description coverage is 100%, so the two parameters are already documented with meaningful descriptions: limit controls session count, dry_run controls whether real platform actions are executed. The tool description itself does not add parameter-level detail, but per the rubric the 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 states a clear action ('运行一轮' — run one round) on a specific resource ('招聘自动化' — recruitment automation) and enumerates the pipeline stages: scanning, decision-making, threshold control, execution, and lead generation. It is generally distinguishable from sibling tools like boss_agent_stop and boss_agent_train, though it does not clearly differentiate itself from other 'run' siblings such as boss_watch_run.

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 only includes availability metadata for roles and platforms, which is a constraint rather than usage guidance. There is no mention of exclusions, prerequisites, or when a caller should choose a sibling tool instead.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. '查看' suggests a read-only operation, and the listed stat categories add some context, but there is no mention of output format, data freshness, permissions, side effects, or what exactly the circuit-breaker statistics represent.

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 and front-loads the core purpose before the availability note. The duplicated '可用性: 可用性:' is a minor formatting flaw, but the main content is efficiently expressed.

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 no-parameter stats viewer, the description captures the essential subject matter, but it lacks guidance on when to choose this tool over boss_stats and does not describe the shape or scope of the statistics returned. It is minimally viable but not fully complete.

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

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

The tool has zero parameters and the schema coverage is effectively 100%, so there is no parameter information the description needs to add. The baseline of 4 is appropriate for a parameter-free tool.

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

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

The description states a specific action and resource: it is for viewing execution, skip, history queue, and circuit-breaker statistics in recruitment automation. This is clear enough to identify the tool's function, though it does not explicitly differentiate it from the sibling tool boss_stats.

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 instead of alternatives such as boss_stats or the other boss_agent_* tools. It implies a stats-related use case but gives no exclusions, prerequisites, or routing cues.

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 burden. It does disclose the core mechanism and effect (turning on a circuit breaker to stop subsequent automatic execution). However, it omits whether a currently running execution is interrupted, whether the stop is persistent/reversible, and how to resume.

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 text is short and front-loaded, but it contains a duplicated '可用性: 可用性:' and mixes availability metadata into the purpose statement, making it slightly cluttered.

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

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

For a simple one-optional-param stop command this is minimally adequate: it states purpose, effect, and availability. But it leaves open what scope the stop applies to (all automation, current run, a specific flow) and the consequences for the current execution, so an agent may still need to infer 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%, and the only parameter 'reason' has a definition (熔断原因) plus default. The tool description adds no extra semantic detail about the reason field, so 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 names a clear action (打开熔断/stop subsequent automatic execution) and a domain (招聘自动化/recruitment automation), so an agent can see this is the halt control for the automation flow. It doesn't explicitly contrast with siblings like boss_agent_run or boss_agent_pending, but 'stop' is distinct enough.

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?

Usage is implied: call this when automatic recruitment execution should be halted. There is no explicit when-not-to-use, no prerequisites, and no mention of alternatives, so the guidance is only implicit.

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

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

No annotations are provided, so the description carries the full burden. It discloses one meaningful behavioral trait: by default it 'rehearses' actions that meet a threshold, suggesting a non-executing/simulated mode. But it doesn't state side effects, whether actions are queued for review, what 'threshold' means, or any permission/rate-limit constraints.

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

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

The core purpose is stated succinctly and front-loaded in a single line. The inclusion of availability metadata is useful but contains a duplicated '可用性: 可用性:' typo, which slightly reduces polish. Overall it is compact and scannable.

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 output schema and no annotations, an agent needs more context about what happens after training: whether actions are executed, reviewed, or only simulated; what threshold means; and how this relates to boss_agent_review/approve/reject. The current description leaves these gaps, so it is incomplete despite the simple parameter 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% for the single optional parameter (`limit`), so the baseline is 3 even though the description adds no parameter-specific explanation. The description does not mention `limit` or how it influences the training run, but the schema already documents it adequately.

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 conveys a specific function: a training/calibration mode whose default behavior is to rehearse threshold-satisfying actions ('训练校准模式，默认演练满足阈值的动作'). It names a clear verb and resource, and the phrase '训练校准模式' helps set it apart from the execution/review siblings. However, it does not explicitly contrast with any sibling or define what 'threshold' means.

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 tool's purpose implies it is for training/calibration rather than production execution, which gives some context. But there are no explicit when-to-use conditions, no exclusions, and no named alternatives among the many boss_agent_* and boss_* siblings. An agent must infer when to choose this over boss_agent_run or boss_agent_review.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It does disclose the core analysis behavior and the outputs (match score and gap analysis), which implies a read-only operation. However, it does not state side effects, data handling, or explicit constraints beyond the availability tag, so transparency is incomplete.

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

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

The description is a single concise sentence with the main purpose front-loaded. The embedded availability metadata is useful, though the duplicated '可用性: 可用性:' is a minor formatting flaw that prevents a perfect score.

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

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

For a simple two-parameter tool with no output schema, the description covers the essential inputs and explicitly mentions the key outputs. The availability tag adds useful role and platform context. It could be more complete by describing the format or scale of the match score, but the current level is sufficient 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?

Schema description coverage is 100%, and the input schema already describes 'jd_text' and 'resume' clearly. The tool description adds no additional parameter-level meaning beyond what the schema provides, so the baseline score of 3 is appropriate.

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

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

The description clearly states what the tool does: analyze a job description, evaluate resume fit, and output a match score and gap analysis. It identifies a specific verb, resource, and output. However, it does not explicitly distinguish itself from closely related siblings such as boss_ai_fit or boss_ai_suggest, so it misses the top score.

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 about when to use this tool versus alternatives like boss_ai_fit, boss_ai_suggest, or boss_recommend. The embedded availability tag restricts use to candidates on certain platforms, but it does not help an agent decide between 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?

No annotations are provided, so the description carries the full burden. It describes the core behavior (analysis plus generated suggestions/templates) and uses '给出' rather than '发送', implying it does not send messages. But it does not disclose read-only status, data handling, or limitations such as minimum chat history length.

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 front-loaded, with the availability bracket adding useful role/platform context. The duplicated '可用性: 可用性:' is a minor flaw, but overall the description is efficient and 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?

The trigger and expected outputs are present, and the availability information constrains usage to specific roles/platforms. However, with no output schema and no annotations, the return format is unspecified, and no guidance is given for choosing this over closely-related siblings.

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 3 applies. The description adds no extra parameter-level detail and merely reinforces chat_text as the central input. No enums or nested objects require additional explanation.

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 ('诊断') and resource ('聊天记录'), and names concrete outputs: next-step action suggestions and ready-made message templates. This clearly separates it from sibling tools like resume optimization or interview prep.

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?

Usage context is implied: use when the user wants communication diagnosis and message templates based on chat history. However, it never names alternatives or exclusion conditions, so with many similar sibling tools (boss_chat_summary, boss_ai_reply, boss_ai_optimize) the agent is left to infer when this is the correct choice.

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

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

没有 annotations，描述需要承担行为披露职责；'仅草稿，不发送'清楚排除了发送副作用，这是关键行为信息。但描述未补充参数组合要求（job_id 与 jd_text 二选一）或返回内容形态，行为透明性只达到基本合格。

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?

一句话承载了用途、输入、输出边界三个关键信息，信息密度高且核心动作前置。唯一瑕疵是可用性片段中'可用性:'重复，略微影响整洁度。

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?

对草稿生成类工具，描述配合完整 schema 已覆盖用途、可用角色/平台和关键副作用。虽然没有 output schema，但'草稿'已足够表达返回的是文本内容，整体对智能体选择与调用足够完整。

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

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

输入 schema 对 5 个参数的描述覆盖率为 100%，枚举值和互斥关系已在 schema 中说明。描述本身没有增加超越 schema 的参数语义，因此按 100% 覆盖率的基线给 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?

动词'起草'与资源'求职信/自我介绍草稿'明确，且限定输入为'本地简历与目标岗位'并强调'仅草稿，不发送'。仅凭描述即可与发送类工具（boss_apply/boss_greet）和简历优化类工具（boss_ai_resume_optimize）区分。

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?

描述给出明确使用边界：角色限 candidate、平台限 zhilian/zhipin、recruiter_platforms=-，并说明只产出草稿不发送。但未点名具体替代工具或何时改用其他 boss_ai_* 工具，尚非完全显式的路由指引。

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

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

With no annotations provided, the description carries the burden of disclosing behavior. It does reveal a key behavioral trait: it uses '已缓存职位详情' (cached job details), implying no fresh fetching. But it does not mention whether the operation is read-only, what happens if no cached jobs exist, or any side effects.

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 main functional description is one compact sentence that front-loads purpose and inputs. However, the bracketed availability suffix contains a duplicated phrase '可用性: 可用性:', which is a minor typographical flaw that slightly reduces polish.

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?

Without an output schema, the description partially compensates by naming the report's key components (match, gaps, keywords). Still, it lacks detail on the exact return format, error conditions (e.g., missing resume or empty candidate pool), and how the limit parameter affects the output—leaving the agent with some uncertainty.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds context about the resume being local and job details being cached, which aids understanding of the underlying data, but it does not elaborate on the 'limit' parameter or provide any format/syntax details beyond the schema.

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

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

The description states a clear verb ('生成'), a specific resource ('逐岗匹配度、能力缺口和关键词命中报告'), and identifies the inputs (local resume + cached job details). This gives a concrete sense of the tool's function, though it does not explicitly distinguish it from sibling tools by name.

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 when to use the tool: when a candidate wants a per-job match report based on cached job details. However, it provides no explicit when-not-to-use guidance or alternative tool references, leaving the agent to infer boundaries based on 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?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It does not mention that the tool is read-only (no mutations), what the output format is, whether it requires authentication, or any side effects. It simply states it generates content, which is a minimal behavioral trait. Since it doesn't contradict annotations (none provided), it's low but not contradictory.

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 core functional sentence is concise and front-loaded. The appended availability note adds some length but is structured as a bracket after, so it doesn't clutter the main purpose. Overall it's efficient, though the availability note is a minor distraction.

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

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

This is a content-generation tool with no output schema. The description does not explain what the tool returns (e.g., list of questions, suggestions, format, length). It also doesn't mention any prerequisites, constraints, or error conditions. For an agent to correctly invoke and use the result, the return format is critical, and it's absent. The description is clearly incomplete.

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 adds value by explaining that the resume parameter is optional and used to customize the questions, which goes beyond the schema's bare 'reference resume name'. It doesn't add context for count or jd_text, but the one added insight pushes it above baseline.

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

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

The description clearly states the tool's function: generate mock interview questions and preparation suggestions based on a target job description, with optional resume-based customization. The verb 'generate' and resource are specific, and it's obvious this is a content-generation tool. However, it doesn't distinguish between siblings like boss_ai_analyze_jd or boss_ai_chat_coach, so it's clear but not differentiated.

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 the many sibling AI tools. It doesn't mention scenarios, alternatives, or exclusions. The availability note (candidate roles, specific platforms) gives context about who can use it but not when it's the right choice among similar 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?

With no annotations provided, the description carries the transparency burden. It does disclose a key behavior: 'not directly writing back to disk' (不直接写回磁盘), signaling a non-destructive preview. However, it does not explain other potential side effects, auth requirements, or what exactly 'outputs optimized structure' means.

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 core description is a single compact clause with a useful parenthetical. However, there is a duplicated '可用性:' token, and the availability bracket adds clutter without clear added value. It is concise but slightly messy, keeping it from a 4.

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

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

For a simple two-parameter tool with no output schema, the description covers purpose, the non-destructive behavior, and availability constraints. The phrase 'outputs optimized structure' hints at the return shape. Missing details like exact output structure are minor given the low complexity.

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

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

Schema description coverage is 100%: both 'resume' and 'jd_text' have descriptions in the schema. The tool description adds no additional parameter-level meaning beyond what the schema already provides, so the 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 the verb-resource relationship: 'optimize resume based on target job description'. It is specific and actionable. However, it does not differentiate from the closely related sibling tool 'boss_ai_resume_optimize', so it misses the sibling-distinction bar for a 5.

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 when-to-use or alternative routing guidance is provided. The availability constraint (roles/platforms) is meta-information, not usage context. There is no mention of when to choose this over boss_ai_resume_optimize or other AI resume tools, leaving the agent to guess.

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 text carries the full burden, and it does disclose the main behavior: it generates 2-3 draft replies and does not claim to send them. However, it omits details such as how the optional resume/context affect results, any rate limits or service dependency, and it relies on a malformed availability suffix that repeats '可用性'.

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 main sentence is compact and front-loads the action, result count, and key customization options. The availability bracket is useful but has a duplicated '可用性: 可用性:' and uses terse metadata notation, which slightly lowers polish.

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 four-parameter, no-output-schema, no-annotation tool, the description gives the core output shape (2-3 candidate drafts) and role/platform restrictions, which is adequate. It remains incomplete about the exact return structure and how the optional context should be supplied, so it is only minimally viable.

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

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

Schema description coverage is 100%, so the baseline is 3. The description reinforces the role of two parameters (resume and tone) and implicitly ties tone to output style, but it adds little beyond the schema and does not explain the optional 'context' parameter.

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

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

The description states a clear verb ('生成'/'generate'), a clear object ('回复草稿'/'reply drafts'), and an input condition ('基于招聘者消息'/'based on recruiter message'), so the agent can tell what it produces. The availability suffix clarifies it is for the candidate role on zhilian/zhipin, which indirectly distinguishes it from HR-side reply tools, but it does not explicitly name or compare siblings.

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 only implicit usage conditions (candidate role, zhilian/zhipin platforms) and output features. It does not state when the agent should pick boss_ai_reply over nearby alternatives such as boss_ai_chat_coach or boss_hr_reply, and it gives no exclusions or fallback 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?

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states that the tool only gives suggestions and does not modify the resume, which is the most important behavioral trait for an agent to know. The availability suffix adds role/platform guardrails, though it does not describe output format or AI processing 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 primary action and key non-modification boundary are front-loaded in a single compact sentence. The trailing availability metadata is useful but contains a duplicated '可用性:' typo, which prevents a perfect structure score.

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 3-parameter tool with no output schema, the description is mostly self-sufficient: purpose, non-destructive behavior, and availability are covered. However, it does not explain how to choose between job_id and jd_text in practice, what the returned suggestions look like, or that 'resume' is a resume name obtained from another 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 description coverage is 100%, so the baseline is 3; each parameter already has a meaningful description. The overall tool description does not add significant parameter-level meaning beyond 'based on target position,' and the exclusivity of job_id vs jd_text is already stated in 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 states a specific verb and resource: optimize resume wording based on a target job. The parenthetical '仅建议，不修改简历' adds a clear boundary that prevents confusion with tools that would rewrite or modify the resume. It does not explicitly differentiate from the similarly named sibling boss_ai_optimize, so it falls short of a 5.

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 when a candidate wants resume wording tailored to a target job, and the availability suffix adds role/platform constraints (candidate only, zhilian/zhipin, recruiter_platforms=-). However, it provides no explicit when-not-to-use guidance or comparison with the many sibling AI tools such as boss_ai_optimize, boss_ai_suggest, or boss_ai_fit.

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

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

With no annotations provided, the description carries the full burden. It discloses that the tool does not modify the resume, which is a key behavioral trait. However, it does not describe the output format, whether suggestions are returned as a list, how priority ordering is applied, or any side effects. This is partial disclosure but leaves significant 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 core instruction is one clear sentence. However, the embedded availability string is redundant (repeats '可用性:') and adds noise. Still, the main content is concise and front-loaded, earning a 4 rather than a 5.

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 only two simple parameters and no output schema, so the description must explain the return value. It mentions suggestions are priority-sorted but does not specify the response structure, such as a list of suggestions or any metadata. Given the lack of annotations and output schema, this is a moderate gap.

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 both parameters (resume and jd_text) are already documented. The description does not add any additional meaning beyond the schema, such as format expectations or relationship between parameters. According to the baseline, with high coverage, a score of 3 is appropriate.

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

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

The description clearly states the tool's function: providing resume improvement suggestions based on a target job description, and explicitly notes it does not modify the resume. This is specific and distinguishes it from modification tools, but it does not name sibling tools like boss_ai_resume_optimize, so differentiation is left to the agent.

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 mention of when to use this tool versus alternatives such as boss_ai_resume_optimize or boss_ai_suggest_keywords. The description only notes it doesn't modify resumes, which hints at a read-only advisory role, but no explicit usage context 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?

No annotations are provided, so the description must carry the disclosure burden. It only describes the high-level recommendation behavior; it does not mention side effects, dependence on candidate-pool state, or result format. Since mutating behavior is not indicated, there is no contradiction, but the disclosure is thin.

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 definition is a single compact sentence followed by an availability bracket, so it is not bloated. The duplicated '可用性: 可用性:' is a minor formatting blemish, and the availability data would be cleaner in structured annotations, but information density remains good.

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 invocation is feasible because the optional limit parameter is documented and the purpose is clear. Missing pieces include the shape of the returned keyword suggestions, whether a populated candidate pool is required, and the effect of varying limit. With no output schema or annotations, the description is adequate 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 coverage is 100%: the only parameter (limit) is already described as '候选池职位数上限'. The description adds no extra parameter meaning beyond connecting the limit to the candidate-pool job analysis. 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?

Description states a specific action and object: it recommends search keyword combinations based on an analysis of candidate-pool jobs ('基于候选池职位分析推荐搜索关键词组合'). This makes the core purpose clear. It does not explicitly differentiate itself from sibling AI tools such as boss_ai_suggest or boss_ai_analyze_jd, though the keyword-combination focus is fairly distinctive.

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 bracketed availability text provides a concrete boundary: candidate role, zhilian/zhipin platforms, and no recruiter platforms. This tells the agent when the tool is permitted. It does not, however, say when to choose it over related AI sibling tools or state preconditions like having jobs in the candidate pool, so usage guidance is only implicit.

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

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

No annotations are present, so the description carries the full burden. It discloses idempotency ('幂等，不会重复投递'), which is valuable, and includes availability context. However, it does not describe the effects of an application/communication action, permissions, or result behavior. The duplicated '可用性:' is a minor flaw.

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 text is short and front-loads the action before the idempotency note and availability metadata. The duplicated '可用性:' is a minor formatting flaw, but overall the description is appropriately sized 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?

With no annotations and no output schema, the description leaves out important context for an action tool: what a successful call returns, side effects beyond idempotency, and how this action differs from nearby chat/greet tools. The availability block helps but is not sufficient for complete guidance.

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%; both parameters are described as '职位的 encrypt_job_id' and '职位的 security_id'. The description adds no additional parameter semantics, so the schema-based 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 specific action ('发起投递或立即沟通动作') and adds the idempotency trait, making the tool's core purpose clear. It does not explicitly distinguish itself from sibling chat/greet tools like boss_chat or boss_greet, though the name and '投递' carry most of the differentiation.

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 availability block gives role/platform constraints ('roles=candidate; candidate_platforms=zhilian, zhipin') but provides no guidance on when to choose boss_apply over alternatives such as boss_chat or boss_greet, and no exclusion criteria. The usage context is implied rather than stated.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only mentions the greeting limit and availability constraints; it does not disclose side effects, whether messages are actually sent, permission requirements, rate limits beyond the count, or what happens in preview/dry-run mode. This is thin for a tool that likely performs a real-world action.

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 appropriately short and front-loaded with the action and limit. However, it contains a duplicated '可用性: 可用性:' prefix and packs the availability clause into the same sentence, which slightly harms clarity without adding structural 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?

For a tool with no annotations and no output schema, the description is incomplete. It omits expected return values, error behavior, confirmation behavior, and the practical implications of the dry_run flag. The availability details are useful, but an agent still lacks essential execution context for a side-effecting batch 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 description coverage is 100%, so the schema already documents all four parameters. The description adds marginal context by tying the tool to 'search' and mentioning a limit of 10, but it does not enrich the meaning of query, city, limit, or dry_run beyond what the 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 description states a specific action — batch greeting after search — and includes a concrete constraint (up to 10). It clearly identifies the tool's resource and operation, though it does not explicitly name a sibling alternative to distinguish itself from, unlike stronger examples.

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 when to use the tool ('after search') and includes role/platform availability, which provides useful context. However, it gives no explicit guidance on when not to use it, does not mention alternatives like boss_greet or boss_apply, and leaves the selection criteria between sibling tools to inference.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says the tool lists communications and supports filtering; it does not mention output shape, pagination behavior, default time range, or access caveats beyond an availability tag. The availability metadata adds some context, but most behavioral traits remain undisclosed.

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 core sentence is concise and front-loads the purpose, but the description contains a duplicated '可用性: 可用性:' fragment and includes availability metadata in prose that might belong in a structured annotation field. It is short but slightly noisy.

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 three optional parameters, the description covers the resource and filters, and the schema documents every parameter. However, with no output schema and no annotations, the description does not reveal what the returned communication list looks like, how pagination behaves, or what the default time window is, so an agent still has some uncertainty before calling it.

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

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

Schema description coverage is 100%, so the schema already explains days, page, and from_who. The description adds a light mapping by referring to '发起方' and '时间' filters, which reinforces but does not meaningfully extend 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 states a specific verb and resource ('查看沟通列表' — view communication list) and mentions the available filters, so the basic intent is unmistakable. It does not explicitly differentiate itself from sibling tools like boss_chatmsg or boss_chat_summary, but the word 'list' narrows the resource enough for an agent to form a useful initial hypothesis.

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 use this tool versus alternatives such as boss_hr_chat, boss_chat_summary, or boss_chatmsg. The description only states what the tool can do, not the conditions under which an agent should choose it or avoid 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?

No annotations are provided, so the description must carry the burden of behavioral disclosure. The word '查看' implies a read-only operation, but the description says nothing about compliance filtering, pagination behavior, message ordering, truncation, or potential errors.

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 front-loads the purpose in a single sentence. The only structural flaw is the duplicated '可用性: 可用性:' text in the availability tag, which is minor but slightly sloppy.

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 paginated read tool, the description and schema together cover the basic invocation details: all parameters are documented and the purpose is clear. However, with no output schema and no description of the returned message format, ordering, or compliance behavior, an agent has only partial context for fully anticipating results.

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

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

Schema description coverage is 100%, so the baseline is 3 even though the tool description itself adds no parameter-level meaning. The useful note about the 'raw' parameter being compliance-gated lives in the schema, not in the overall 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 states the specific action '查看与指定好友的聊天消息历史' (view chat message history with a specified friend), making the core purpose clear. It does not explicitly distinguish itself from sibling tools like boss_hr_chatmsg, though the role/platform availability hint provides some differentiation.

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 availability suffix gives useful context that this tool is intended for candidates on zhilian/zhipin platforms and not for recruiters. However, it does not explicitly say when to use this tool over alternatives such as boss_chat, boss_chat_summary, or boss_hr_chatmsg.

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

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

No annotations are provided, so the description carries the behavioral burden. It adds useful context by listing availability roles/platforms (candidate; zhilian, zhipin), but it does not disclose whether the operation is read-only, what output shape to expect, or any side effects.

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

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

The description is a single front-loaded sentence that communicates purpose efficiently. The duplicated '可用性:' tag is a minor formatting flaw, but overall there is no wasted prose.

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

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

For a one-parameter tool with complete schema coverage, the description is mostly adequate. However, with no output schema and no usage-vs-alternative guidance, the agent is left to infer what the structured summary includes and when this tool should be chosen over boss_digest or boss_history.

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% for the only parameter, security_id, described as '好友的 security_id'. The description adds no parameter-specific meaning beyond the schema, 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 specific action and resource: '基于聊天历史生成结构化摘要与下一步建议' (generate a structured summary and next-step suggestions from chat history). This clearly conveys what the tool does and is not a tautology. However, it does not explicitly distinguish itself from similar siblings such as boss_digest or boss_history.

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?

Usage is implied: an agent should call this when a chat summary with next-step suggestions is needed. There is no explicit when-to-use vs alternatives guidance or exclusions, and the included availability block is a restriction rather than usage direction.

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 must carry behavioral disclosure. It communicates that the operation is a non-destructive listing and adds availability constraints, but it does not mention output format, pagination, or any side effects. This is adequate but not rich.

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

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

The core purpose is one concise sentence and the availability info is front-loaded in brackets. However, '可用性: 可用性:' contains a duplicated label, which is minor 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 zero-parameter, no-output-schema tool, the description covers purpose, approximate result count, and availability constraints. It is complete enough to let an agent invoke it correctly without further clarification.

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 zero parameters, so there is nothing for the description to explain. Baseline for 0 parameters is 4; the description provides no contradicting or missing parameter detail.

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

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

The description states a specific verb ('列出') and a specific resource ('支持的城市列表'), and adds a concrete detail (~40 cities). This clearly distinguishes it from the many boss_* sibling tools, none of which serve this exact function.

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: use it when you need the list of supported cities. The availability bracket adds context about which roles and platforms can call it, but it does not explicitly state when to prefer this tool over alternatives or include any 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?

With no annotations, the description carries the behavioral disclosure burden. It does identify the destructive target — expired caches and temporary files — and the dry_run parameter in the schema signals a non-destructive preview option. However, it does not warn about permanence, side effects, or permissions, which prevents a higher score.

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 core purpose is stated in a single, front-loaded sentence with no filler. The only structural issue is the duplicated '可用性: 可用性:' label in the availability bracket, which is minor clutter but keeps it from a perfect score.

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

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

For a simple two-parameter utility with no output schema, the description and schema together are sufficient for basic invocation. However, the lack of any destructive-operation warning or expected return behavior means it is only minimally complete.

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

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

Schema description coverage is 100%, with both parameters ('all' and 'dry_run') already documented in the input schema. The tool description adds no additional parameter-level meaning, so the baseline score 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 uses a specific verb ('清理' / clean) and a concrete resource ('过期缓存和临时文件' / expired cache and temporary files), which makes the tool's purpose immediately clear. It is also clearly distinct from the other boss_* siblings, none of which cover cache or temporary-file cleanup.

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 role and platform availability constraints, which help an agent know who can use the tool. However, it does not explicitly explain when to choose boss_clean over alternatives or state exclusions, leaving usage context mostly 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?

With no annotations, the description must disclose behavior, but it only says 'view and modify' and lists some configuration availability. It does not explain side effects of set/reset, whether changes are persistent, permission requirements, or what the tool returns.

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, but it contains a duplicated '可用性: 可用性:' typo and mixes an availability list into the main description, making it slightly messy. It is compact yet 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 no output schema and no annotations, the description does not cover return values, behavioral side effects, or when to choose this tool. The schema covers parameter mechanics, but the description leaves too much about operational behavior to inference for a config-mutation 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 baseline is 3. The description adds value by listing possible configuration domains and values (roles, candidate_platforms, recruiter_platforms), which helps an agent understand what keys look like beyond the generic schema labels.

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

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

The description states a clear verb and resource: '查看和修改配置项' (view and modify configuration items), and the action enum (list/get/set/reset) reinforces the intended scope. It does not explicitly distinguish itself from sibling tools, but the configuration focus is unique enough among the boss_* siblings.

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 no guidance on when to use this tool versus alternatives. The bracketed availability list reads as domain/configuration context rather than usage conditions, and no exclusions or alternative tools 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?

No annotations are provided, so the description carries the behavioral burden. '读取' clearly signals a read-only operation, and '持久化' indicates it reads stored data. Still, it does not mention side effects, output behavior, pagination limits, or whether any crawl state is affected. It provides basic transparency but not full coverage.

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 core description is a single efficient sentence with action first and filters second. However, the trailing availability string is somewhat redundant and contains a duplicated '可用性: 可用性:', which adds noise. Overall it is compact but not perfectly clean.

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 schema covers all input parameters, and the description communicates the tool's purpose. But there is no output schema and the description does not describe what the returned data looks like or how results are structured. For a three-parameter read tool this is acceptable but could be more complete.

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

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

Schema description coverage is 100%, so the input schema already documents all three parameters. The description adds little beyond restating the idea of filtering by page and detail status. No parameter meaning is materially enriched by the 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 the action ('读取' = read), the resource ('持久化 crawl 职位' = persisted crawl positions), and the available filters (page and detail status). This distinguishes it from siblings like boss_crawl_status and boss_crawl_shortlist, since it targets the stored job results themselves rather than crawl status or shortlist data.

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 when to use the tool: when you need to read persisted crawl results rather than crawl status or shortlists. However, it never explicitly names alternatives or states conditions for choosing this tool over the many sibling crawl-related tools. Usage context is implicit, not 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?

With no annotations provided, the description carries the disclosure burden and does add useful behavioral context: it explicitly states no BOSS request is made and that the operation is local. However, it does not disclose side effects such as duplicate handling, overwrite behavior, or whether existing shortlist entries are modified, which would matter for a data-import 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?

The main instruction is a single concise, front-loaded sentence that conveys the action, source, destination, and offline behavior. The availability metadata is useful, though the duplicated '可用性: 可用性:' is a minor formatting blemish.

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 5-parameter tool with no annotations and no output schema, the description establishes the key workflow dependency on crawl results and clarifies the local-only behavior. However, it does not describe what the tool returns on success or failure, which leaves a gap for an agent invoking the tool without an 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 description coverage is 100%, so the schema already documents all five parameters thoroughly. The description adds contextual linkage by mentioning that selectors come from boss_crawl_results and the destination is the local shortlist, but it does not add meaningful detail 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 uses a specific verb and resource: '将 crawl results 返回的 selector 导入本地 shortlist' (import selectors returned by crawl results into the local shortlist). It also adds a distinguishing behavioral marker, '不请求 BOSS' (does not request BOSS), which helps differentiate it from BOSS-side tools, though it does not explicitly name a sibling alternative.

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 clear context: this tool is used after a crawl run, to import selectors into a local shortlist rather than making a BOSS API call. It does not explicitly list alternatives or 'when not to use' conditions, but the source/destination relationship and the '不请求 BOSS' exclusion make the intended usage reasonably 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly indicates this is a read-only status operation and names the exact data points returned. It does not discuss side effects, but '读取' makes the non-mutating nature clear, and no additional behavioral context is obviously required for a status-check 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?

The core description is one concise sentence that front-loads the purpose and enumerates the returned status fields. The availability suffix is useful but contains a duplicated '可用性:' typo, which is a minor structural flaw.

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

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

For a simple one-parameter status tool, the description adequately covers what the tool does, what it returns, and the availability context. There is no output schema, so the listed fields help, but the description does not explain the possible values or interpretation of 'risk status' or 'detail progress'.

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 run_id property is already described as a crawl run identifier returned by 'boss crawl start'. The tool description adds no additional parameter-level detail, so the baseline of 3 is appropriate since the schema fully documents the parameter.

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 a specific read operation ('读取') and specifies the resource being read: crawl page cursor, job count, detail progress, and risk status. It is easy to distinguish from sibling tools like boss_crawl_results because it explicitly focuses on status fields, though it does not name the alternatives.

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

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

The tool's purpose implies it is used when an agent needs the status of a crawl run, and the run_id parameter description references 'boss crawl start'. However, the description provides no explicit guidance on when to use this tool versus sibling tools, nor does it list exclusions other than availability constraints.

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 burden of behavioral disclosure. '查看' implies a read-only operation, and the description adds a useful prerequisite (security_id from search/recommend) plus availability constraints. It does not disclose output shape, error behavior, or the effect of providing job_id, but for a simple detail-view tool this is adequate.

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 very short and front-loaded with the core purpose, which is good. It loses a point for the duplicated '可用性: 可用性:' text and for embedding availability metadata awkwardly in the same string.

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 is simple and the essential calling pattern is described, but there is no output schema and the description does not mention how the optional job_id fast path affects behavior. It also does not differentiate from sibling detail-view tools. Overall it is minimally complete but has clear 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 the baseline is 3. The description adds the useful provenance hint that security_id comes from search/recommend results, but it does not add meaning for job_id, which is already well described in the schema. This is a minor enhancement over 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 states a specific verb ('查看' / view) and a clear resource ('职位详情' / job details), making the tool's purpose immediately understandable. It does not explicitly distinguish itself from sibling tools like boss_show or boss_hr_jobs_detail, so it stops short of a 5.

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 clear context by noting that security_id is obtained from search/recommend results, which tells the agent when and how to use this tool. It does not mention alternatives or exclusions, so it does not reach the full 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 burden of behavioral disclosure. It explicitly states 只读 (read-only), indicating no mutation, and discloses the available roles/platforms as well as md output support. This is adequate for a non-destructive digest tool, though it does not mention edge cases such as empty data or default time-window 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 a single front-loaded sentence with no filler, followed by a compact availability suffix. It loses a point because the availability label is duplicated: 可用性: 可用性:.

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 digest tool with three optional and fully documented parameters and no output schema, the description covers purpose, read-only nature, output format, and availability. It lacks explicit sibling-routing guidance, but the schema completes the remaining invocation details.

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 all three parameters (format, output, days_stale) are already documented in the schema. The description adds only the rationale that md output is convenient for email/Feishu, which slightly enriches the format parameter but does not add meaning to output or days_stale. 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 uses a specific verb, 汇总 (summarize), and names the exact resource scope: newly added positions, pending follow-up conversations, and interview items. It also calls itself a read-only daily report, which clearly distinguishes it from the many sibling tools focused on individual actions like apply, chat, or export.

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

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

The description clearly implies use for a daily overview digest and includes an explicit availability constraint: roles=candidate, candidate_platforms=zhilian/zhipin, recruiter_platforms=-. It does not name alternative sibling tools, but the 'read-only daily report' wording provides enough context for when this tool is appropriate.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It lists what is diagnosed but does not state whether the tool is read-only, whether it makes network calls, what side effects may occur, or what the output/return format is.

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

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

The description is short and front-loaded with the core purpose, but it contains a duplicated '可用性: 可用性:' sequence and trailing availability metadata that is not essential to understanding tool 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?

The description names the diagnostic areas but, with no output schema and no annotations, it does not explain what the agent will receive, what counts as success/failure, or whether any prerequisites exist. The zero-parameter signature makes invocation simple, but behavioral outcomes remain unclear.

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 zero parameters with 100% schema coverage, so there are no parameter semantics to clarify. The description does not need to compensate for undocumented parameters, earning the baseline score.

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 action verb, 诊断 (diagnose), tied to concrete resources: local runtime environment, dependencies, login state, and network connectivity. This makes the tool's purpose clear and distinguishes it from most siblings, though it does not explicitly name any diagnostic alternatives.

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

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

There is no guidance on when to use this tool versus alternatives, no exclusions, and no routing logic such as 'use when X, otherwise use Y'. The only context is the availability metadata, which does not explain selection behavior.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It indicates the action is a 'request' to exchange contact info, but does not explain side effects, whether the other party is notified, whether this action can be undone, or what the response looks like after a successful request.

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

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

The description is a single concise sentence followed by useful availability constraints. It is front-loaded with the action and target. The repeated '可用性:' typo is a minor structural blemish but does not materially impair 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 simple one-parameter tool with no output schema, the description provides the essential invocation context: what the tool does, who can use it, and which platforms are supported. It does not describe return behavior, but the lack of an output schema and the tool's low complexity make this a minor gap.

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

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

Schema description coverage is 100%, and the single parameter security_id is already described as the contact's security_id. The tool description adds context about what the exchange covers (phone or WeChat) but does not add any additional meaning to the parameter itself, so the 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 a specific action ('请求交换联系方式') and the target resource (phone/WeChat contact exchange), with the security_id parameter identifying the contact. It is distinct from the broader sibling set, though it does not explicitly differentiate itself from the similarly named boss_hr_exchange.

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 availability metadata embedded in the description gives clear context: this tool is for candidate roles on zhilian and zhipin platforms, and explicitly not for recruiters (recruiter_platforms=-). This provides concrete when-to-use constraints, though it stops short of naming or contrasting an alternative sibling.

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 full transparency burden and provides meaningful behavioral detail: it defaults to masking job_id/security_id/boss_name and always omits platform identifiers, recruiter names, and salaries from HTML output. This goes well beyond what the schema alone communicates, though it does not cover side effects or file-write behavior in depth.

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 main purpose is front-loaded in one clear sentence, followed by important privacy behavior and availability metadata. Minor duplication in the availability string ('可用性: 可用性') prevents a perfect structure score, but overall it is compact and 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 14-parameter tool with no output schema, the description plus detailed parameter schema is mostly complete: it explains output formats, URL reuse, privacy defaults, and availability. A little more detail about expected output or error conditions would help, but the schema already documents output_file/stdout 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 adds useful cross-parameter context by explaining that a search-page URL can reuse filters and that masking behavior is controlled by include_private. This adds value beyond individual schema 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 states a specific verb and resource: 'export search results' to CSV/JSON/HTML files. It also adds a distinctive capability, reusing BOSS Zhipin search page URLs for filters, which separates it from sibling bosses that search, crawl, or manage resumes.

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 clear context: use when exporting search results to files, with optional URL-based filter reuse. It also includes availability constraints for roles and platforms. It does not explicitly name alternatives or exclusions, but the intended use 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?

With no annotations provided, the description carries the behavioral burden and explicitly states '不落库' (not persisted), signaling a preview-only operation with no database side effects. This is valuable transparency, though it does not detail all possible side effects or response 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 main description is one efficient sentence that front-loads the action and scope and includes the important non-persistence note. The duplicated '可用性:' inside the availability bracket is a minor structural blemish but not confusing enough to lower the score further.

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 one optional parameter and no output schema, the description gives the essential action and side-effect profile. However, it leaves the meaning of '有效状态' vague and does not describe what the agent should expect in the response, so an agent must infer the return value.

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

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

Schema description coverage is 100% and the single optional 'page' parameter is already documented as '页码'. The description adds no extra meaning about pagination or parameter format, so it defaults to 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 uses a specific verb '预览' with a specific resource ('BOSS 职位收藏单页及有效状态'), clearly identifying this as a favorites-list preview tool. This distinguishes it from sibling list tools like boss_shortlist_list, boss_watch_list, and boss_resume_list, even without naming them 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 gives no guidance on when to use this tool versus alternatives such as boss_shortlist_list or boss_watch_list. It only provides availability constraints for candidate roles/platforms, which is a restriction, not a usage criterion.

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 full behavioral burden. It does disclose the selection logic (unread, overdue, interviews) and the verb 筛出 implies a read/filter operation. However, it does not explicitly state whether the operation is read-only, what the output format is, or whether any state changes 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 core purpose is front-loaded in one efficient sentence, and the availability metadata is useful. It loses a point for the duplicated '可用性: 可用性:' typo, but is otherwise concise and well-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?

For a low-complexity tool with one optional parameter and no output schema, the description covers purpose and basic filtering criteria. It leaves open whether criteria are OR-combined, what the returned candidate list contains, and any pagination/limit behavior, making it adequate but not fully complete.

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

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

The single parameter days_stale is fully described in the schema with a default and meaning, and schema description coverage is 100%. The main description's mention of 超时未推进 echoes the parameter but adds no extra semantic detail 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 uses a specific verb 筛出 with a clear resource (候选项 needing priority follow-up) and lists three concrete criteria: unread, overdue/no-progress, and interviews. It does not explicitly name sibling tools for differentiation, but the purpose and scope are 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 given on when to use this tool instead of related siblings such as boss_hr_candidates, boss_history, or boss_interviews. The availability note restricts it to candidate role and specific platforms, but that is a precondition rather than an alternative-selection rule.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only restates the action and prerequisites; it does not disclose whether this sends a message, creates a chat, has side effects, requires special permissions, or is subject to rate limits. This is a significant gap for a tool that performs an action.

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 very short and front-loaded, with the action stated first and availability appended. The duplicated '可用性: 可用性:' is a minor formatting blemish but does not meaningfully harm readability.

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

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

For a simple two-parameter action, the core purpose and inputs are covered, and the availability block adds useful platform/role context. However, with no output schema and no annotations, the description omits behavioral effects and does not help the agent distinguish this tool from closely related siblings, leaving the definition minimally sufficient rather than complete.

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

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

Schema description coverage is 100%, with both security_id and job_id already described as IDs. The description only echoes that both are needed, which adds no semantic meaning beyond the schema and the required field list. Baseline 3 applies because the schema handles parameter 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 states a clear action ('greet the recruiter') and a specific resource, and it names the two required IDs. It does not explicitly distinguish itself from sibling tools like boss_batch_greet, but the verb and object are unambiguous enough for an agent to identify its basic 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 practical context: it is for candidate roles and limited to zhilian and zhipin platforms, and it notes required IDs. However, it does not explain when to choose this tool over alternatives such as boss_batch_greet or boss_apply, nor does it mention any exclusion conditions. The usage is implied rather than 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?

With no annotations, the description carries the full burden of behavioral disclosure. It only states that the tool views history and adds availability constraints, but it does not mention what the returned history contains, whether it is purely read-only in practice, pagination, or any side effects.

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 purpose, with availability constraints appended compactly. There is a minor duplication ('可用性: 可用性:') that slightly reduces polish, but the overall structure is efficient and scannable.

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 no-parameter read tool, the description is nearly adequate, and the availability constraints add useful context. However, it does not clarify what 'browsing history' refers to or what the tool returns, and the lack of an output schema makes those gaps more noticeable.

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, so there is nothing the description needs to add beyond the schema. The schema coverage is effectively complete because the parameter list is empty, so the baseline of 4 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 clearly states the action and resource: '查看浏览历史' means 'view browsing history.' It is specific enough to distinguish the tool's intent from most siblings, though it does not explicitly name alternatives.

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

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

The availability block provides a concrete precondition: roles=candidate, candidate_platforms=zhilian,zhipin, and recruiter_platforms=-, which tells agents who may use it. However, there is no explicit guidance on when to choose this tool over alternatives like boss_show, boss_stats, or boss_digest.

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 full burden. It does disclose that this is a read-only list view and adds availability constraints, but it omits behavioral details such as whether the list is scoped to the current recruiter, pagination behavior, or what the returned entries look like.

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

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

The description is short and front-loaded with the core purpose before the availability note. The duplicated phrase '可用性: 可用性:' is a minor flaw, but the overall size is appropriate.

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 three-optional-parameter read tool, the purpose and filters are mostly sufficient for invocation. However, there is no output schema and no statement about the returned list structure or how pagination and filtering interact, leaving moderate 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 the schema already explains page, job_id, and label_id. The prose description adds no extra parameter semantics, so the baseline of 3 applies.

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

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

The description states a clear verb and resource: in recruiter mode, view the list of candidates' submitted applications. This unambiguously identifies the tool's function but does not explicitly contrast it with sibling tools such as boss_hr_candidates or boss_hr_jobs.

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 only contextual hint is 'recruiter mode' and the role/platform availability restriction, which tells who may use it but not when to choose it over alternatives. No exclusions or sibling differentiation 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?

No annotations are provided, so the description carries the full behavioral disclosure burden. It only says 'search candidates' and lists availability constraints; it does not disclose return format, pagination behavior, side effects, or whether any state changes 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 short and front-loads the main purpose, but it contains a duplicated token ('可用性: 可用性:') and combines availability metadata awkwardly in brackets. It is concise but not polished.

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 12 optional parameters, no annotations, no output schema, and a large sibling list, the description does not provide enough context. It lacks guidance on defaults, expected results, or how this search differs from other search-related tools.

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

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

Schema description coverage is 100%, so all 12 parameters are already documented with meaningful descriptions in the input schema. The tool description itself adds no parameter-level meaning, but the baseline of 3 applies because the schema handles the heavy lifting.

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

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

The description clearly states a specific verb and resource: '搜索候选人' (search candidates) within '招聘者模式' (recruiter mode). It is easy to tell this is a recruiter-scoped candidate search tool, though it does not explicitly name sibling tools for differentiation.

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 availability context ('roles=recruiter; ... recruiter_platforms=zhipin-recruiter'), implying this is for recruiters on a specific platform. However, it provides no guidance on when to choose this tool over siblings like boss_search, boss_recommend, or boss_hr_applications.

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 full burden. It discloses that the tool returns a list with unread counts and recent message summaries, implying a read-only view, but it does not explicitly mention side effects (e.g., whether viewing marks messages as read) or pagination behavior. This is partial disclosure, not comprehensive transparency.

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 sentence with the main function front-loaded and availability appended, keeping it scannable. However, the duplicated '可用性:' prefix is a minor structural flaw that slightly reduces polish.

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?

In the absence of an output schema and annotations, the description gives core information about list content and recruiter availability, but it omits details on pagination, output format, and differentiation from related chat list/message tools. It is sufficient for basic invocation but not fully complete for confident tool 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?

All three parameters (page, job_id, label_id) have descriptions in the schema, achieving 100% coverage, so the description need not add parameter semantics. The label_id values are fully enumerated in the schema, and the description adds no additional parameter-level 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 states '招聘者模式：查看与候选人的沟通列表（含未读数和最近消息摘要）' which clearly identifies the specific action (view), resource (communication list with candidates), and content (unread count and recent message summary). It is distinct from candidate-mode tools by explicitly labeling 'recruiter mode', and the resource and details differentiate it from sibling chat tools.

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 implicit context through '招聘者模式' and availability constraints (roles=recruiter), but it does not explicitly state when to use this tool over alternatives like boss_hr_chatmsg or boss_hr_last_messages. There are no exclusions, prerequisites, or alternative routing, so the agent must infer applicability.

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 behavioral transparency burden. '查看' clearly implies a read-only history view, but the description does not explicitly address side effects, pagination behavior, or response contents. It is not misleading, but it leaves some behavioral details to inference.

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 core description is a single front-loaded sentence followed by compact availability metadata. The duplicated '可用性:' label is a minor flaw, but the overall size is appropriate and there is no unnecessary exposition.

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 relatively simple read-historical-chat tool, the description plus complete schema covers the essential use case: recruiter mode, target candidate, message count, and paging. There is no output schema, but the return type (chat message history) is implied by the description.

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

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

Schema description coverage is 100%, so the schema already documents friend_id, count, and max_msg_id. The description adds little semantic detail beyond restating the candidate scope ('指定候选人'), so the 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 a specific action (查看/view) and a specific resource (chat message history with a specified candidate), and it frames the tool as recruiter-mode. It distinguishes itself from candidate-side siblings through the 招聘者模式 scope, though it does not name an alternative 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 provides clear context by declaring availability: roles=recruiter and recruiter_platforms=zhipin-recruiter. This tells the agent when the tool is intended to be used, but it does not explicitly name candidate-side alternatives or state when not to use 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?

With no annotations provided, the description carries the full behavioral burden. It says '请求交换' which implies a request rather than a guaranteed immediate exchange, but it does not disclose side effects, whether candidate consent is needed, what happens after the request, or how results are returned. Availability metadata is present but does not substitute for behavioral transparency.

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-loads the core action, but it contains a duplicated '可用性:' typo and embeds availability metadata in brackets. This is concise overall, but the structural defect and metadata clutter prevent a higher score.

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 and no output schema, the description does not explain the request's lifecycle, return value, or failure modes. It also does not distinguish this tool from the similarly named boss_exchange. The schema covers parameters, but the broader context an agent needs to select and invoke the tool correctly is incomplete.

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 both parameters are already described in the schema: type is '交换类型' and friend_id is '候选人会话 friend_id'. The description adds no meaningful parameter semantics beyond echoing the phone/WeChat choice already enumerated in 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 action ('请求交换' / request exchange) and the resource ('候选人手机号或微信' / candidate phone or WeChat), and scopes it to recruiter mode. It does not explicitly name a sibling alternative such as boss_exchange, so differentiation relies partly on the tool name and the mode label.

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 availability constraints ('roles=recruiter', 'recruiter_platforms=zhipin-recruiter') but gives no guidance on when to use this tool versus alternatives like boss_exchange. There is no explicit when-to-use or when-not-to-use context, so an agent must infer the conditions from the name and mode label.

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 full behavioral burden. It reveals that online/offline operations change job status, but it does not disclose effects on job visibility, reversibility, prerequisites, or any side effects beyond the operation names. The list behavior also lacks detail about scope, pagination, or what data is returned.

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 front-loaded with the core purpose before the availability bracket. The duplicated '可用性: 可用性:' is a minor typo that reduces polish, but the overall structure wastes very few 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?

For a simple two-parameter tool, the description plus schema is mostly adequate to invoke it correctly. However, there is no output schema and no description of what the list action returns, what fields are visible, or how status changes are reflected, leaving meaningful gaps for an agent relying on this definition.

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: action is an enum with default 'list', and job_id is documented as required for online/offline. The description adds little beyond repeating the action types, so the baseline of 3 is appropriate since the schema does the heavy lifting.

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

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

The description clearly states the tool's purpose: viewing a job list or performing online/offline operations in recruiter mode. It distinguishes itself from the sibling boss_hr_jobs_detail by focusing on list and status changes rather than details, but it does not explicitly name or contrast any sibling tool.

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 given about when to use this tool versus alternatives such as boss_hr_jobs_detail, boss_hr_applications, or other recruiter-mode tools. The availability note mentions recruiter roles and platform, but that is access information, not use-case guidance. The action enum implies some usage contexts but is not expanded into when/why choices.

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

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

With no annotations provided, the description carries the full burden. It clearly states the tool is a read-only 'view' operation and adds availability context, but it does not disclose return format, error behavior, authentication nuances, or any side effects. For a simple detail-view tool this is adequate but not thorough.

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

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

The description is a single concise sentence that front-loads the main purpose and then adds availability information. The duplicated '可用性:' is a minor typo that prevents a perfect score, but otherwise every element 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?

The tool is low-complexity with one parameter and no output schema. The description names the key return content (完整详情 including postDescription) and availability constraints, which is sufficient for an agent to invoke it correctly. It does not enumerate every possible return field, but that is not critical given the 'complete details' phrasing.

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

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

The schema already provides 100% coverage of the single parameter enc_job_id with a clear explanation ('职位的加密 ID（encryptJobId）'). The description adds no parameter-level semantics beyond referencing '指定职位', so it stays at the baseline for fully schema-documented parameters.

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

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

The description states a specific verb ('查看') and resource ('指定职位的完整详情'), and highlights a distinguishing feature: inclusion of the job description field postDescription. The '招聘者模式' qualifier differentiates it from candidate-facing tools, though it does not explicitly name a sibling to compare against.

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 communicates that this tool is for recruiter mode and specifies availability (roles=recruiter; recruiter_platforms=zhipin-recruiter), giving implied context for when it is appropriate. However, it does not explicitly state when to use this over sibling tools like boss_hr_jobs or boss_detail, nor does it provide exclusions or 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?

没有提供任何标注（annotations），因此描述必须承担行为透明度的全部责任。但描述仅说明功能，未提及任何行为特征，例如是否只返回摘要而不包含完整消息、分页行为、是否需要特定权限（虽然可用性提示提到角色，但未详细说明）、是否只返回当前页面的候选人等。缺少对操作影响和返回内容的披露。

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?

描述简短，但存在一个明显的重复错误：“[可用性: 可用性: ...]”，这破坏了专业性。内容上比较精炼，但结构简单，没有分点或结构化呈现。考虑到错误，给3分。

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?

工具涉及4个参数，但没有输出模式，且描述未说明返回内容（如摘要的格式或字段）。对于批量摘要工具，代理需要知道返回什么，但描述缺失。此外，没有说明不传 friend_ids 时如何获取候选人，虽然模式中有提到，但描述没有强化。整体信息不完整，代理可能难以正确使用。

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?

参数模式提供了100%的覆盖，每个参数都有详细描述（如 page 是沟通列表页码，job_id 按职位筛选等）。描述本身未增加额外语义，但依赖模式已足够。基线为3，合理。

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?

描述明确说明了工具的功能：批量查看候选人最近消息摘要，并指明了招聘者模式。这足以让代理理解工具的基本用途，并能与兄弟工具如 boss_hr_chat、boss_chatmsg 等区分开。但描述中没有提及任何区分性的细节，比如与单个聊天查看的区别，因此未达到5分。

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?

描述没有提供任何关于何时使用此工具、何时使用替代工具（如 boss_hr_chat 或 boss_chatmsg）的指导。也没有提及使用前提或限制条件（除了提示中的角色限制）。代理无法确定该工具是用于批量获取摘要还是用于具体场景，缺乏使用上下文。

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 bears the full burden of disclosing behavior. It only says 'reply', which implies a write/message-sending action, but it does not mention delivery effects, whether the message is sent immediately, permissions required, or the return value.

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 core purpose is stated in one concise clause, and the availability metadata is useful. Minor deduplication issue ('可用性: 可用性:') slightly mars the structure, but the description 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?

For a simple two-parameter tool, the core invocation details are present. However, without annotations or an output schema, the agent lacks guidance on expected results, how to obtain friend_id, or any constraints beyond the inline availability note. Adequate but with clear 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 coverage is 100%; both friend_id and message have clear Chinese descriptions in the schema itself. The description adds no extra parameter meaning, so the 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?

The description clearly states the action ('回复候选人消息' — reply to candidate messages) and the role context ('招聘者模式' — recruiter mode). This distinguishes it from candidate-facing tools, though it does not explicitly name or contrast sibling tools like boss_ai_reply or boss_hr_chat.

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 guidance about when to use this tool versus alternatives. The sibling list includes several messaging-related tools (boss_ai_reply, boss_hr_chat, boss_chat, boss_greet), but the description only implies 'recruiter mode reply' without stating when to pick this over those.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'request candidate share attachment resume' and does not explain side effects, whether a message is sent to the candidate, prerequisites, permission requirements, or what happens after invocation. This is a significant gap for an action-oriented 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?

The description is short and front-loaded with the purpose, which is good. However, it contains a duplicated '可用性: 可用性:' prefix and packs availability metadata into the same sentence, making it slightly cluttered and less polished than a tightly written definition.

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 is simple: one required parameter with full schema coverage and no nested objects. The purpose is clear enough for basic invocation, but there is no output schema and no description of expected return values, confirmation, or error conditions. For such a low-complexity tool this is acceptable, though not fully complete.

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

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

The input schema already documents friend_id as '候选人会话 friend_id' with 100% coverage, so the description need not repeat it. The description adds no additional parameter meaning beyond what the schema provides, matching the baseline of 3 for high schema coverage.

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 a specific action ('请求候选人分享附件简历' – request candidate share attachment resume) and identifies the mode ('招聘者模式'), making the tool's purpose obvious. However, it does not explicitly distinguish itself from siblings such as boss_hr_resume or boss_resume_show, so it stops short of a 5.

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 bracketed availability metadata ('roles=recruiter; candidate_platforms=-; recruiter_platforms=zhipin-recruiter') and the '招聘者模式' prefix give some context about when the tool is applicable: recruiter mode on the zhipin-recruiter platform. It does not name alternatives or explicitly explain when to request a resume versus viewing one, so usage guidance remains mostly 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'view', implying a read operation, but does not explain side effects, required permission context beyond roles, response behavior, or what happens when the resume is unavailable. This is minimal coverage of 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 very short and front-loaded with the main purpose, which is good. However, it contains a duplicated typo '可用性: 可用性:' and the bracketed availability block is somewhat noisy relative to the simple 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 tool with no output schema and no annotations, the description gives only the core action and availability. It does not describe the returned resume content, how it relates to boss_resume_show, or any limitations, leaving an agent with incomplete context for correct 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 description coverage is 100%, and the property descriptions already explain geek_id, job_id, security_id, and raw. The tool description adds no parameter-level meaning beyond what the schema provides, so the baseline score of 3 is appropriate.

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

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

The description clearly states the action and resource: '查看候选人在线简历' (view candidate's online resume) in recruiter mode. It identifies a specific verb and object, but it does not distinguish itself from sibling tools like boss_resume_show or boss_resume_list.

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 only availability constraints (roles=recruiter, platform=zhipin-recruiter) and no guidance on when to use this tool versus alternatives. There is no mention of when-not-to-use or why it should be preferred over boss_resume_show.

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 disclosure burden. "查看" (view) conveys a read-only operation, which is useful, but the description does not mention return format, pagination, or whether any side effects occur beyond listing.

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 definition is very short and front-loads the core meaning, but the bracket metadata contains a duplicated prefix: "可用性: 可用性:". This repetition and the awkward embedded constraints prevent a higher structural score.

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 read/list tool, the role and platform availability are essential invocation context and are present. However, there is no output schema and no description of what an interview invitation entry contains, leaving return semantics unspecified.

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 zero properties and full coverage by virtue of being empty, so there are no parameter semantics to document. The description adds no parameter-level detail, but none is needed for a parameterless tool.

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 Chinese description "查看面试邀请列表" clearly states a specific verb and resource: viewing a list of interview invitations. It is readily distinguishable from sibling tools like resume lists or chat tools, though it does not explicitly contrast itself with any sibling.

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

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

The availability metadata provides explicit role and platform context: roles=candidate, candidate_platforms=zhilian and zhipin, and recruiter_platforms=-. This implies when the tool is usable, but it does not name alternative tools or conditions for choosing among the many sibling list/read 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?

With no annotations, the description carries the full burden of behavioral disclosure. It identifies the mutation (add/remove tag) but does not describe side effects, idempotency, overwrite behavior, permissions, or what happens when the remove flag is absent. This is thin for a write operation.

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 core sentence is concise and front-loaded with the action and resource, followed by useful tag examples. The availability block adds context but includes a duplicated '可用性: 可用性:' that makes it slightly noisy.

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 3-parameter mutation tool with full schema coverage, the description covers the basic operation and availability. However, it lacks explicit usage-selection guidance and deeper behavioral detail, so an agent may still need to infer how to route to it among many sibling contact tools.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds example tag values but no semantic detail beyond what the schema already provides for tag, remove, and security_id.

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

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

The description states a specific action ('添加或移除标签') on a specific resource ('联系人') and gives concrete tag examples. It is clear, but it does not name or explicitly differentiate related sibling tools such as boss_shortlist_add or boss_favorites_list.

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 availability context (candidate roles on zhilian and zhipin, not recruiters), which helps an agent infer when the tool applies. It does not explicitly name alternatives or state when-not-to-use cases beyond the availability constraint, so it falls 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?

There are no annotations, so the description carries the disclosure burden. The verb '获取' clearly indicates a read/fetch operation scoped to the current logged-in user, which is useful. However, it does not mention side effects, default behavior when 'section' is omitted, or any other behavioral detail beyond the basic retrieve action.

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 core purpose is stated compactly and front-loaded, followed by availability metadata. However, there is a duplicated '可用性: 可用性:' typo and the availability suffix feels mechanically appended, which slightly hurts clarity.

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

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

The tool has no output schema and the 'section' parameter is optional, but the description does not say what happens when it is omitted or what the full response shape looks like. The data categories are listed, which provides a reasonable baseline, but an agent still lacks some context for invoking 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?

The schema only says '指定查看的部分' for the 'section' parameter, but the tool description maps the English enum values (info, resume, expect, deliver) to Chinese concepts (基本信息、简历、求职期望、投递记录). This adds practical meaning beyond the schema, so it earns above baseline despite full schema coverage.

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 a specific action ('获取当前登录用户信息') and resource, and enumerates the data categories (基本信息、简历、求职期望、投递记录). It does not explicitly differentiate itself from siblings like boss_resume_list or boss_show, so it stops short of a 5.

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 availability information explicitly restricts use to candidate roles and names supported platforms, while 'recruiter_platforms=-' signals that recruiters should not use it. It provides clear context but does not name alternative tools or decision conditions, so it lacks the full 5-level 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?

No annotations are provided, so the description carries the full burden. It reveals that the tool combines chat and interview data and generates a view, but it does not disclose whether the operation mutates state, requires special permissions, or how the aggregated data is scoped or refreshed. The duplicated '可用性' also suggests casual metadata quality.

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 core description is a single short sentence that front-loads the action and purpose, with a compact availability note in brackets. However, the duplicated '可用性' is a minor typo that detracts from polish.

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