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 shape of the result (a completeness score, a list of missing/weak items, follow-up questions, placeholder detection), which implies a non-mutating read. However, it never states that the resume is left unmodified or how it behaves on unreadable/missing files, which matters because optimize_resume is a sibling that does mutate.

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 content is front-loaded and dense, with the core purpose first and the optional JD behavior last. The trailing English sentence partially restates the Chinese clause, which is mild redundancy rather than 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?

There is no output schema, but the description compensates by enumerating the report contents an agent should expect. Combined with the schema's mutual-exclusion note for path/content, an agent has enough to invoke it correctly; only edge-case behavior (file not found, non-resume input) is 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 100%: jd, path and content are each documented, including the 与 content 二选一 / 与 path 二选一 constraint. The description restates only the optional JD keyword-matching role and adds no format or resolution detail beyond the schema, 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?

The description gives a specific verb+resource (分析简历结构与完整度) and enumerates concrete outputs: 分区识别, 完整度评分 0-100, 缺失/偏弱项, 问题清单, 占位符检测, plus optional JD 关键词匹配. This makes it unmistakably an analysis (not a mutation) operation, distinguishable in kind from import_resume/optimize_resume/export_resume. It never names a sibling or states the boundary explicitly, so it falls just 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?

Usage is only implied: the tool is for assessing a resume, and the optional JD parameter is flagged as 可选 for keyword matching. There is no guidance on when to pick this over optimize_resume (e.g., analyze first, then optimize) or on preconditions such as the resume already being imported.

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 usefully discloses that PDF export auto-detects Chinese fonts (PingFang/Noto/雅黑), but never states that it writes/overwrites a file on disk, whether parent directories are created, or what happens on 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?

Short and front-loaded, with the core operation stated first. The English sentence largely re-states the Chinese one, which is mild redundancy but keeps the definition compact.

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-required-param write tool with no annotations and no output schema, key facts are missing: overwrite behavior at out_path, directory creation, and what the call returns. The font-detection note is a nice touch but does not close those 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 all three parameters (format, content, out_path) are already documented in the schema. The description only restates out_path and the format list, adding no syntax, path, or constraint detail beyond the structured fields.

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 (导出/export) plus the resource (Markdown 简历) and enumerates the exact output formats (md/pdf/docx). That is naturally distinguishable from the siblings import_resume, analyze_resume, and optimize_resume without opening a schema.

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 export over its siblings, nor any prerequisites or exclusions. Apart from the format options and the font note, the agent gets no routing guidance at all.

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 return shape {markdown, sourceFormat, warnings}, which hints at partial-failure handling, but says nothing about path resolution requirements, permission/auth needs, file size limits, or error behavior for unsupported or unreadable 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?

Two short sentences, front-loaded with the action and formats, then the return shape. The English sentence largely duplicates the Chinese one and adds only 'PDF/Word' phrasing, which is minor redundancy rather than 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?

For a single-parameter import tool with no annotations and no output schema, the definition covers what it does, which formats it accepts, and what it returns. Remaining gaps are secondary details like error handling for unsupported or corrupted files.

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 'path' parameter is fully documented in the schema, including the supported extensions. The description merely restates the same format list, adding no new semantics such as whether relative paths resolve against a workspace root. 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 ('Import a resume file and convert it to markdown text') and enumerates supported formats, so the tool's job is unambiguous. It does not explicitly contrast itself with siblings analyze_resume/optimize_resume/export_resume, though the import/convert framing is distinctive enough to separate it from those.

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: the format list (.md/.markdown/.txt/.docx/.pdf) tells the agent which inputs qualify, and 'import' suggests this is the entry step before analyze/optimize. There is no explicit when-to-use, when-not-to-use, or named alternative among the sibling tools.

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

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

With no annotations, the description carries the full burden and does well: it discloses the credential-dependent branching, the mode=host-llm fallback payload, and the honesty constraint against fabricating employers or numbers. Missing details are minor (no note on output format length, cost, or latency of the LLM path).

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 action and the honesty constraint are front-loaded, and the bilingual restatement is compact rather than padded. The Chinese and English halves overlap considerably, which is slight redundancy but not enough to hurt selection.

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-parameter, no-annotation, no-output-schema tool, the description covers what matters: what it does, how it behaves with and without API keys, and what comes back in each mode. An agent can call it correctly without further reading.

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 schema documents all three parameters (jd, content, extra_info) in Chinese. The description only gestures at parameters indirectly via 'JD alignment' and the no-fabrication rule; it adds no syntax, format, or priority detail beyond the schema, 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 verb+resource (polish/optimize a resume) and qualifies the scope with concrete techniques — STAR, quantification, JD alignment — plus the hard constraint 'never fabricates employers or numbers'. It does not explicitly name a sibling to contrast with (analyze_resume is the closest overlap), 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?

It explains the two execution paths clearly: call the LLM directly when DEEPSEEK_API_KEY/OPENAI_API_KEY is configured, otherwise return mode=host-llm with instructions for the host model. That is useful environmental context, but there is no guidance on when to pick this tool over analyze_resume or import_resume, 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.