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

With no annotations, the description carries the full behavioral burden and does disclose concrete consequences: seekers can no longer see or apply, and the job drops out of matching. It does not state whether the close is reversible/reopenable or what the response contains, so it is good but not complete.

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

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

Two sentences, both front-loaded: action and prerequisite first, consequences second. No filler, no repetition of the schema.

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

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

An output schema exists, so return values need not be explained, and the description covers the action, auth requirement, and post-close effects. The only meaningful gap is reversibility, which an agent might care about before closing a posting.

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 0% and the description never mentions job_id or its expected format, so it does not compensate for the coverage gap. However, the single parameter is a self-evident identifier matching the described resource, keeping this at the minimum-viable level rather than deficient.

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 (关闭已发布的招聘岗位 / close a published job posting), and the effect clause makes the action unambiguous. It does not name the counterpart sibling (publish_job) to sharpen the boundary, so it stops short of a 5.

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

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

The description supplies a prerequisite (需要 employer 角色) and an implied condition for use (when a posting should be taken down), but gives no explicit when-not or alternative routing against siblings such as publish_job. Usage is therefore inferred rather than spelled out.

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 disclosure burden, and it only covers the role requirement. It says nothing about whether creation is idempotent, what happens on duplicate company names, whether setting is_default silently unsets an existing default, or what failure modes to expect.

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 compact sentence that front-loads the action and the role prerequisite before listing inputs. No filler, though the parameter list reads partly as a restatement of schema property names.

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?

An output schema exists, so return values need not be described, and the role requirement is covered. Still missing for a mutation tool with zero annotation coverage: duplicate-name behavior, the interaction between is_default here and the set_default_company sibling, and error conditions.

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

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

Schema description coverage is 0%, so the description has to compensate, and it does name all three parameters and clarify that is_default means 'set as the default enterprise'. It still does not explain side effects of is_default (e.g. whether it unsets a prior default) or expected format/length for description.

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

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

The description states a specific verb and resource (创建公司信息) and lists the fields it accepts, so the agent knows exactly what the tool produces. It does not, however, distinguish the tool from siblings like set_default_company, even though the is_default parameter overlaps with that sibling's purpose.

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

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

It provides one genuine precondition — the caller needs the employer role — which is real usage guidance. But there is no statement of when to choose this tool over set_default_company or list_companies, and no note about what happens if a company with the same name already exists.

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 employer-role authorization requirement, which is genuine behavioral context beyond the schema, but says nothing about rate limits, what the statistics cover, or whether the result is user-scoped vs platform-wide.

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 sentence, front-loaded with the action and immediately followed by the access constraint. No filler whatsoever.

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?

An output schema exists, so return values need not be described, and the auth requirement is stated. For a zero-parameter read tool this is nearly sufficient, though the scope of the statistics (platform-wide vs employer-scoped) is left implicit.

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 baseline for a parameterless tool 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: '获取平台统计数据' (get platform statistics). It is unambiguous what the tool returns, but it does nothing to differentiate itself from the closest sibling, market_analysis, which an agent might reasonably confuse it with.

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 '(需要 employer 角色)' gives a real access prerequisite, which is useful usage context, but there is no guidance on when to pick this over market_analysis or other analytics-flavored siblings, and no 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 burden. It usefully discloses the required candidate role and the upsert (import-or-update) nature of the call, but says nothing about how updates reconcile with existing data (merge vs replace), size limits on the Base64 payload, or failure behavior. The auth-role disclosure is real added value, but mutation semantics are incomplete.

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

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

The purpose is front-loaded, and the bracketed sections (work experience fields, project rules, attachment rules) are load-bearing given 0% schema coverage rather than filler. There is mild redundancy in the repeated emphasis phrases ('切勿遗漏'), but overall it is dense without being bloated.

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?

An output schema exists, so return values need no explanation, and the description covers the most failure-prone inputs. Still, with 10 parameters and zero schema documentation, the absence of any guidance for the education, languages, certificates and basic_info fields, plus the unaddressed relationship to upload_resume_attachment, leaves meaningful 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 0% for 10 parameters, so the description must compensate, and it does substantial work: it enumerates required subfields for work_experiences and projects and explains the three resume_file_* attachment parameters. It leaves skills, education, languages, certificates and basic_info entirely unspecified, so it is good but not complete.

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 pair (import or update a candidate resume) and clarifies it is an upsert of structured resume data. It clearly separates the parsing burden onto the agent. However, it never distinguishes itself from the sibling upload_resume_attachment, which seems to overlap with the attachment portion of this 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?

It gives a clear precondition (requires candidate role) and a when-to condition for the attachment path (local PDF/Word/image files). But it offers no exclusions and, more importantly, does not acknowledge the sibling upload_resume_attachment, which a reasonable agent would consider for file uploads, leaving ambiguity about which tool to pick.

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 two useful traits: the employer-role requirement and that the result scope is limited to the caller's own companies, and it notes the default company is included. It does not state read-only semantics, ordering, or pagination, 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?

A single, front-loaded sentence that names the resource first and appends the role requirement parenthetically. Nothing is wasted, though it packs the 'default company' detail in without explaining why it matters.

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?

An output schema exists, so return values need not be described. For a simple no-param, read-oriented listing tool, the description covers scope and the access prerequisite; only mild gaps remain regarding read-only confirmation and result ordering.

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 are no parameter semantics to document; the baseline for a parameterless tool is 4. The description correctly implies the implicit filter (current recruiter) rather than suggesting any inputs.

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: listing all company/enterprise entities under the current recruiter, plus the default company. It is clearly distinguishable from mutating siblings like create_company and set_default_company, though it never names them to reinforce that distinction.

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 one prerequisite (requires the employer role), which is genuine usage guidance, but it offers no when-to-use versus when-not-to-use framing and no routing to siblings such as create_company or set_default_company. Usage is implied by the scoping to 'current recruiter' but not elaborated.

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

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

No annotations are provided, so the description carries the full burden. It discloses a genuine behavioral trait — the employer-role requirement — which is useful beyond the schema. It does not, however, clarify read-only nature, response shape, or rate/scope 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?

A single compact sentence with the purpose front-loaded and no wasted words. Efficient and well-structured.

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

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

An output schema exists, so return values need not be explained. But with 0% schema coverage, no annotations, and the location parameter unmentioned, the definition is only minimally adequate for an agent 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 0% and all three parameters (keyword, industry, location) are undocumented in the schema. The description maps only loosely onto keyword/industry (技能/行业) and says nothing about location, leaving one parameter entirely unaddressed.

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 (查询/query) and resource (talent supply/demand for a skill/industry), which is distinguishable from siblings like search_candidates or get_stats. It is clear but does not explicitly differentiate itself from the potentially overlapping get_stats sibling.

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

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

The description supplies a precondition (requires employer role), which is real usage guidance. However, it gives no guidance on when to prefer this over alternatives such as get_stats, nor any exclusions, leaving usage largely 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 and discloses the auth requirement (employer role) and the return content (scoring details plus experience/education). It does not state whether the operation is read-only or otherwise safe, nor any rate limits or side effects, leaving a behavioral gap for a matching 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?

A single, well front-loaded sentence that pairs purpose with the role prerequisite and the return summary. Nothing is wasted, though brevity comes at the cost of the parameter detail noted elsewhere.

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?

An output schema exists, so return values need not be restated. But for a tool with a nested 'preferred' object and an opaque required array at 0% schema coverage, the description does not provide enough to invoke it correctly.

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

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

Schema description coverage is 0% across 3 parameters, so the description must compensate. 'Top-N' loosely hints at max_results, but the critical 'required' (array) and 'preferred' (object) parameters are entirely unexplained in both schema and description, which is a significant gap for a nested-object input.

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 ('匹配候选人' / match candidates) and notes the return shape (Top-N with scoring details, work experience, education). This differentiates it somewhat from sibling search_candidates, though it never names or contrasts 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?

Provides a real prerequisite ('需要 employer 角色' / requires employer role), which implies usage context. However, it gives no when-to-use guidance relative to search_candidates or match_job_requirement, leaving the agent to infer 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 burden. It discloses the employer-role authorization requirement, which is real behavioral context, but says nothing about whether matching writes records, is idempotent, or is long-running.

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, front-loaded with the action and scoped by the role requirement. Slightly wasteful in that '直接传入 job_id' adds little beyond restating the required parameter.

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?

An output schema exists so return values need no explanation, but with no annotations and 0% parameter coverage the description leaves max_results and the side effects of the matching operation unaddressed.

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

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

Schema description coverage is 0%, so the description must compensate. It only gestures at job_id ('直接传入 job_id') without format or constraints, and max_results (default 10) is entirely undocumented in both schema and description.

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

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

States a specific action (执行自动匹配) against a specific resource (已发布的岗位), and the caller learns that job_id is the entry point. It is distinguishable from siblings like search_candidates, though its boundary with match_candidates is not spelled out.

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 one real prerequisite — the employer role — which is genuinely useful routing information. It offers no when-not guidance and does not say how it differs from match_candidates or match_jobs_for_me.

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 role prerequisite and the shape of the result (score-sorted jobs with a breakdown), but says nothing about which resume is used, whether the resume must exist first, or any rate/limits 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?

Two compact clauses, front-loading the purpose and then the return shape; nothing is wasted. It could be marginally tighter but is well structured.

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

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

An output schema exists, so the return details need not be explained, and the description correctly summarizes that result. For a zero-parameter read tool with a role note, this is nearly complete, lacking only the resume-source detail.

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 coverage is complete, so the baseline of 4 applies. There are no parameters whose meaning the description could clarify.

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 (match published jobs) scoped to the caller's own resume, and notes the candidate-role requirement. It implicitly distinguishes itself from the reverse-direction sibling match_candidates, but does not name that sibling to make the contrast explicit.

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

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

It gives a precondition (requires candidate role), which is useful usage context, but offers no when/when-not guidance or comparison to alternatives like search_candidates or match_candidates. Usage is implied rather than specified.

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 full behavioral burden; it does disclose an auth/role requirement and the negotiable-salary default behavior, which is genuinely useful. But it omits whether the job goes live immediately, moderation/reversibility, or error behavior for a mutation tool.

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

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

A single compact paragraph that front-loads the core action and role requirement, then layers supporting details. Every clause carries information 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?

Output schema exists so return values need not be explained, and the description covers auth, currency, and negotiable-salary behavior. For an 8-parameter, 0%-coverage mutation tool it still leaves title, raw_text, and salary_unit semantics undocumented.

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 0%, so the description must compensate; it supplies enum values for salary_currency (data the schema lacks), explains the required/preferred structured conditions, and the dual salary_field negotiable rule. It leaves title, raw_text, and salary_unit (default 'monthly') unexplained, so coverage is partial but adds real value beyond the schema.

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

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

Names a specific verb (publish) and resource (job posting) and adds the required role, so an agent knows this creates a live job listing. It does not explicitly contrast with siblings like close_job or match_job_requirement, but the create-action is unambiguous.

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

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

States a concrete prerequisite ('requires employer role') and the negotiable-salary case ('don't pass both salary fields'), which is useful routing context. However, it never tells the agent when to pick this over siblings such as close_job or create_company, so usage remains 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. It discloses only that a user_id is returned; it does not say whether a new account is created on first use, how the role default is applied, or what happens on invalid/expired codes. For a combined register-or-login mutation, this leaves the key behavioral question (does calling it create a user?) unanswered.

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, front-loaded with the purpose before the return value, with no wasted words. It is terse rather than bloated, though the terseness is part of why other dimensions suffer.

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?

An output schema exists, so the return format need not be explained, but the description still omits the role parameter's meaning, the send_verification_code prerequisite, and any account-creation behavior. For a tool with an undocumented optional parameter and no annotations, this is under-specified.

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

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

Schema description coverage is 0% and the description compensates only partially, implying email and code via '邮箱验证码'. The optional role parameter with its default of 'candidate' is never mentioned, so an agent has no signal about when or why to set it. With three parameters and no schema-level documentation, this is a significant gap.

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 pair on a specific resource: register or log in using an email verification code. An agent can distinguish it from generic auth tools, though it does not explicitly differentiate itself from the sibling send_verification_code, which is clearly its prerequisite.

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

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

No guidance on when to use this versus alternatives. The sibling send_verification_code exists and is evidently required to obtain the code this tool consumes, but the description never mentions that dependency or any precondition. Usage must be inferred entirely from the name.

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 employer-role authorization requirement, which is genuine behavioral context. It says nothing about safe/read-only nature, ranking behavior, result limits, or pagination, so the disclosure is partial rather than complete.

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 short sentence with the precondition parenthesized and front-loaded — no filler. It is efficient, though the brevity shades into under-specification rather than true economy.

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?

An output schema exists, so return values need not be described, but the definition still omits sibling differentiation, parameter semantics at 0% schema coverage, and most behavioral traits. For a search tool with a competing match_candidates sibling, this is not enough for confident invocation.

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

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

Schema description coverage is 0%, so the schema documents neither parameter. The description's phrase 'natural-language search' only hints that query is free text and never explains max_results (default 10) or how results are capped, leaving the parameter contract largely undocumented.

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 ('自然语言搜索候选人' = natural-language candidate search), so the core action is unambiguous. It does not, however, distinguish itself from the sibling tool match_candidates, which an agent could easily confuse with a natural-language search.

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?

Adds one real usage constraint — an employer role is required — which is actionable context. But it gives no guidance on when to prefer this over match_candidates or match_job_requirement, so tool selection between these siblings 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 behavioral burden. It discloses the sequencing prerequisite, but nothing about rate limits/cooldowns, code expiry, single-use semantics, or whether re-sending invalidates a prior code — all material for a code-dispatch tool with side effects.

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

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

A single short sentence with the action front-loaded and the usage condition in a compact parenthetical. Efficient, though the parenthetical could be split for clarity and no return/error expectations are hinted at.

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?

An output schema exists, so return values need not be described. For a prerequisite dispatch tool the core workflow hint is present, but the absence of annotation coverage leaves behavioral details (expiry, throttling, reuse) undocumented anywhere.

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 0% and the only field is an untyped-in-prose 'email' string. The description adds that the email is the destination address ('向指定邮箱'), but no format, validation, or multi-recipient constraints — a modest gain over the bare 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?

States a specific verb and resource: send a verification code to a given email. The parenthetical clarifies its role as a prerequisite to registration/login, which separates it from siblings like register_or_login, though it does not name that sibling 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?

Explicitly says it must be called before register/login, giving a clear trigger condition. It stops short of stating exclusions or naming the follow-up tool (register_or_login) that consumes the code, so routing is implied rather than spelled out.

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 and it does disclose an authorization requirement (employer role), which is valuable. However, for a mutation it does not say whether it overwrites an existing default, what side effects occur, or that changes take effect immediately.

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 with the purpose front-loaded followed by the role prerequisite and parameter note. Nothing redundant, though it is terse enough to leave some gaps.

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?

An output schema exists so return values need not be explained, and the role requirement plus parameter note cover the basics. For a mutation with no annotations, however, it should disclose side effects such as whether an existing default is replaced.

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 0%, so the description must compensate, and it does name and gloss the single parameter as the enterprise entity ID. This adds real meaning beyond the bare 'company_id: string' in the schema, though it does not clarify format or constraints.

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 — '指定默认公司/企业主体' (set the default company/entity) — which is unambiguous and distinguishable from siblings like create_company and list_companies by intent. It stops short of explicitly naming those siblings, so it is clear but not fully differentiated.

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

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

It states a prerequisite ('需要 employer 角色') which usefully scopes who can use it, but gives no when-to-use/when-not guidance or comparison to alternatives such as list_companies or create_company. Usage context is implied rather than spelled out.

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 and does disclose useful behavior: the candidate role requirement (auth need), the accepted formats (PDF, DOCX, DOC, PNG, JPG), and that the local file is read and Base64-encoded. It omits size limits and whether an existing attachment is overwritten, which would round out a mutation 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?

Three front-loaded sentences with no padding: purpose, then when-to-use, then the mechanical how. Efficient, though slightly list-heavy.

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?

An output schema exists so return values needn't be explained. For a mutation tool the description covers role, formats, and encoding, leaving only overwrite behavior and size constraints unstated.

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 0% across 3 parameters, so the description must compensate. It explains file_name and file_base64 (including the Base64 encoding step), which is valuable, but file_type is left entirely undocumented in both schema and description.

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

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

States a specific verb and resource: uploading/supplementing the original resume attachment for the current candidate. It distinguishes itself from sibling import_resume by scoping to the attachment file rather than the resume import itself.

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?

Explicitly names the alternative (import_resume) and the condition that selects this tool: when import_resume was imported without an attachment, or when the user separately needs to update/resubmit the original. Clear when-to-use routing.

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