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

The description discloses an important behavioral detail beyond the annotations: files are always saved within the workspace project directory. It also indicates the use of current legal permissions, which implies session-dependent behavior. The annotations only state readOnlyHint=false and openWorldHint=true, so this additional context adds meaningful 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 description is a single, compact sentence that conveys the core function and a key behavioral guarantee. Every word is useful and there is no redundancy or 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?

While the description conveys the basic purpose and file location, it does not mention authentication prerequisites (e.g., needing cnki_login or a valid session), error scenarios, or behavior when the paper is not cached. The presence of an output schema reduces the need to explain return values, but given the sibling tools for session management, more contextual guidance would be helpful.

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 60%, with title, subdirectory, and preferred_format described. The tool description does not add extra explanation for the undocumented profile and overwrite parameters. However, it reinforces the workspace-location constraint related to subdirectory, providing some overlap. Overall, the description adds marginal 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?

The description clearly states the tool's purpose: download a paper using current valid CNKI permissions. It names the specific action (download) and the resource (paper), and the mention of saving files in the workspace distinguishes it from read-only tools like cnki_read_online_html.

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 is provided on when to use this tool versus alternatives. It does not mention prerequisites like needing an active CNKI session, nor does it contrast with sibling tools such as cnki_search or cnki_get_metadata. The phrase 'using current legal CNKI permissions' implies a session requirement but does not state when this tool should be selected.

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?

The description adds no behavioral detail beyond the annotation readOnlyHint=false. It does not mention that uncached titles trigger automatic searches, that files are saved to a workspace, or any side effects. The phrase '安全自定义模板' is vague and uninformative.

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, focused sentence that conveys the core purpose and lists output options. No redundant fluff, front-loaded with the action and object.

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

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

The tool has 8 parameters, complex behaviors like auto-searching uncached titles, file saving, and custom templates, but the description only provides a high-level summary. It does not prepare the agent for side effects, prerequisites, or exceptional cases, though schema parameter details partially fill this gap.

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

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

Schema description coverage is 75%, covering most parameters (format, titles, profile, search_id, save_filename, custom_template). The tool description itself does not explain parameters, but the schema carries the weight. Missing limit and offset are standard pagination parameters, so the lack is not critical.

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

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

The description clearly states the verb '导出' (export) and the resource '缓存题录' (cached bibliographic records), listing specific output formats (BibTeX, RIS, EndNote, CSL-JSON, CSV). This distinguishes it from sibling tools like search, download, and read 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 explains that it exports cached records, which implies a prerequisite (having cached data). It does not explicitly exclude alternatives or mention when not to use, but the context is clear enough for an agent to select this for export tasks.

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?

Annotations already declare readOnlyHint and openWorldHint, covering safety and external variability. The description adds no significant behavioral detail beyond "read metadata"; it doesn't mention caching, refresh behavior, or auto-search as noted in the schema, so it stays at baseline.

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 conveys the core function and inputs with no filler. Every word is purposeful.

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 rich schema with parameter descriptions, an output schema, and annotations, the description sufficiently orients the agent to the tool's role. It clearly states the input mode (title or search_id) and the output scope (metadata for single/batch papers), which is enough to select and invoke the tool 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 is 71%, and the description highlights titles and search_id as the primary inputs, which aligns with the schema. It does not explain other parameters (limit, offset, fields, profile, refresh), but the schema provides sufficient descriptions for most, so the description adds only marginal meaning.

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 reads paper metadata (resource) using full titles or search_id (specific inputs), and supports single or batch mode. This distinguishes it from siblings like cnki_search (search) and cnki_download_paper (download), even without naming 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?

The phrase "按完整标题或 search_id" gives clear context: use this tool when you have complete titles or an existing search_id. It does not explicitly outline exclusions or alternatives, but the condition for use is unmistakable.

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?

Annotations already declare readOnlyHint and openWorldHint, so the agent knows it's a safe read operation with external access. The description adds that matching is 'high-confidence' and produces Markdown links, but does not disclose behavior for unmatched titles, caching, or the effect of the min_confidence parameter. It provides some extra context beyond annotations but not comprehensive.

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 that clearly states the transformation. No unnecessary words, and the structure is easy to parse.

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

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

The tool's core behavior is simple, and an output schema exists, so return values are likely documented. However, the description does not mention edge cases like what happens to titles that cannot be matched, how confidence threshold affects linking, or whether the original text formatting is preserved. Given the annotations and schema, it is minimally adequate but lacks completeness for a robust understanding.

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 50%, and the description partially compensates by using '高置信度' to imply the min_confidence parameter's role. The 'text' parameter is already well described in the schema. However, the 'profile' parameter lacks any explanation in both schema and description, and 'search_missing' is only covered in the schema. The description adds some value but does not fully resolve missing parameter semantics.

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

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

The description uses a specific verb ('匹配到' and '添加链接') and clearly identifies the resource (CNKI detail pages) and the task (linking paper titles in text). It differentiates from sibling tools like cnki_search or cnki_get_metadata, which focus on searching or retrieving metadata rather than transforming text into links.

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 purpose is self-evident: use for linking paper titles in text. However, there is no explicit guidance on when not to use this tool or which alternative to choose (e.g., when only a single title needs lookup, cnki_search might be more direct). The usage context is implied 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?

The description adds behavioral context beyond the annotations: it explicitly states that a visible Playwright browser will be opened and that the user must manually complete login, indicating an interactive operation. It also mentions detecting campus network permissions, which provides insight into the tool's decision-making. This is useful information not present in the annotations alone.

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 primary action ('打开可见 Playwright 浏览器') and clearly communicates the login wait. There is no redundancy or 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?

The description is reasonably complete for a login tool with an output schema. It explains the core workflow (open browser, detect permissions, wait for login). It does not detail the various login methods or post-login behavior, but these are covered by parameter descriptions and the output schema. However, it could benefit from mentioning the session impact or what happens after login.

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

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

The input schema has 100% parameter description coverage, with clear explanations for method, profile, timeout_seconds, and remote_access_url. The description adds no additional parameter semantics, but since the schema already covers all parameters, 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 clearly states the tool's purpose: it opens a visible Playwright browser, detects campus network permissions, and waits for the user to manually complete account/institution login. This is a specific action (open browser and login) with a clear resource (CNKI login), and it distinguishes from sibling tools like search, download, and session status.

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 does not provide any guidance on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or reference sibling tools like cnki_session_status or cnki_search. The usage context is implied (login is needed) but not explicitly stated.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds that access is limited by '当前合法权限' (current legal permissions) and that it handles HTML only, not PDF/CAJ. It also mentions '全部或分段' (all or segmented) reading behavior. This adds value beyond the annotations, though it does not detail error handling or pagination.

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 one concise sentence, front-loaded with the primary purpose and immediately states the format exclusion. No wasted 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?

Given the tool has a detailed input schema with 83% coverage and an output schema, the description sufficiently outlines the core purpose and limitation (no PDF/CAJ). It could explicitly name alternative tools for non-HTML formats, but the sibling list and tool name provide enough context. The description covers the main usage for a read-only HTML reader.

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 descriptions cover 83% of parameters, including title, offset, section, read_all, and max_characters with meanings. The main description only references 'all or segmented' which maps to read_all and max_characters but doesn't explain them beyond schema. At high coverage, no extra parameter insight is required.

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: '使用当前合法权限读取全部或分段的 CNKI 在线 HTML 正文' (read all or segmented CNKI online HTML full text with current legal permissions). It explicitly excludes PDF/CAJ, which differentiates it from download_paper among siblings.

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

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

The description provides context that it reads HTML full text and handles only that format, explicitly stating '不处理 PDF/CAJ'. This implies for PDF/CAJ the agent should use a different tool, though no specific alternative is named. The intended use case is clear for reading CNKI HTML content.

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?

Annotations already establish read-only and open-world hints, and the description adds meaningful behavioral context: multi-query planning, deduplication, and a specific re-ranking heuristic. This goes beyond the annotations and gives the agent insight into the tool's non-obvious behavior, though it doesn't mention any rate limits or potential response issues.

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, information-dense sentence that front-loads the tool's core behavior. It avoids redundancy and every phrase adds relevant detail about the internal query planning and re-ranking strategy.

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?

While an output schema exists and the annotations cover safety, the description lacks usage context and does not mention any implications of the multi-query planning (e.g., longer execution time). It does not address how search results are returned or how the agent should interpret the re-ranked output relative to a simple search. Overall, it is adequate but leaves the agent without critical context for effective use.

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 67%, with query, mode, limit, and profile described in the schema. The description itself adds no parameter information, but the schema already provides reasonable meaning for most parameters. Year_from and year_to lack descriptions, but their names and boundaries are self-explanatory. The description neither compensates for nor detracts from 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 explains the tool's internal behavior: planning multiple queries, deduplicating, and re-ranking results based on relevance, abstract, source tier, literature type, and influence. This clearly distinguishes it from sibling tools like cnki_structured_search, but it lacks an explicit verb like 'searches' or a direct mention of the resource being searched (scholarly literature), which prevents 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 does not state when to use this tool versus alternatives. There is no mention of 'use this for general searches' or 'use cnki_structured_search for field-specific queries'. No exclusions or alternatives are referenced, leaving the agent without guidance for tool selection.

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?

The annotations already declare readOnlyHint=true and openWorldHint=true, indicating a safe, non-destructive operation. The description adds value by specifying the exact statuses checked (accessibility, login, and CAPTCHA), which is more detailed than the tool name alone. There is no contradiction with annotations.

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 that efficiently summarizes the tool's purpose with no redundant words. It front-loads the action verb and clearly lists the three aspects checked, making it highly concise and well-structured.

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

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

For a simple status-check tool with one optional parameter and an output schema, the description provides sufficient context. It covers the core functionality precisely, while the output schema and annotations fill in structural details. It could mention when to use it, but that is already accounted for in the usage guidelines dimension.

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 only parameter, profile, is fully documented in the schema with a clear description ('要检查的浏览器身份名称'). The description itself does not add parameter semantics, but since schema coverage is 100%, the schema already carries the burden. The description adds no extra context beyond the schema.

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

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

The description uses the specific verb '检查' (check) and clearly identifies the resource: CNKI accessibility, institution/account login status, and CAPTCHA status. This distinguishes it from sibling tools that perform actions like login, search, or download, making the purpose 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?

The description provides no guidance on when to use this tool versus alternatives such as cnki_login or cnki_search. It simply states what it does without mentioning scenarios or prerequisites (e.g., 'use before login'), leaving the agent without decision support.

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?

Annotations already declare readOnlyHint and openWorldHint. The description adds the behavioral trait of strict execution of caller-specified conditions, which is useful context. However, it does not disclose session requirements, pagination behavior, or rate limits, which are relevant for a retrieval tool.

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

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

The description is a single sentence with no redundant wording, front-loading the core purpose and key behavioral trait. It is highly concise and efficient, earning a perfect score on this dimension.

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 complex with 11 parameters and likely depends on a CNKI session (sibling cnki_login exists). The description does not mention prerequisites, typical use cases, or how it differs from cnki_search in practical terms. Even with an output schema, the description leaves significant gaps in operational 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 64%, so the schema already documents many parameters. The description adds emphasis on fields, Boolean relations, and match modes, which clarifies the conditions array semantics. But it provides no added meaning for other parameters like limit, pages, or metadata_depth.

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 it as a structured CNKI search tool with a specific focus on fields, Boolean relations, and match modes. This distinguishes it from the generic cnki_search sibling, though it does not explicitly name the alternative.

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

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

The description implies usage for precise, structured queries via '严格执行调用者指定的...' but provides no explicit when-to-use or when-not-to-use guidance compared to cnki_search. There are no stated exclusions or alternatives, so the guidance is implied rather than explicit.

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