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

No annotations are provided, so the description carries the full burden. '查看' implies a read operation and '旧版本遗留' hints at legacy reads, but there is no detail on return shape, ordering, volume, or auth beyond the role/platform tag. Disclosure is minimal for a tool with zero annotation 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?

A single front-loaded sentence is efficient, but the availability bracket is malformed with a duplicated label ('可用性: 可用性:'), wasting tokens and adding noise.

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-param, no-output-schema viewer, the description gives the core purpose plus availability. However, it never explains what the pending queue actually contains or what invoking it returns, leaving a meaningful gap for an automation-oriented 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 tool takes zero parameters, so the baseline of 4 applies; there is nothing in the schema for the description to compensate for.

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?

States a specific verb ('查看'/view) and resource ('旧版本遗留的待执行动作队列'/legacy pending action queue from old versions), so the agent knows it inspects a leftover queue. It doesn't explicitly differentiate itself from agent siblings like boss_agent_run or boss_agent_review, but the 'legacy/compatibility' framing is distinctive 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?

The availability bracket lists roles and platforms, which is a prerequisite hint, but there are no when-to-use or when-not-to-use conditions, and no routing versus the many agent_* siblings. The agent is left to infer context entirely.

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 supplied, so the description carries the full behavioral burden. It implies a read ('查看') of a legacy queue, but discloses nothing about return format, pagination, whether the queue is read-only, or how it interacts with the approve/reject siblings.

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?

It is short and front-loads the verb+resource, but the bracketed availability string contains a duplicated '可用性: 可用性:' typo and low-value platform metadata, which adds noise without clarifying 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?

For a zero-param, no-output-schema tool the description covers the basic purpose and flags its legacy nature. It remains incomplete on return shape and its relationship to the sibling review/pending tools, but the structural simplicity keeps the gap modest.

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 takes zero parameters and the schema is fully (trivially) covered, so there is no parameter semantics to add. Baseline 4 applies; nothing in the description could meaningfully improve on an empty 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+resource ('查看...人工复核队列' / view the legacy manual review queue), which is more than a tautology. However, it does not distinguish itself from near-siblings like boss_agent_pending or the boss_agent_review_approve/reject pair, leaving the agent to guess which queue tool to call.

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

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

It labels itself a '兼容接口' (compatibility interface) for 'old version legacy' data, which implies some usage context, but never states when to use it versus boss_agent_pending or the approve/reject actions. No explicit when/when-not or alternative routing 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 disclosure burden. It does add one genuinely useful behavioral fact beyond the schema: the operation writes into a pending queue, i.e. it has a persistent side effect. It says nothing about permissions, idempotency, reversibility, or what happens on failure, which for an unannotated mutation is a real gap.

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

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

The core sentence is compact and front-loaded, and the availability constraint is appended rather than buried. Minor defect: the bracket label is duplicated ('可用性: 可用性:'), which is sloppy but not misleading.

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 no output schema and no annotations, the description covers the side effect and the platform/role availability, which is reasonably complete. It still leaves the central ambiguity unresolved – whether this approves, rejects, or merely requeues a legacy item – which is the one thing an agent most needs to know.

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

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

There is a single parameter and schema description coverage is 100% ('review item id'), so the schema already fully documents it. The description adds no format, sourcing, or validation detail about the id beyond what the schema states. Baseline 3 applies when the schema does the work.

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 verb and resource ('处理旧版本复核项并写入 pending 队列' – process legacy review items and write them into the pending queue), which is more than a restatement of the name. However, it never says this is the *approve* path, and it gives no differentiation from the adjacent siblings boss_agent_review, boss_agent_review_reject and boss_agent_pending, so an agent cannot confidently separate it from them. '兼容接口' (compatibility interface) is also vague about what is actually being approved.

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 an implicit signal that this is for legacy/old-version review items, hinting that newer items should go elsewhere, but no alternative tool is named and there is no explicit when-to-use or when-not-to-use statement. An agent has to guess at the routing 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 behavioral burden. It does disclose one side effect beyond the name (a skip event is recorded), but says nothing about irreversibility, whether the item must be pending, required permissions, or what happens on failure for what is clearly a state-changing mutation.

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 short and front-loaded, but the appended availability block is cluttered and even duplicates the label ('可用性: 可用性:'), wasting space without adding operational meaning. Structure is acceptable but not 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?

For a mutation tool with no annotations and no output schema, the definition is thin: it does not say what state the review item moves to, whether the action is reversible, or what the caller gets back. The availability metadata does not compensate for these operational 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% with only two parameters, so the schema already documents 'id' (review item id) and 'reason'. The description adds no format, constraint, or meaning beyond that, which is the baseline 3 case.

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 specific verb ('拒绝'/reject) and resource ('旧版本复核项'/legacy review items), plus a side effect ('记录跳过事件'/record skip event), so the purpose is clear. It does not name its obvious counterpart boss_agent_review_approve, and the 'legacy version' qualifier is unexplained, so sibling differentiation is only partial.

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

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

The phrase '旧版本复核项' and '兼容接口' imply this is for legacy/compatibility review items rather than current ones, which is a weak usage signal. It never states an explicit when-to-use condition, prerequisites, or that boss_agent_review_approve is the alternative.

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

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

No annotations are provided, so the description carries the full behavioral burden. It implies mutation (execution and lead generation) but never states what real platform actions are performed, what permissions/auth are needed, or whether the run is reversible; the dry_run default is only in the schema, not explained here.

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 sentence is reasonably front-loaded and compact, but the trailing availability bracket contains a duplicated token ('[可用性: 可用性:'), signaling sloppiness, and the stage enumeration adds length without much precision.

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 multi-stage orchestration tool with no output schema and no annotations, the description conveys the conceptual flow but omits what gets executed, what the run returns, and side-effect behavior. It is minimally adequate but leaves real gaps given the tool's complexity.

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

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

Schema description coverage is 100% and both parameters (limit, dry_run) are documented in the schema, so the schema does the heavy lifting. The description adds no parameter-level meaning beyond this, making the baseline 3 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 specific verb ('运行一轮' / run a round) and enumerates the pipeline stages (scan, decide, threshold control, execute, lead generation), which distinguishes it from siblings like boss_agent_train or boss_agent_review. It is clear enough to identify the tool, though the stage list is somewhat nebulous.

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 statement of when to use this tool versus alternatives such as boss_agent_review, boss_agent_pending, or boss_agent_stop, nor any prerequisites or exclusion conditions. The bracketed availability tag (roles, platforms) is a gating constraint, not usage 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 exist, so the description carries the full burden. It does add genuine behavioral context beyond the schema by disclosing role and platform availability (candidate/recruiter, zhipin), and 'view' implies a non-destructive read, but it never explicitly states read-only behavior, auth requirements, or what the 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 core sentence is tight and front-loaded, but the availability clause is duplicated ('可用性: 可用性:'), an obvious defect that adds noise. Overall short, but the redundancy costs 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 zero-parameter, no-annotation, no-output-schema stats tool, the description lists what is counted and who may call it, which is roughly adequate. It does not explain the return shape or how these aggregate stats should be interpreted, leaving a modest 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline is 4. The four named stat categories effectively describe the output scope rather than any 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?

States a specific verb (查看/view) and resource (statistics) and enumerates the four stat categories covered: execution, skip, history queue, and circuit-breaker. This is enough to distinguish it from the general sibling boss_stats, though it never names that sibling 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 never says when to choose this over boss_stats, boss_status, or boss_agent_run. The availability bracket (roles=candidate, recruiter; platforms=zhipin) is access gating, not usage guidance, so an agent must infer the selection condition.

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 one meaningful behavioral trait: it halts future auto-execution rather than killing in-flight work. But it omits whether the stop is reversible, what happens to queued tasks, and any permission requirements beyond the availability tags.

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 a single compact sentence, with availability metadata appended. Slightly noisy due to the duplicated '可用性: 可用性:' prefix, but otherwise efficient with no filler.

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

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

For a zero-annotation, single-parameter mutation-style tool with no output schema, the description covers the basic purpose and audience constraints but leaves behavioral questions unanswered (reversibility, effect on pending tasks, restart path). 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 description coverage is 100% and the single 'reason' parameter is fully documented in the schema (with type and default). The description adds no additional semantics for the parameter, so this is the baseline case where the schema does the work.

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 ('打开熔断，停止后续自动执行' – open the circuit breaker and stop subsequent automatic execution) on a clear resource (recruitment automation). It is readily distinguishable from siblings like boss_agent_run or boss_agent_train as the stop counterpart, though the phrasing is somewhat terse.

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 block specifies roles and platforms (candidate/recruiter, zhipin), which gives context about who may invoke it. However, it never states when to stop automation versus continuing it, nor references any alternative tool, leaving usage only 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 behavioral burden. It hints at a dry-run-by-default posture, which is genuinely useful, but says nothing about permissions, what state the training mutates, what the threshold is, or reversibility.

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 short, but the trailing availability tag is redundant and duplicated ('可用性: 可用性:'), adding noise. Purpose is front-loaded, so structure is acceptable but not 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?

With no annotations, no output schema, and a single documented parameter, the description should explain the threshold concept and what training produces. It leaves the agent guessing about the calibration workflow and its relationship to sibling agent 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?

Only one optional parameter ('limit') exists and the schema already documents it at 100% coverage. The description adds nothing about batching or limit semantics, 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 identifies a specific function ('train calibration mode, default dry-run actions that meet a threshold'), which is more than a tautology. However, it does not distinguish itself from close siblings like boss_agent_run or boss_agent_stop, so an agent cannot easily tell which agent command to pick.

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

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

It notes that actions meeting the threshold are rehearsed by default, but gives no explicit when-to-use or when-not-to-use guidance versus boss_agent_run or boss_agent_review. The bracketed availability string is metadata, not usage 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 behavioral burden. It usefully discloses the output shape (match score + gap analysis), which substitutes for the absent output schema, but says nothing about permissions, side effects, or cost. Adequate but with clear 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?

A single front-loaded sentence that leads with the action and result. Minor waste in the duplicated availability label ('可用性: 可用性:'), but overall tight.

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 2-parameter analysis tool, the description explains the operation and its outputs, which is the main gap-filler given no output schema. It still omits usage context and any routing among the many boss_ai_* siblings, leaving the agent to guess which analysis tool to pick.

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 (jd_text, resume) are already documented in the schema. The description adds no syntax or format detail beyond what the schema provides, 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?

States a specific verb+resource in Chinese: analyze a job description and evaluate resume match, returning a match score and gap analysis. This is clear and tells the agent what it produces. It does not, however, differentiate itself from the closely related sibling boss_ai_fit, which likely overlaps in intent.

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 when-to-use guidance, no prerequisites, and never names an alternative such as boss_ai_fit or boss_ai_optimize. The bracketed text is a platform-availability gate (roles=candidate; candidate_platforms=zhipin), not usage 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 disclosure burden. It implies a non-mutating diagnostic (it 'diagnoses' and 'suggests'), and the availability line adds who-can-call context, but it says nothing about whether state changes, token cost, or how templates are generated. Moderate rather than rich disclosure.

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

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

A single front-loaded sentence captures the core action plus outputs, and the availability tag is appended. Slightly marred by the duplicated '可用性: 可用性:' text, but overall tight and well-ordered.

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-output-schema tool, the description names the return artifacts (diagnosis, next-step actions, message templates) so an agent knows what to expect. Combined with 100% schema coverage, it is largely complete, though it lacks differentiation from siblings and any note about template/style interaction.

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 chat_text, style, and resume are already documented in the schema. The description adds no parameter-level meaning beyond that, so the baseline 3 for full schema coverage 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?

States a specific verb and resource: diagnose communication status from chat records and return next-step suggestions plus ready-made message templates. Clear about the output artifacts (diagnosis + action advice + templates), but does not differentiate itself from plausible siblings like boss_ai_reply or boss_ai_suggest.

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 tag (roles=candidate; candidate_platforms=zhipin; recruiter_platforms=-) implicitly gates when the tool can be invoked, which is useful. However there is no explicit guidance on when to choose this over sibling reply/coach tools, so usage is only 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 carry the behavioural burden. It usefully discloses that this is draft-only and never sends, plus audience/platform availability (roles=candidate, zhipin). It does not describe output format, generation quality, or reversibility, so the coverage is partial.

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

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

The purpose is front-loaded in a single effective clause, with the non-sending caveat immediately following. The only flaw is the duplicated '可用性: 可用性:' prefix in the availability tag, a 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 5-parameter generation tool with no annotations and no output schema, the description covers purpose and the draft-only constraint adequately. It omits any hint about the output shape or how the resume/jd inputs are combined, leaving it merely 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%, so the five parameters (including lang and tone enums, and the job_id/jd_text 二选一 relationship) are already fully documented. The description adds the resume/target-position framing but no syntax or format detail beyond the schema, warranting 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?

States a specific verb (起草/draft) and resource (求职信/自我介绍) plus the input basis (local resume + target position). It is distinguishable from siblings, though it does not explicitly name any alternative tool. Clear but without active sibling 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?

'仅草稿，不发送' clarifies the boundary of the action, and the availability tag scopes it to candidate roles on zhipin. However, there is no explicit guidance on when to prefer this over sibling tools like boss_ai_reply or boss_ai_resume_optimize; usage is only 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 must disclose behavioral traits. It mentions generating a report from local resume and cached jobs, implying a read operation, but does not state whether it is read-only, mutates state, requires permissions beyond availability, or how it handles missing cache. Insufficient for a tool with zero annotation 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?

Single sentence plus availability tag is front-loaded and concise. However, the availability tag contains a duplicated '可用性: 可用性:' and could be clearer. Otherwise no waste.

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

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

Given 2 parameters, no output schema, and no annotations, the description covers the tool's purpose and output content (match score, gap, keyword hits). It also provides availability constraints. However, it lacks behavioral details and usage alternatives, leaving some gaps for correct invocation.

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

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

Schema description coverage is 100%, so the schema already documents both parameters (resume name, limit). The description adds no additional syntax or format details beyond what the schema provides, 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?

States a specific verb (生成) and resource (逐岗匹配度、能力缺口和关键词命中报告) based on local resume and cached job details. Distinguishes from siblings like boss_ai_analyze_jd by focusing on per-job match report, but 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?

Provides availability constraints (roles=candidate; candidate_platforms=zhipin; recruiter_platforms=-), which implies when the tool can be used. However, it does not explicitly state when to choose it over alternatives like boss_ai_analyze_jd or boss_ai_optimize, nor does it provide exclusions beyond availability.

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

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

No annotations are provided, so the description carries the full behavioral burden. It conveys the generative intent but says nothing about permissions, cost, whether resume customization requires an existing resume, or what the output looks like. For a generation tool with zero annotation coverage this is a real gap.

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

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

The purpose is front-loaded in a single tight sentence, with the resume-customization parenthetical and the availability tag appended. Nothing is wasted, though the doubled '可用性: 可用性:' repetition is 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 3-parameter generation tool with full schema coverage and no output schema, the description covers the core intent adequately. It stops short of describing the shape or volume of generated output, which an agent planning a call would find useful.

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 the count default and the resume/jd_text params are already documented in the schema. The description adds only a hint that resume enables customized questions, matching the baseline 3 when 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 names a specific verb+resource: generating mock interview questions and preparation advice from a target job description, with optional resume-based customization. This clearly distinguishes it from JD-analysis siblings like boss_ai_analyze_jd, though it never names 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?

There is no when-to-use/when-not guidance or named alternative. The availability tag (roles=candidate; candidate_platforms=zhipin) does give contextual scoping about who may invoke it, which is useful, but the agent is left to infer when this beats boss_ai_chat_coach 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?

No annotations are provided, so the description carries the full burden. It does disclose the key behavioral trait that the result is returned as a structure and not written back to disk, which is valuable. It does not address permissions, rate limits, or whether the optimization is idempotent, leaving gaps for a no-annotation 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?

Front-loads the core action and its non-destructive output in a single efficient sentence. The availability tag is slightly noisy with the duplicated '可用性: 可用性:' text, but overall it is compact and appropriately sized.

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 two-parameter tool with no output schema and no annotations, the description covers the purpose and the non-write behavior, which is the essential context. It stops short of describing the returned structure's shape or how the optimization is scoped, so it is 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 description coverage is 100%, so the schema already documents both parameters (resume name, target job description). The description restates the intent of using a target JD and a resume but adds no syntax, format, or size requirements beyond the schema. Baseline 3 applies when 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?

States a specific verb and resource: it optimizes a resume against a target job description. The parenthetical clarifies the output behavior ('outputs optimized structure, does not write to disk'). However, it gives no differentiation from the near-identically named sibling boss_ai_resume_optimize, which an agent would struggle to tell apart.

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 tag (roles=candidate; candidate_platforms=zhipin; recruiter_platforms=-) implies this is only for candidate users on the zhipin platform, which is useful routing context. But there is no explicit when-to-use guidance versus alternatives like boss_ai_resume_optimize, boss_ai_suggest, or boss_ai_fit, so usage is only inferred.

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 the key behavioral fact that this produces drafts (not sends) and returns 2-3 candidates using resume and tone inputs, and the availability tag conveys role/platform preconditions. It stops short of stating side effects, quota/rate limits, or whether outputs are locally staged vs submitted, leaving meaningful gaps for an unannotated 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?

Purpose is front-loaded, followed by parenthetical capability detail and a bracketed availability tag, so the reader gets the essential 'what' immediately. It is efficiently sized, with only a minor defect: the availability prefix 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 4-param generation tool with one required param, full schema coverage, and no output schema, the description covers purpose, the nature of the produced output, and eligibility constraints adequately. The main omission is how it relates to sibling reply/suggestion tools, which is a minor gap rather than a blocking one.

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 four parameters (tone, resume, context, recruiter_message) are already documented in the schema, including the enum values for tone. The description only corroborates resume reference and tone preference at a high level and adds no format, length, or interaction detail, matching the baseline 3 for schema-driven params.

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?

States a specific verb and resource: generate reply drafts (生成回复草稿) based on recruiter messages, with concrete output scope (2-3 candidates, resume reference, tone preference). The availability tag (roles=candidate, candidate_platforms=zhipin) signals it is the candidate-side counterpart of the recruiter-side boss_hr_reply, aiding differentiation, though that sibling is not named 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 phrase "基于招聘者消息" implies the trigger context, and the availability bracket states the platform/role preconditions (candidate role, zhipin platform), which is useful eligibility guidance. However, it never says when to prefer this over adjacent tools like boss_ai_suggest, boss_ai_chat_coach, or boss_hr_reply, so alternative routing is left 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 disclosure burden. It usefully states that the tool only produces suggestions and does not modify the resume, which is an important non-destructive signal for an AI-optimization tool. Beyond that it discloses nothing about return format, permissions, or rate limits.

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

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

The purpose is front-loaded and the whole definition is short. The only blemish is the awkward duplicated label '可用性: 可用性:' in the availability bracket, but the overall length 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?

There is no output schema and only 3 params, so the description needn't explain return values. It covers the core action and the non-mutating constraint but omits surrounding context such as how optimization output is surfaced or which sibling to prefer, leaving minor gaps for this fairly simple 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. The description adds no parameter-level detail (e.g. resume name vs. job_id vs. jd_text semantics) and only addresses tool-level availability, so it does not earn 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 states a specific verb and resource ('优化简历措辞' = optimize resume wording) plus scope ('基于目标岗位' = based on the target job). It clearly demarcates the action as advisory ('仅建议，不修改简历'). However, it does not distinguish itself from nearby siblings such as boss_ai_optimize, boss_ai_suggest, or boss_ai_fit, leaving the agent to infer the difference.

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 parenthetical '仅建议，不修改简历' implies an advisory use case, and the availability string (roles=candidate; candidate_platforms=zhipin) tells the agent who/where it applies. But there is no explicit when-to-use vs. when-not, nor any pointer to an alternative sibling 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, the description must carry the behavioral load. It does disclose two important traits — output is priority-ordered and the resume is left unmodified (non-destructive) — but says nothing about prerequisites, permissions, or whether a saved resume name is required versus raw text.

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?

One front-loaded sentence carrying the purpose and the key non-mutation constraint. The availability tag is slightly redundant (duplicated '可用性: 可用性:') but overall the text is tight.

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 advisory tool with full schema coverage, the description conveys purpose, input basis (target JD) and non-mutation adequately. Only the guidance relative to sibling AI tools and any prerequisite for the resume input are missing.

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

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

Schema description coverage is 100%, so 'resume' and 'jd_text' are already documented. The description adds no format or linkage detail beyond the schema's own field descriptions, 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?

States a clear verb and resource: produces prioritized resume improvement suggestions based on a target job. The parenthetical '(does not modify resume)' usefully distinguishes it from the optimize-style siblings, but it does not differentiate from near-neighbors like boss_ai_fit or boss_ai_suggest_keywords.

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 only implied: it works against a target JD and returns advice rather than changing the resume. No explicit when-to-use, when-not, or named alternative among the many boss_ai_* siblings is given.

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

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

No annotations are provided, so the description carries the full behavioral burden. It mentions the analysis source is candidate-pool jobs, but omits return format, whether recommendations are generated live or cached, platform/auth prerequisites beyond the availability tag, and read/write safety profile.

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 short sentence, but the duplicated '可用性: 可用性:' and bracketed metadata introduce avoidable noise.

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?

There is no output schema and no annotations, so the description should explain what the tool returns. It does not describe the returned keyword combinations, their count, or their structure, leaving a significant gap for a recommendation 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% and the sole optional parameter 'limit' is fully described in the schema. The description adds no parameter meaning, 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?

States a specific verb phrase ('推荐搜索关键词组合') and scopes it to candidate-pool job analysis, so the basic purpose is clear. It does not, however, distinguish itself from nearby AI siblings such as boss_ai_suggest or boss_ai_analyze_jd.

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 tag gives implied context that this is for the candidate role on zhipin rather than recruiter platforms. There is no explicit when-to-use, when-not-to-use, or alternative-tool 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 provided, the description carries the full burden and does disclose one meaningful behavioral trait: the operation is idempotent and will not create duplicate applications. It omits other load-bearing behavior for a mutation tool — whether a quota or daily limit applies, what a successful result looks like, and whether the action is reversible.

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

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

A single front-loaded sentence: the action comes first, then the idempotency guarantee, then the availability constraint. It is slightly blemished by the duplicated '可用性: 可用性:' label, but nothing is padded.

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 two-required-param mutation tool with no annotations and no output schema, the description covers the essentials — what it does, that it is idempotent, and who can call it. It stops short of describing the observable outcome or failure modes, which an agent would want before firing an irreversible-looking side effect.

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 both parameters (job_id as encrypt_job_id, security_id) are fully documented in the schema itself. The description adds no syntax, format, or sourcing guidance for these IDs, so the baseline of 3 is appropriate — the schema does all the work.

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

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

The description names a concrete action pair — initiate an application ('投递') or start immediate communication ('立即沟通') — on the boss/job resource, which an agent can distinguish from read-only siblings like boss_detail or boss_status. It does not, however, explicitly differentiate itself from the nearby greet-family tools (boss_greet, boss_batch_greet, boss_hr_greet), so the boundary is inferable rather than stated.

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

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

It supplies a real usage gate — roles=candidate and candidate_platforms=zhipin — which tells the agent who may call it. It never says when to pick this over boss_greet or boss_batch_greet, nor does it state exclusion conditions, so the routing guidance is only 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 carries the full burden. It discloses the batch cap of 10 and the availability gating, but says nothing about the fact that this sends real messages to real candidates, whether actions are reversible, or any auth/rate-limit behavior beyond the cap.

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?

Very short and front-loaded, with the core operation stated first and constraints bracketed after. One redundancy: the bracket repeats '可用性:' twice, a small structural blemish on an otherwise efficient line.

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 bulk messaging tool with no annotations and no output schema, the description is thin. It omits what actually happens on invocation (messages dispatched), what dry_run returns, and any prerequisite/auth context an agent needs before bulk-contacting candidates.

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

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

Schema coverage is 100%, so the schema already documents all four parameters, giving a baseline of 3. The description adds one useful detail the schema lacks (the hard cap of 10, versus the schema's default limit of 5), but ignores dry_run and city.

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?

States a specific verb and resource: batch greeting (批量打招呼) performed after a search, with a stated cap of 10. The batch framing distinguishes it reasonably from the single-target boss_greet, though it doesn't name the sibling 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 '搜索后' (after searching) phrasing implies a workflow order, and the bracket gives role/platform availability constraints, but there is no explicit statement of when to prefer this over boss_greet or boss_hr_greet. Usage must be inferred.

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 usefully discloses platform/role availability (candidate-only, zhipin) and that results include a uid, but says nothing about the read-only nature, pagination behavior, rate limits, or auth requirements.

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

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

Two tight sentences plus an availability tag, front-loaded with purpose and filtering scope. Minor blemish: the availability tag repeats '可用性:' twice, a small editing artifact but not enough to obscure meaning.

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

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

For a 3-parameter, no-required-args list tool with no output schema and no annotations, the description is adequate but thin. It notes the uid in returned items but doesn't describe what else a chat-list entry contains, how paging works, or the tool's read-only nature, leaving gaps an agent would need.

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 days, page, and from_who (with an enum). The description only restates the filtering dimensions (发起方/time), which loosely maps to from_who and days, adding no syntax or format details beyond the schema. 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?

States a specific verb and resource (查看沟通列表) and clarifies the returned items carry a stable uid usable in boss_chatmsg / boss_mark / boss_exchange, which helps distinguish it from those siblings. The availability tag (roles=candidate, recruiter_platforms=-) further separates it from recruiter-side chat tools like boss_hr_chat, though it never names the closest alternative (boss_chat_summary) directly.

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 through its filtering capabilities (按发起方和时间筛选) and the platform/role gating, but gives no explicit when-to-use or when-not-to-use guidance relative to alternatives like boss_chatmsg or boss_chat_summary. The uid cross-reference hints at a workflow but is a chaining note rather than an invocation condition.

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 does not state whether the tool is read-only (implied by '查看', but not explicit), whether it requires authentication, whether pagination is supported (the schema has page/count, but the description omits it), or how results are returned. The availability constraint is disclosed, which is positive, but overall the behavioral picture is thin beyond the name.

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 states the core purpose. The availability constraint is appended in brackets, which is slightly clunky (e.g., repeated '可用性:'), but it is concise and contains no redundant filler. It could be structured more cleanly, but it is efficiently sized.

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

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

Given a tool with 4 parameters (one required) and no output schema, the description should at least explain the basic return format or pagination behavior to be complete. It does neither, and with no annotations, it leaves the agent without essential context about safety, behavior, or output. The availability note is helpful but insufficient for completeness.

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

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

Schema description coverage is 100%, so the schema already documents all four parameters (raw, page, count, security_id) with descriptions. The description adds no further parameter detail. With full schema coverage, the baseline is 3 – the description does not need to compensate for gaps, but it also adds no extra value.

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

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

States a specific verb+resource: '查看...聊天消息历史' (view chat message history with a specified friend). Clear what the tool does. However, it does not differentiate itself from the very similar sibling 'boss_hr_chatmsg' or 'boss_chat' explicitly. The availability note (candidate role, zhipin platform) does implicitly distinguish it from boss_hr_chatmsg, which likely has different role constraints, but the description doesn't state that.

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

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

Provides no when-to-use, when-not-to-use, or alternative tool guidance. There are multiple siblings that relate to chat messages (boss_hr_chatmsg, boss_hr_last_messages, boss_chat_summary). The description does not tell an agent when to pick this one over the others. The availability constraint is a gating condition, which is helpful, but it's not usage 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 disclosure burden. It does add useful behavioral context — the source of truth is chat history and access is restricted by role (candidate only) and platform (zhipin) — but it is silent on whether the operation is read-only, whether it consumes AI quota, or whether results are persisted.

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

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

A single front-loaded sentence stating purpose, followed by a compact availability tag. Slight waste from the duplicated label ('可用性: 可用性:'), but overall tight and easy to scan.

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, no-output-schema tool, the description covers what it produces (structured summary, next-step suggestions), where the data comes from, and the access constraints. It stops short of describing summary granularity or length, which would help an agent set expectations.

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

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

With one parameter at 100% schema coverage, the schema already documents security_id and even the recommendation to source the uid from boss_chat. The description adds nothing further about the parameter, 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 gives a specific verb+resource: generating a structured summary plus next-step suggestions from chat history. It is clearly distinct in kind from sibling utilities like boss_chatmsg or boss_history, but it never explicitly contrasts itself with plausible alternatives such as boss_digest or boss_ai_suggest.

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 block (roles=candidate, candidate_platforms=zhipin, recruiter_platforms=-) does tell the agent when the tool is callable at all, which is genuine usage gating. However, it offers no guidance on when to prefer this summary tool over siblings like boss_digest or boss_history, leaving the choice 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?

With no annotations, the description carries the full burden. It discloses the result size (~40 cities) and the role/platform availability scope, which is genuinely useful context. It does not state that the operation is read-only or describe the return shape, so it falls short of full behavioral disclosure.

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

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

A single compact sentence with the purpose front-loaded, followed by the availability tag. Slightly marred by the redundant duplicated label '可用性: 可用性:' inside the bracket, but the total length is well within bounds.

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 trivial zero-parameter lookup tool with no output schema, the description is nearly sufficient: it names the resource, gives the expected result size, and states the availability scope. Only the read-only nature and the exact return shape are left implicit, which is a minor gap for a tool this simple.

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 takes zero parameters, so the baseline is 4 — there is nothing for the description to disambiguate. It correctly implies a parameterless enumeration, and the schema (empty object, no required fields) is consistent with that.

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?

States a specific verb ('列出' / list) and resource ('支持的城市' / supported cities) plus the approximate cardinality (~40), which tells an agent exactly what it will get. No sibling tool covers cities, so the resource itself differentiates it, though the description never explicitly contrasts with 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 bracketed availability tag ('roles=candidate, recruiter; candidate_platforms=zhipin; recruiter_platforms=zhipin-recruiter') implicitly scopes when this tool is applicable, which is more than nothing. However, it gives no explicit when-to-use guidance, no prerequisites, and no alternatives — usage is only implied by the platform/role constraint.

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 names the targets (expired cache, temp files) but does not disclose whether deletion is irreversible, what 'expired' means, permission requirements, or any safety/rate considerations for a destructive 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 description is a single front-loaded clause with no wasted words. The duplicated '可用性: 可用性:' prefix in the metadata block is sloppy but the actual purpose statement is appropriately terse.

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

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

For a destructive maintenance tool with zero annotations and no output schema, the description is too thin: it omits irreversibility, scope of cleanup, and what a run returns or affects. An agent cannot confidently decide whether to invoke it with 'all' or rely on 'dry_run' first.

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 ('all' = 全量清理, 'dry_run' = 仅预览不删除) are already fully documented in the schema. The description adds no additional meaning about how these flags interact or default behavior, 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?

States a specific verb (清理/clean) and resource (过期缓存和临时文件/expired cache and temp files), which is clear enough to understand the operation. No sibling tools perform cleanup, so differentiation is implicitly obvious, but the description never frames how it relates to the maintenance/sibling 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 only scoping hint is the bracketed availability metadata (roles=candidate, recruiter; platform=zhipin), which limits audience but is not usage guidance. There is no statement of when to run this, whether it is safe to run routinely, or what alternatives exist.

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

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

With no annotations, the description carries the full behavioral burden, yet it discloses almost nothing: it does not explain that reset mutates/clears state, whether set requires prior get, permission requirements, or return behavior. The availability/roles line adds mild access context but no real behavioral traits.

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

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

A single front-loaded purpose clause plus a bracketed availability tag; nothing is wasted. Minor flaw: the duplicated '可用性: 可用性:' is sloppy, but overall the structure is tight.

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 config mutation tool with no annotations and no output schema, the description is minimal: it does not state what config keys exist, what reset does, or what the calls return. Schema params are fully covered, but the behavioral and return gaps leave it only adequate.

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 key, value (仅 set 时需要), and the action enum. The description adds no syntax, format, or constraint details beyond the schema, 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?

States a specific pair of verbs (查看/修改 = view/modify) and resource (配置项 = config items), matching the list/get/set/reset enum. It is clear what the tool operates on, but it never names a sibling or clarifies how it differs from adjacent admin tools like boss_status, so it falls short of full 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?

There is no explicit when-to-use, when-not-to-use, or alternative routing. The only scoping guidance is the availability tag (roles/platforms), which tells who may call it rather than when to prefer it over siblings. Usage is left to inference from the action enum.

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. '读取' implies a read, but it says nothing about whether results are paginated, the shape of the return, rate limits, or auth/permission needs. For a no-annotation read tool this 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?

A single compact sentence front-loads the verb and resource, followed by a structured availability tag. Nothing is wasted, though the duplicated '可用性: 可用性:' looks like a formatting slip.

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 filtered-list tool with no output schema and no annotations, the description covers purpose and filters but omits the return format and the origin of run_id. It is minimally adequate but leaves gaps an agent would have to guess at.

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%: page, run_id, and detail_status are all documented in the schema, including the enum semantics for detail_status. The description's mention of page/detail-status filtering adds nothing beyond the schema, 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?

States a specific verb+resource: '读取持久化 crawl 职位' (read persisted crawl job listings) with a scope qualifier about filtering. An agent understands this retrieves stored crawl output. It does not differentiate itself from sibling crawl tools such as boss_crawl_status or boss_crawl_shortlist, so it lands at 4 rather than 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 says results 'can be filtered by page and detail status' but gives no when-to-use guidance, no alternatives, and does not mention that run_id must come from boss crawl start. Usage is only weakly implied by the read verb.

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 usefully discloses that no BOSS request is made (local-only write), but says nothing about duplicate handling, idempotency, merge/overwrite behavior, or write-side effects of importing into the shortlist.

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

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

A single front-loaded sentence with the core action first and the no-BOSS qualifier second; the availability tag is compact. 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?

No output schema and no annotations, so the description should do more for a 5-parameter write tool. Parameters are fully covered by the schema, but the description omits what the import produces or how the shortlist is affected, leaving the agent without return/effect context.

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

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

Schema description coverage is 100%, so the schema already documents all five parameters (all/selectors mutual exclusion, run_id, note, tags). The description only loosely references the selector source, adding little beyond the schema. Baseline 3 is appropriate.

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

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

States a specific verb and resource: importing selectors from crawl results into the local shortlist, distinguishing it from boss_shortlist_add (manual add) and boss_crawl_results (fetch). However, it does not explicitly name the alternative sibling tools, leaving differentiation to inference.

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: it's the bridge between boss_crawl_results and boss_shortlist_*, and '不请求 BOSS' signals a local, no-network operation. But there is no explicit when/when-not guidance or named alternative (e.g., boss_shortlist_add for single/manual entries).

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 bears the full disclosure burden. It implies a passive read by listing the returned signals, but never states it is read-only, side-effect-free, or what environment (run state) is required; for a simple status read the omission is mild but real.

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

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

A single front-loaded sentence enumerating the read outputs, followed by a compact availability tag. Slightly marred by the redundant '可用性: 可用性:' duplication but otherwise waste-free.

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, no-output-schema read tool the description conveys the salient return fields (cursor, counts, progress, risk), which is adequate. It stops short of explaining progress units, risk-state meaning, or error behavior for an invalid/missing run.

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 run_id is already documented as the crawl run identifier returned by boss crawl start. The description adds no syntax, format, or sourcing detail beyond the schema, 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?

Names a specific verb (读取/read) and enumerates the resource facets it returns: crawl page cursor, job count, detail progress, and risk state. This distinguishes it reasonably from listing siblings like boss_crawl_results, though it never explicitly contrasts with 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?

No when-to-use, when-not-to-use, or alternative guidance. The availability tag (roles=candidate, platforms=zhipin) is a precondition but does not tell the agent when this status check is warranted versus e.g. boss_status or boss_crawl_results.

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 genuine behavioral constraint (candidate role, zhipin platform only, blank recruiter platform), which is useful. But it says nothing about the read-only nature, permissions, rate limits, or output shape expected of a detail-lookup tool.

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

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

Front-loaded and short: purpose first, then the required parameter source, then availability. Minor redundancy in the duplicated '可用性: 可用性:' prefix slightly hurts polish but nothing is wasted.

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?

Adequate for a simple read-detail tool with full schema coverage and no output schema requiring explanation, but thin overall: it omits error/availability behavior when the platform/role constraint fails and gives no indication of what the detail response contains.

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 are already documented. The description adds only the provenance of security_id (from search/recommend), which marginally helps the agent source the value but adds no syntax or format detail beyond the schema. Baseline 3 is appropriate.

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

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

States a specific verb+resource (查看职位详情 / view job details), so the action is unambiguous. However, it does not distinguish this tool from nearby siblings like boss_show or boss_hr_jobs_detail, leaving the agent to infer the difference.

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

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

Provides a provenance hint for the required parameter (security_id comes from search/recommend results) and an availability qualifier (roles=candidate, candidate_platforms=zhipin), which implicitly tells the agent when it applies. It does not state when to prefer this over other job-detail tools or any explicit exclusions.

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 states the tool is read-only ('只读日报') and documents the md output option, but omits auth requirements, rate limits, or return format details. Adequate but with clear 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?

One front-loaded sentence states the purpose, followed by a bracketed availability note. The note contains a redundant '可用性: 可用性:' but overall the description is appropriately sized and focused.

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

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

For a read-only composite report with no annotations and no output schema, the description gives purpose, format, and availability. It lacks return value details and alternative-tool guidance, leaving gaps an agent would need to call 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%, so the schema already documents all three parameters. The description adds no parameter-level syntax or constraints beyond the schema; 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?

States a specific verb ('汇总' / summarize) and enumerates the resources: new jobs, follow-up conversations, and interview items as a read-only daily report. It does not explicitly differentiate from siblings like boss_stats or boss_pipeline, so sibling differentiation is absent.

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

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

Provides clear context via the availability tag (roles=candidate, candidate_platforms=zhipin) and the scenario '支持 md 输出便于邮件/飞书直发'. It does not name when-not or alternative tools, so it stops short of explicit 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?

No annotations are provided, so the description carries the full burden. It usefully discloses the four areas it inspects, but says nothing about whether it mutates state, whether it requires prior authentication, or what output the caller should expect from a diagnostic run.

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?

Front-loaded with the core purpose in a single compact sentence. The bracketed availability suffix is a bit noisy and contains a duplicated '可用性: 可用性:' token, but overall it is tightly sized with 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 zero-parameter, no-output-schema diagnostic tool, the description covers the essential scope of what gets checked and who may run it. Nothing critical is missing, though a note on whether it is read-only would round it out.

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 takes zero parameters and the schema is empty, so there is nothing for the description to disambiguate. Baseline 4 applies 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?

States a specific verb (诊断/diagnose) and enumerates the concrete resources it inspects: local runtime environment, dependencies, login state, and network connectivity. This is clearly distinct from the many action-oriented siblings (apply, greet, chat), though it does not explicitly name a sibling like boss_status as an 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 bracketed availability line (roles=candidate, recruiter; platforms=zhipin) gives implied context about who can use it, but there is no explicit when-to-use guidance, no prerequisites, and no routing between this and any alternative diagnostic/status 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, the description carries the full behavioral burden. It says this is a 'request' exchange but doesn't disclose whether it triggers a notification to the other party, requires mutual consent, has rate limits, or what happens on rejection — all material for a social/mutating 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 front-loaded in a single short clause, with the constraint relegated to a bracketed tag — good structure. Minor deductions for the stuttering, duplicated '可用性: 可用性:' label that wastes a few characters.

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 no output schema, the description covers what it does and who can use it, which is minimally sufficient. It omits expected outcome (does the exchange complete immediately or require the contact's approval?) and failure behavior, leaving meaningful gaps for an interaction 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?

Only one parameter (security_id) with 100% schema description coverage ('联系人的 uid（推荐）或 security_id'), so the schema already fully documents it. The description adds no syntax or format meaning beyond mentioning the exchange channel, 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?

States a specific verb+resource (request to exchange contact info: phone or WeChat), which is clear and distinguishable from the recruiter-side sibling boss_hr_exchange. The trailing availability tag further scopes it to candidate/zhipin, though the double '可用性:' duplication slightly muddies the phrasing.

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 constraint (roles=candidate; candidate_platforms=zhipin; recruiter_platforms=-) implicitly tells the agent this tool is only for candidate sessions, which is useful routing context. However, it never explicitly names alternatives like boss_hr_exchange or states when not to use it, leaving the comparison 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?

With no annotations, the description carries the full burden. It usefully discloses that job_id/security_id/boss_name are redacted by default and that HTML always omits platform identifier, recruiter name, and salary, plus availability limits. It omits file-writing side effects (overwrite behavior), permission/auth needs, and rate limits, which matters for a tool that writes output files.

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, format options, URL reuse, and redaction behavior are front-loaded in a compact multi-sentence block. The trailing availability string is slightly redundant ('可用性: 可用性:') but overall it is 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 and no annotations, the description covers the important redaction/format behavior but leaves return-shape and file-output semantics to the parameter descriptions (e.g., output_file/stdout). Adequate but there are clear gaps around side effects and the result envelope.

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 14 parameters and the baseline is 3. The description only adds the default-redaction and HTML-omission behavior, which partly overlaps the include_private parameter's own description, so it adds marginal meaning 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 specific verb and resource: it exports search results as CSV/JSON/HTML files, and clarifies that BOSS Zhipin search-page URLs reuse the web filter conditions. This lets an agent distinguish it from siblings like boss_search or boss_clean, though it never names a specific sibling to differentiate 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?

It implies the tool is for exporting search results and that a search-page URL can supply filters, plus an availability constraint (roles=candidate; zhipin). However, it never says when to choose this over boss_search/boss_crawl_results, nor any explicit exclusions, so usage is only 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 burden. It usefully discloses that the operation does not persist ('不落库'), signaling a read-only preview with no side effects, and it scopes the read to a single page. It stops short of describing pagination behavior, return contents, or any rate/auth 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?

A single, front-loaded sentence stating the operation, scope, and non-persistence caveat. Minor defect: the duplicated '可用性: 可用性:' token, otherwise no wasted text.

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 list tool with no output schema and no annotations, the description covers the essentials – what it lists, the page scope, and the no-persistence caveat. It is still thin on return shape and how paging interacts with available results, leaving some inference to the agent.

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

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

Schema description coverage is 100% – the single 'page' parameter is documented as 页码 in the schema. The description's '单页' (single page) phrasing reinforces pagination but adds no syntax or format detail beyond the schema, 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?

States a specific verb (预览/preview) and resource (BOSS 职位收藏单页 – BOSS job favorites, single page) plus the extra scope of 有效状态 (validity status). An agent can tell this is a paginated favorites-listing tool. It does not, however, name or distinguish itself from near-neighbors such as boss_shortlist_list or boss_preset_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 availability tag declares the intended audience and platform (roles=candidate; candidate_platforms=zhipin; recruiter_platforms=-), which tells an agent when the tool applies. However, there is no guidance on when to prefer this over similar list tools, nor any stated prerequisites or exclusions beyond the role/platform filter.

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

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the selection criteria (unread, stale, interview), which is useful, but says nothing about whether the operation is read-only, what permissions/auth are needed beyond the role tag, or what the result looks like. For a mutation-free filter tool this is a notable gap.

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

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

A single front-loaded sentence states the purpose before the bracketed availability metadata. It is appropriately sized, though the availability tag contains a duplicated fragment ('可用性: 可用性:'), a minor structural 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?

With one optional parameter and no output schema or annotations, the description is nearly complete on purpose but leaves the agent without usage routing, safety profile, or return-format expectations. Adequate as a minimum viable definition 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 description coverage is 100%: days_stale is fully documented in the schema as the staleness threshold. The description adds no syntax, format, or default information beyond what the schema already provides, so baseline 3 applies.

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

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

States a specific action (筛出/filter out) on a specific resource (候选项 needing follow-up) and enumerates the three qualifying criteria (未读/unread, 超时未推进/stale, 面试/interview). This lets an agent distinguish it reasonably well from generic pipeline or list siblings. However, it never explicitly names which sibling to use instead, so it stops short of full 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 lists what gets filtered but gives no when-to-use guidance, prerequisites, or alternatives (e.g. boss_pipeline or boss_digest). The availability tag (roles=candidate) is an access constraint, not usage guidance. An agent must infer 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?

No annotations are provided, so the description carries the full burden. Greeting is a mutating, outreach action with side effects, yet the description never states whether it sends a message, is rate-limited, or is irreversible. The availability constraint is the only behavioral context given.

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

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

Two short sentences that are front-loaded with the core action. It is slightly marred by the duplicated '[可用性: 可用性:' text, indicating a formatting glitch.

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-required-param action with no output schema, the essentials are covered. However, with no annotations and no disclosure of side effects, success/failure behavior, or limits of a write-like outreach, it falls short of complete for an agent to invoke confidently.

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 (job_id, security_id) are fully documented in the schema. The description merely restates '需要 security_id 和 job_id', adding no meaning beyond the structured field 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?

States a specific verb and target: '向招聘者打招呼' (greet the recruiter). An agent understands the action, but the description never distinguishes it from the closely related boss_batch_greet or explains the single-vs-batch scope.

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

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

The availability clause (roles=candidate, candidate_platforms=zhipin) implies a calling context, but there is no explicit when-to-use guidance and no reference to alternatives like boss_batch_greet for bulk greeting.

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 supplied, so the description carries the full behavioral burden. "查看" implies a read-only, non-destructive operation, but nothing is said about scope, ordering, pagination, or what window of history is returned, leaving an agent to guess at the result set.

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?

One short line with the purpose front-loaded and no wasted prose. It loses a point for the duplicated label "可用性: 可用性:" and a trailing"-" placeholder, which are careless artifacts rather than useful content.

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

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

For a zero-parameter read tool with no output schema and no annotations, the description should at least indicate what the returned history contains (jobs viewed? candidates?) and roughly how much. The availability constraint is a useful addition, but the return-content gap keeps it merely adequate.

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 takes zero parameters, so there is nothing for the description to disambiguate; the schema is an empty object with no properties to document. Baseline 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?

States a specific verb+resource ("查看浏览历史" / view browsing history), so an agent immediately knows what it returns. However, it offers no differentiation from the many other list/history-shaped siblings (boss_crawl_results, boss_chatmsg, boss_stats), so the agent must infer scope from the name alone.

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 block gives a precondition (roles=candidate, candidate_platforms=zhipin), which tells the agent when the tool is callable. It does not, however, name any alternative tool or say when-not to use this one, so guidance remains 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 behavioral burden. It discloses important constraints: it requires explicit operator approval before passing yes=true and states '不自动下载或重试'. However, it does not explain the side effects of accepting, reversibility, or what the tool returns on success or failure.

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 purpose and the critical operational caveat. It loses a point due to the duplicated token '可用性: 可用性:' and inline availability metadata that adds minor clutter.

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

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

Given the absence of annotations and output schema, the description covers the main target and safety gate but omits what happens after approval, how results/errors are surfaced, and how it relates to sibling resume actions. The schema fully documents parameters, so invocation is possible, but operational expectations are underspecified.

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 mainly reinforces the yes parameter semantics already present in the schema ('操作者已明确批准同意这条请求') and adds no meaningful detail about friend_id, message_id, 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 clearly states a specific verb and resource: '同意指定候选人的附件简历请求' (approve a candidate's attachment-resume request) in recruiter mode. It is distinguishable from siblings by the accept/approve action, though it does not explicitly name or differentiate itself from related tools like boss_hr_download_resume or boss_hr_request_resume.

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

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

It provides clear invocation context: recruiter mode and a candidate's attachment-resume request. It also gives an explicit condition for setting yes: '仅在操作者明确批准后传 yes=true'. It does not list alternatives or explicit when-not-to-use cases, but the context and consent condition are adequate.

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 behavioral burden and discloses two meaningful non-obvious behaviors: it will not automatically agree to access and will not overwrite existing files. It also limits scope to already-allowed received attachments. It could add error/return behavior, but the key side-effect guarantees are present.

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 concise sentence with constraints front-loaded before the availability bracket. It loses a point for the duplicated '可用性: 可用性:' typo and for embedding availability in prose rather than cleaner structured metadata.

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 tool with three fully documented parameters and no output schema, this is largely complete: it states the mode, target, preconditions, and side-effect constraints. It does not describe result/error shape, but that is a minor gap given the straightforward file-download behavior.

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

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

Schema description coverage is 100%, so the baseline is 3. The description does not add material parameter-level meaning beyond the schema; '已收到' and '附件简历' loosely echo the message_id and attachment concepts already documented. No parameter semantics gap to compensate for.

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 ('下载指定候选人已收到且允许访问的附件简历' — download a specified candidate's received and accessible attachment resume) with clear scope and constraints. It differentiates from related siblings such as boss_hr_resume and boss_hr_accept_resume by explicitly noting it only downloads already-permitted attachments and does not auto-consent.

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

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

Provides clear context: recruiter mode, only for received/accessible attachments, and explicitly says it does not automatically consent or overwrite files, implying when it is not appropriate. It does not name alternative tools explicitly, so it misses the highest bar but is not vague.

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?

Since no annotations are provided, the description carries the behavioral burden. It discloses that the tool requires explicit operator approval and does not send read receipts, which are meaningful side-effect details beyond the schema's 'yes' field. It could mention irreversibility or response behavior, but it is not silent.

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

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

The description is a compact single sentence with the core action and key caveats front-loaded. The availability suffix is structured but contains a duplicated '可用性:' typo, which 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?

For a 9-parameter mutation tool with no output schema, the description covers the action, approval requirement, and read-receipt behavior, and the schema covers all parameters. However, it does not mention success/failure behavior, return values, or when to prefer sibling greet tools, so it is 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?

Schema description coverage is 100%, so all nine parameters are already documented inline (e.g., yes, dry_run, geek_id). The description adds only the approval-gate context already mirrored by the 'yes' parameter, so no substantial extra parameter semantics are provided.

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 specific action ('发送首次招呼' / send initial greeting) and resource ('招聘者模式' / recruiter mode, single-session establishment). It implies distinction from sibling tools like boss_batch_greet or boss_hr_reply via '单次' and '首次', though it does not name alternatives 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?

It gives clear context: recruiter mode, first greeting, single session, and a hard precondition ('需操作者明确批准'). It does not explicitly list when not to use it or name sibling alternatives, but the '首次' and '单次' framing strongly implies it is not for batch greetings or replies.

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 carries the burden for behavioral disclosure. '读取' indicates a read-only operation and the object of the read is specified, but it does not state side effects, auth requirements beyond the embedded availability line, or pagination/return behavior beyond the page parameter.

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 action-first, but it contains a duplicated '可用性: 可用性:' prefix that adds noise. Overall it is compact 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?

For a simple two-parameter read tool with no output schema, the description names the main return contents (full cards and first-chat parameters) and role/platform constraints, which is adequate. However, it does not explain what '首次开聊所需参数' looks like or how the results are ordered/paginated, leaving some ambiguity.

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

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

Input schema coverage is 100% and both parameters already have descriptive labels ('招聘职位的加密 ID', '页码'); the description adds no parameter-specific meaning. The baseline of 3 applies because the schema does the work.

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 specific action ('读取' / read), a specific resource ('推荐牛人完整卡片' recommended-talent full cards), and an additional deliverable ('首次开聊所需参数' first-chat parameters). It clearly goes beyond the tool name, though it does not explicitly contrast itself with sibling 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?

It explicitly scopes the tool to recruiter mode ('招聘者模式') and to the zhipin-recruiter platform in the availability metadata, and the '首次开聊' phrasing signals the intended use case. It does not name alternative tools or exclusion conditions, so it stops short of a 5.

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

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

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.