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

With no annotations provided, the description carries the full burden, and it communicates that this is a diagnostic, read-only operation ('检查', '验证') and that it is free ('免费'). It does not detail the response format, but for a zero-parameter health check the main behavioral traits are adequately disclosed.

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 states the action, target, and diagnostic purpose without any filler. Every clause adds meaningful information.

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

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

For a zero-parameter health check with no output schema, the description covers what is checked and why. It stops short of specifying the exact response shape, but that is a minor omission given the simple diagnostic nature of the tool.

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

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

The tool has zero parameters and schema coverage is trivially 100%, so the baseline is 4. There are no parameter semantics to add beyond what the empty schema already conveys.

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 opens with a specific verb '检查' (check) and names two concrete resources: the MCP connection and the membership entitlement status of the current API key. This clearly separates it from the sibling tools, which are all content-generation or assessment operations.

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 states the intended use case explicitly: '用于验证 key 是否有效、当前套餐档位' (to verify key validity and current plan tier). It does not mention exclusions or alternatives, but no sibling tool performs a health-check role, so the usage context is clear enough without them.

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 disclosure burden and does it well: it states the tool is free, uses deterministic rule-based calculation, and defines what happens in each mode based on whether answers are provided. It does not discuss partial answer sets, but schema constraints already cover the 60-item limit and score range.

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

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

The description is a single compact sentence with no filler. The primary rule is front-loaded, and the conditional behavior is stated efficiently.

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 single-optional-parameter tool with no output schema, the description covers how to start, how to complete, and what result format to expect. The only notable gap is explicit handling of incomplete answer sets, but the schema's maxItems constraint partially mitigates this.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds value by linking the presence or absence of the answers parameter to completely different outputs. It also clarifies that a full submission of 60 answers is what triggers the career code and report.

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 resource (Holland career interest assessment) and defines a clear two-mode behavior: return 60 questions when answers are absent, or return a three-letter code and full report when 60 answers are submitted. This clearly distinguishes it from the sibling resume, interview, and search 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 makes invocation context explicit: call without answers to fetch the question set, call with answers to obtain the scored interpretation. It does not explicitly name alternatives, but the sibling tools are in clearly different domains, so no exclusion is strictly necessary.

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

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

With no annotations provided, the description carries the transparency burden. It discloses membership requirements, the core scoring behavior, and the return content (score, highlights, improvement suggestions, reference answer). It could add more context about how the evaluation is generated, but the essential behavior is clear.

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 plus a membership note. Every phrase carries information: function, target input, output categories, and access level. The only slight redundancy is '（会员）' and '需会员', but it is minor and reinforces an important constraint.

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

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

For a low-complexity tool with fully documented parameters and no output schema, the description provides enough operational context: required/optional inputs, membership, and expected output types. It lacks explicit routing guidance against sibling tools and a precise output structure, but those are modest 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 question, userAnswer, and optional resumeText. The main description adds no parameter-level 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 action ('对某道面试题的回答打分') and a concrete resource ('某道面试题的回答'). It also enumerates outputs (亮点、改进点、参考回答), making it easy to distinguish from siblings like interview_questions_bank (generates questions) and resume_tailor/rewrite (work on resumes).

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

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

The description clearly implies the use case: evaluate a user's answer to an interview question and provide feedback. It also states an access condition ('需会员'), which is a useful exclusion for non-members. It does not explicitly name alternatives or when-not-to-use 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 provided, the description carries the disclosure burden. It clearly discloses the membership requirement ('需会员') and what the response contains (reference answers, answering ideas, and follow-up questions). It does not explicitly discuss non-mutating behavior, but the predictive phrasing makes that evident; minor gaps remain around failure behavior for non-members, but the key constraints are visible.

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 two compact sentences with no filler: the core purpose is front-loaded, the deliverables are listed in one clause, and the membership gate is stated last. Every sentence earns its place.

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

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

For a generation tool with a required company and job title, the description is largely complete: it names the inputs from the schema, describes the output components, and flags the membership constraint. Because there is no output schema, it wisely describes the return content. It could add guidance on the optional resumeText personalization or the default count, but those are covered by the input schema.

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

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

Schema coverage is 100%, so the baseline is 3. The description's phrase '根据公司与岗位' mirrors the required companyName and jobTitle parameters but does not add extra meaning about count or resumeText; the schema already documents those. The description neither compensates beyond schema nor omits critical parameter context.

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 ('预测可能被问到的面试题'), the resource (interview questions tailored to a company and job title), and the deliverables (reference answers, answering approaches, follow-up questions). This clearly distinguishes it from sibling tools like interview_questions_bank, which suggests a generic question repository rather than company-specific prediction.

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

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

The description implies when to use the tool: when a user wants predicted interview questions for a specific company and job title, and it warns that membership is required. However, it does not provide explicit when-to-use/when-not-to-use guidance or mention alternatives such as interview_questions_bank or interview_coach, so an agent must infer the appropriate routing.

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

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

With no annotations, the description carries the behavioral burden and does well: it discloses that the bank is free, that questions are drawn without answers, and that check returns correctness, the correct answer, and explanation. It does not cover edge cases or rate limits, but the core behavioral contract for an agent is clearly stated.

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

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

The description is a single compact sentence that front-loads the resource and then enumerates each action mode in a parallel structure. There is no filler and every clause contributes actionable information.

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

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

Although the tool has 8 parameters and no output schema, the description plus rich schema is enough: each action's return behavior is stated (tree, questions without answers, check with explanations), and parameter constraints live in the schema. A small gap is that the description does not explicitly link that questions returns questionId for use by check, but this is inferable.

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 schema already documents action enums, count limits, company/section examples, and check-required fields. The description adds only a little by mapping '按大类/企业' to section/company, which reinforces but does not significantly extend 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 names the resource (笔试真题库) and breaks the tool into three explicit actions: sections for the category tree, questions for drawing exam questions, and check for grading answers. This makes the tool's purpose unambiguous and clearly distinct from siblings like resume_rewrite or interview_coach.

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 action-level routing: use sections to browse categories, questions to draw questions by section/company, and check to submit answers for grading. It does not explicitly state when to prefer this tool over sibling tools, but the internal action guidance is sufficient for correct use.

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

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

With no annotations provided, the description carries the behavioral disclosure burden. It transparently states that the tool performs OCR, consumes monthly quota, requires Pro access, and returns structured question/answer/explanation data. It also includes an acceptable-use restriction. It does not mention error behavior or data retention, but the core operation and resource implications are disclosed.

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

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

The description is three concise sentences: the first names the tool and its access/quota context, the second explains input-process-output, and the third states the usage policy. Every sentence earns its place; no redundancy or verbose 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 single-parameter tool with no output schema and no annotations, the description covers the input format, the operation, the return content, and access constraints. It does not describe possible failure cases or empty search results, but for the tool's simplicity the provided context is 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%: the imageBase64 parameter is already documented with format details (base64, optional data URI prefix, ≤6MB suggestion). The tool description only repeats '上传题目图片的 base64' without adding new semantic meaning, so the baseline of 3 applies.

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

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

The description explicitly states the verb and resource: 'OCR 拍照搜题' (upload base64 of question image, recognize question stem, return structured questions, answers and explanations). This clearly distinguishes the tool from its siblings, which are all resume, interview, or health related.

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 the intended trigger ('上传题目图片的 base64') and access constraints ('Pro 专属，月度额度', '仅限合法学习用途'). It does not name alternatives because none of the sibling tools overlap with OCR-based exam search, so no explicit exclusion is needed. A small gap is the lack of explicit guidance on when not to use it beyond the Pro/quota restriction.

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. It discloses the output structure and the access limitation (free once, then membership required), which are important behavioral constraints. It does not explicitly state that the operation is non-mutating, but the diagnostic action implies no modification.

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 deliver the purpose, input, output, and usage restriction with no filler. Important information is front-loaded, and every clause 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?

For a simple one-parameter tool with no output schema, the description is complete: it specifies what to pass in, what results to expect, and the access conditions. Nothing critical is missing for an agent to invoke it correctly.

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

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

Schema coverage for the single parameter is 100%, so the schema already defines resumeText as plain resume full text with length limits. The description repeats this notion without adding new semantic detail, so it meets the baseline but does not exceed it.

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 (resume diagnosis), the required input (resume full text), and the returned outputs (overall score, five-dimension scores, strengths, issues, actionable suggestions). This clearly distinguishes it from siblings like resume_rewrite and resume_tailor.

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

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

The description clearly communicates how to use the tool: feed the full resume text to receive a diagnosis, and notes the free-trial and membership requirement. However, it does not explicitly mention when not to use it or point to alternatives such as resume_rewrite or resume_tailor.

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 discloses the transformation approach (STAR), the return format (full resume and change explanation), and the access requirement (membership). It could say more about side effects or failure behavior, but for a text-transform tool these key behaviors are covered.

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 two short sentences with no filler. It front-loads the core action, then adds method, output, and access requirements. Every clause 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?

For a single-parameter, stateless-seeming rewrite tool, the description is largely complete: it states inputs implied by schema, output structure, method, and membership restriction. It could be slightly more complete by naming when to use it instead of resume_tailor, but that gap is already reflected in the usage_guidelines score.

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

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

Schema description coverage is 100%, so the input parameter is already well documented as the full plain-text resume. The description does not add parameter-specific meaning beyond what the schema provides, which matches the baseline 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 the operation: rewriting a resume using the STAR method and refining wording. It also names the output (full rewritten resume plus change notes), which helps distinguish it from diagnostic or interview-related siblings, though it does not explicitly contrast with resume_tailor or resume_diagnose.

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 intended use is implied: the agent should call this when the user requests a STAR-based resume rewrite. However, it does not explicitly say when to prefer this tool over resume_tailor or resume_diagnose, and it only offers a membership precondition rather than selection criteria.

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

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It does disclose membership requirements and the 35-credit cost, which is useful, but it does not state whether the original resume is modified, what the output format is, or any other side effects or limitations.

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 membership and cost stated immediately. Every phrase contributes meaning, and there is no redundant 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 tool with two plain-text string parameters, the schema handles input documentation well and the description covers purpose, cost, and membership. However, with no output schema, the description does not state the return format, and it does not clarify how this differs from the sibling resume_rewrite 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%, with both resumeText and jdText clearly documented as plain-text resume and JD content. The description adds no additional parameter-level detail beyond restating the general purpose.

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

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

The description clearly states the tool's function: tailoring a resume to a target job JD and highlighting matching keywords and experiences. It is specific and understandable, though it does not explicitly differentiate itself from the sibling tool resume_rewrite.

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 use case is implied: use this when you have a target position JD and want a customized resume. However, there is no explicit guidance on when not to use it or how it compares to alternatives like resume_rewrite or resume_diagnose.

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

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

With no annotations, the description carries the behavioral disclosure burden. It adds useful non-obvious details: the tool is free, uses zero AI, and returns only titles, summaries, and links. '检索' implies a read-only operation, and no destructive or side-effect behavior is suggested.

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, focused sentence with no filler. The primary purpose is front-loaded, and each phrase ('免费', '零 AI', '标题、摘要与阅读链接') adds useful information without redundancy.

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

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

For a simple search tool with two well-documented parameters and no output schema, the description is adequately complete: it states the purpose, input, and returned fields. It lacks explicit usage boundaries or sorting/pagination behavior, but these are not critical for this 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 coverage is 100%, so the baseline is 3. The description mentions '输入关键词' but this largely repeats the query parameter description already in the schema. It adds no meaningful detail about limit semantics or parameter interaction.

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

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

The description uses a specific verb ('检索') and resource ('求职干货文章'), and clearly states the return content (titles, summaries, links). It does not explicitly name or differentiate from sibling tools, but the article-focused resource makes the distinction inferable from tools like interview_questions_bank.

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 intended usage is implied through '输入关键词返回匹配的文章' and the listed content areas, but there is no explicit when-to-use or when-not-to-use guidance, nor any mention of alternatives. An agent would have to infer when this is preferable to sibling tools like interview_coach or resume_rewrite.

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