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

With no annotations, the description carries the full burden of behavioral disclosure. It mentions 'intelligent download' and 'cross-platform' but these are vague and do not disclose concrete behaviors like rate limiting, delays (despite the human_like parameter), failure handling, or IRB/auth requirements. The agent lacks critical context about potential side effects or operational constraints.

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

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

The description is a single, concise sentence that front-loads the core purpose. However, the phrase '支持跨平台智能下载' is somewhat vague/marketing-like and could be replaced with more concrete detail. Still, it is brief and to the point, earning a slightly above-average score.

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

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

The tool is moderately complex (batch download with a human_like parameter, max 10 PMIDs, no output schema), but the description is minimal and does not mention the PMID limit, the effect of human_like, or any return/error semantics. It lacks essential contextual information for an agent to invoke the tool correctly and anticipate outcomes.

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 'pmids' and 'human_like' fully described in the schema. The tool description itself does not add any parameter-level detail beyond what the schema already provides, so the baseline 3 applies. It neither enhances nor contradicts the schema.

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

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

The description clearly states the action (batch download), the resource (full-text PDFs of multiple documents), and distinguishes from sibling tools like pubmed_download_fulltext (which is likely single-download). The phrase '批量下载' conveys a specific verb and resource, 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 implies usage for batch downloading PDFs, but it does not explicitly state when to use this tool over alternatives such as pubmed_download_fulltext for single articles or pubmed_batch_query for querying. No when-not-to-use or alternative exclusions are provided, leaving some ambiguity for an agent deciding between 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?

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It only mentions context window optimization, but does not explain output structure, error handling, rate limits, or what happens with invalid PMIDs. For a query tool, this is minimal transparency.

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

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

The description is a single, concise sentence that directly states the tool's purpose, '批量查询多个PMID的详细信息'. It is front-loaded and does not waste words, though it could be slightly more informative without sacrificing conciseness.

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

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

With no output schema, the description fails to specify what '详细信息' (detailed information) actually includes or how the output is structured. The 'optimized context window' hint is too vague to be actionable. Given moderate complexity and no annotations, the description is under-specified for an agent to fully rely on.

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 provides 100% description coverage for all three parameters (pmids, query_format, include_abstracts), so the baseline score is 3. The description itself adds no further parameter-specific meaning beyond what the schema already provides.

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

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

The description clearly states the tool's function: '批量查询多个PMID的详细信息' (batch query detailed information for multiple PMIDs). This specifies the verb (query), resource (PMID details), and scope (batch), effectively distinguishing it from siblings like pubmed_get_details (single) and pubmed_batch_download (download).

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 a batch use case and mentions 'optimize context window usage', but does not explicitly state when to use this tool over alternatives such as pubmed_get_details or pubmed_quick_search. It lacks explicit exclusions or alternative references, making usage guidance only implicit.

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

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

No annotations are provided, so the description carries the full burden of disclosing side effects. It mentions '管理' (management) but does not disclose that actions like 'clear' and 'clean' are destructive, nor does it explain what happens to cached data, whether operations require special permissions, or what the response format looks like.

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

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

The description is a single concise sentence that front-loads the primary purpose and then mentions cache types. Every word earns its place, with no redundancy or irrelevant detail.

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

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

The tool is simple (1 param, no annotations, no output schema), and the description gives a basic understanding of what it does. However, it lacks details about what 'stats' returns, the difference between 'clear' and 'clean', and the side effects of destructive actions. The description is minimally adequate but leaves 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?

The schema covers 100% of the parameter with a description ('缓存操作') and enum values. The tool description adds no meaningful detail beyond the schema—it only broadly mentions memory and file cache, which maps loosely to the action values. Baseline 3 is appropriate since the schema does the heavy lifting.

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

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

The description clearly states the tool's purpose with a specific verb+resource: '获取缓存统计信息和状态' (get cache statistics and status). It also mentions support for memory and file cache management, which distinguishes it from sibling tools focused on search, download, and other PubMed 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?

Usage is implied by the tool's name and description—it is clearly for inspecting or managing the PubMed cache. However, there is no explicit guidance on when to use it versus alternatives, nor any mention of prerequisites or conditions that would trigger its 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 full burden of behavioral disclosure. It doesn't mention that the tool is likely a read-only lookup, what the output looks like, whether it performs network calls, or any rate limits. The description only states the high-level action without explaining behavior beyond the literal phrase.

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 extremely brief—a single sentence—which is concise, but it's under-specified. It doesn't use the space to add useful structure or detail. While there is no fluff, the content is too thin to deserve a higher score.

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

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

There is no output schema, and the description doesn't explain return values or how the tool differs from siblings. The reference_type enum is left unexplained, and the description doesn't mention the types of cross-referencing (citing, cited, similar, reviews). For a tool with three parameters and no output schema, the description is incomplete for effective selection and invocation.

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

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

Schema description coverage is 100%, so the baseline is 3. The description does not add any parameter semantics; it doesn't explain the meaning of pmid, max_results, or reference_type. The schema already documents these, so the description adds no extra value here.

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 '交叉引用相关文献' (cross-reference related literature), which is a verb+resource pairing but remains vague about the exact operation. It doesn't specify that it works via a PMID or that it retrieves citing/cited/similar articles, nor does it distinguish from sibling tools like pubmed_search or pubmed_get_details. The mention of fact-checking and deep analysis gives a use case but not operational clarity.

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

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

There is no guidance on when to use this tool versus alternatives. It says it's for fact-checking and deep analysis, but this is too generic to help an agent decide between pubmed_search, pubmed_get_details, or pubmed_cross_reference. No exclusions, prerequisites, or alternative tool references are provided.

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

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

No annotations are provided, so the description carries the full burden of disclosing behavior. It states what the tool detects but does not explain return format, whether it is read-only, any required permissions, or potential side effects. This lack of detail is inadequate for a tool with no annotation support.

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, front-loaded with the core action, and contains no filler. However, it is so brief that it borders on under-specification, missing context that would aid tool selection and invocation.

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's relative simplicity (2 params, no output schema, no annotations), the description is too minimal. It does not mention return values, usage context, or relationship to siblings, leaving significant gaps in the agent's 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?

The input schema already describes both parameters (pmid, auto_download) with 100% coverage. The description adds no additional parameter semantics, so the baseline of 3 is appropriate; it neither enhances nor detracts from the schema's clarity.

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 'detect' and identifies the resource (literature) and the specific aspect (open access status and full-text availability). It is clear, but it does not explicitly distinguish itself from the sibling tool 'pubmed_fulltext_status', which likely has a similar 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?

The description provides no guidance on when to use this tool versus alternatives. There is no mention of scenarios, prerequisites, or exclusions, leaving the agent to infer timing based on the name alone.

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

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

No annotations are provided, so the description must disclose behaviors. It only says 'if available' but does not explain caching behavior (despite the force_download parameter), what happens on failure, whether it saves to disk or returns content, or any access restrictions. Minimal insight beyond the schema.

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 directly states the tool's function. No unnecessary words or repetition, making it highly concise and front-loaded.

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

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

The tool is moderately complex with no annotations or output schema, yet the description omits important context like caching, success/failure behavior, return format, and differentiation from batch download. It is incomplete for an agent to confidently invoke 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?

Schema description coverage is 100%, so the baseline is 3. The description adds no extra meaning beyond the schema; the pmid and force_download parameters are already clearly described. No additional value provided.

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

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

The description states the action (download), the resource (full-text PDF), and the scope (specified literature). It clearly distinguishes from sibling tools like batch download and detection, as it targets a single article's PDF.

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

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

The description gives no guidance on when to use this tool versus alternatives such as pubmed_batch_download or pubmed_detect_fulltext. It does not mention prerequisites, limitations, or exclusions, leaving the agent to infer usage.

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 of disclosing behaviors. It only suggests a read-only 'get' operation, but the schema includes 'clean' and 'clear' actions, which are mutating/destructive. The description fails to disclose these side effects, potentially misleading the agent.

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 short sentence without fluff, but it is under-specified. It lacks any mention of the action parameter or the tool's broader capabilities, so brevity comes at the cost of completeness.

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 one parameter with four actions, no annotations, and no output schema. The description covers only the 'stats' aspect and omits the other actions, leaving the agent without enough information to correctly invoke the tool for 'list', 'clean', or 'clear'. It is incomplete and could lead to misuse.

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% (the 'action' param has a description), so baseline is 3. However, the description adds no meaning about the parameter or its enum values ('stats', 'list', 'clean', 'clear'), which are not self-explanatory. The parameter description '操作类型' is generic, and the tool description fails to explain what each action does.

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 '获取EndNote导出状态和统计信息' (Get EndNote export status and statistics), which is a specific verb+resource and distinguishes from search tools. However, it only mentions the 'stats' aspect and omits the 'list', 'clean', and 'clear' actions defined in the schema, making the purpose appear narrower than actual.

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

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

No guidance is given on when to use this tool compared to siblings like pubmed_fulltext_status or pubmed_cache_info. The description provides no context, exclusions, or alternatives.

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

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It only states the general function without specifying output format, error handling, side effects, or any constraints.

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

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

The description is an efficiently short single sentence, but it is under-specified. It front-loads the core purpose but omits necessary details, making it more under-specified than appropriately concise.

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

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

With 3 parameters, no output schema, no annotations, and 12 siblings, the description is insufficiently complete. It lacks usage context, output details, and differentiation from other tools, leaving significant gaps for the agent.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds no parameter-specific meaning beyond what the schema already documents.

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 extracts key information from literature, with a specific verb and resource. However, it does not differentiate this tool from siblings like pubmed_get_details or pubmed_cross_reference, so it falls short of a perfect score.

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. There are no exclusions or explicit context, leaving the agent without direction on 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 description says 'get' (获取), which suggests read-only behavior, but the schema includes 'clean' and 'clear' actions that are destructive. With no annotations provided, the description carries full burden and fails to disclose these mutating operations, actively misleading users about the tool's capabilities.

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 short sentence, which is concise, but it omits critical information about the action parameter and destructive operations. It is under-specified rather than efficiently complete, so it does not fully earn its place.

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

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

The tool lacks annotations and an output schema, and the description only covers a narrow 'get status' aspect. It does not explain the 'list', 'clean', or 'clear' behaviors, potential side effects, or return values, making it severely incomplete for a multi-action tool with destructive options.

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

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

Schema description coverage is 100%, and both parameters have descriptions in the schema. The tool description adds no additional parameter context (e.g., behavior of 'clean' vs 'clear'), so it does not improve on the schema. Baseline 3 is appropriate.

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

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

The description states it gets full-text cache status and statistics, which gives a basic verb+resource. However, it does not mention the 'list', 'clean', or 'clear' actions available in the schema, so the full scope of tool operations is unclear. It also does not differentiate from sibling tools like pubmed_cache_info.

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

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

There is no guidance on when to use this tool versus alternatives, no mention of prerequisites, and no context for which action to choose. The description implies a read-only status check, but the schema shows additional actions without any usage direction.

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 fully disclose behavioral traits. It mentions that the result includes '全文摘要和详细元数据' (full-text abstract and detailed metadata), but it doesn't clarify read-only nature, error handling, rate limits, or the exact effect of include_full_text. The phrase '全文摘要' is ambiguous, adding to the lack of transparency.

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

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

The entire description is a single, compact sentence that front-loads the key verb and resource. It contains no filler or unnecessary 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 simple 2-param tool with full schema coverage, the description conveys the core function but lacks details about return format, batch handling, and the meaning of 'complete literature information'. Since there is no output schema, more explicit output expectations would improve completeness.

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

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

The schema already describes both parameters: pmids as 'PMID或PMID列表' and include_full_text as '尝试获取全文链接'. The description adds little beyond restating the tool's purpose, and it doesn't clarify how include_full_text interacts with the returned data. Thus it stays at the baseline for 100% 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 tool's action: '获取指定PMID的完整文献信息' (get complete literature information for specified PMIDs). This specifies a verb, resource, and scope, distinguishing it from search tools like pubmed_search and summary tools like pubmed_extract_key_info.

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 the tool is used when you already have PMIDs and need full details, but it does not explicitly say when to use it versus alternatives or mention any exclusions. No usage context or alternative guidance is provided.

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

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

No annotations are provided, so the description must fully disclose behavior. It does state that results are '精简' (concise) and response speed is optimized, indicating reduced output detail for faster performance. However, it does not specify what exactly is omitted from the results, nor does it mention pagination, error behavior, or any rate limits. This vagueness leaves the agent uncertain about the actual output format.

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, tightly written sentence that begins with the core action ('快速搜索') followed by the key result characteristics. Every word earns its place; there is no fluff or redundancy. It is appropriately sized for a simple tool.

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

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

The tool is simple (two parameters, no output schema), and the description conveys the essential purpose of a fast, concise search. However, the ambiguous meaning of '精简结果' and the absence of information about how this differs from the sibling 'pubmed_search' leaves the description incomplete for an agent trying to select the right tool. It lacks explicit details on return structure or any limitations, though the tool's simplicity 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?

The input schema covers both parameters with descriptions ('搜索查询' for query and '最大返回结果数量' for max_results), achieving 100% coverage. The description adds no additional parameter-specific information, so the schema is the primary source of meaning. As per the baseline for high schema coverage, a score 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 a specific verb ('搜索') and resource ('PubMed文献'), and adds the qualifiers '快速' (quick) and '返回精简结果' (returns concise results), showing it performs a fast, simplified search. However, it does not explicitly distinguish itself from the sibling tool 'pubmed_search', which likely offers more comprehensive search functionality, so it doesn't fully differentiate.

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 '快速搜索' implies it is intended for rapid, lightweight searches, and '优化响应速度' suggests a trade-off of comprehensiveness for speed. This gives implied guidance on when to use it (when speed is prioritized), but it does not explicitly state when not to use it or mention alternatives such as pubmed_search or pubmed_get_details, leaving the usage decision to the agent's inference.

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

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

With no annotations, the description carries the full burden for behavioral disclosure. It only mentions returning structured data, but does not describe pagination behavior, rate limits, or what the structured data includes. Schema defaults provide some implicit behavior, but the description adds no explicit context beyond that.

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 without fluff, but it lacks essential contextual information. It is not overly verbose, but it also does not effectively use its brevity to convey key details about the tool's capabilities.

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 search tool with 7 parameters, no annotations, and no output schema, the description is incomplete. It does not explain the return structure, how to leverage sorting or date filters, or the significance of response_format and include_abstract parameters.

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

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

The schema already provides 100% description coverage for all 7 parameters, so the baseline is 3. The description does not add any additional meaning or usage details beyond what the schema already states.

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 searches PubMed and returns structured data for LLM analysis, which is a specific verb+resource. However, it does not distinguish from siblings like pubmed_quick_search or pubmed_batch_query, so it lacks differentiation.

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

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

No guidance is provided on when to use this tool versus alternatives. The description gives no exclusions, prerequisites, or context about its suitability compared to other pubmed_* 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?

There are no annotations provided, so the description carries the full burden for behavioral disclosure. It only states what the tool checks, but does not describe the nature of the check, potential side effects, return format, or whether it is a safe read-only operation. This is minimal disclosure.

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

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

The description is a single concise sentence that directly conveys the tool's purpose. There is no redundancy or wasted words, making it highly efficient.

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

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

This is a very simple tool with no parameters and no output schema, so the description is the only source of context. It lacks details about what specific system components are checked, what the expected response looks like, or any prerequisites. The description is too minimal to fully prepare an agent for invoking 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, so the schema is empty and there is nothing to explain. The baseline for zero parameters is 4, and the description does not need to add parameter details.

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: to check the system environment and the availability of download tools. It uses a specific verb ('check') and identifies distinct resources, and it is clearly differentiated from sibling tools that focus on searching, retrieving, or downloading content.

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 explicitly state when to use this tool versus alternatives, but the mention of 'download tool availability' implies it could be a prerequisite for download operations. This is only implied guidance, not explicit, so it falls short of a 4.

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