get_references_by_doi

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

With no annotations provided, the description carries full burden and does an excellent job disclosing behavioral traits. It explains performance characteristics ('比传统方法快10-15倍' - 10-15x faster than traditional methods), technical implementation ('使用OR操作符将多个DOI合并为单个查询' - using OR operator to combine multiple DOIs into a single query), and operational benefits ('减少API请求次数、降低网络延迟影响' - reduces API request count, lowers network latency impact). The only minor gap is it doesn't explicitly mention error handling or rate limits.

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

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

The description is well-structured with clear sections (功能说明, 参数说明, 返回值说明, 使用场景, 性能特点, 技术原理), but it's quite verbose with repetitive information about batch optimization and performance benefits. Sentences like '相比传统方法可实现10倍以上的性能提升' and '比传统方法快10-15倍' convey similar points. While informative, it could be more concise by eliminating redundancy while maintaining clarity.

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 complexity (batch optimization, performance characteristics), no annotations, 0% schema coverage, but with an output schema present, the description is remarkably complete. It covers purpose, usage guidelines, behavioral transparency, parameter semantics, return value details ('返回值说明' section), performance characteristics, and technical implementation. The presence of an output schema means the description doesn't need to exhaustively explain return values, and it provides comprehensive context beyond what structured fields would offer.

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 description coverage is 0%, but the description provides parameter information: '参数说明：- doi: 必需，数字对象标识符（如："10.1126/science.adf6218"）' (Parameter explanation: - doi: required, digital object identifier). This adds meaning by specifying it's required and providing an example format. However, with only 1 parameter total, the baseline would be 4 if no param info was provided; since it does provide some info but doesn't fully compensate for the 0% schema coverage (e.g., doesn't explain if multiple DOIs can be passed or format constraints), a 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: '通过DOI获取参考文献列表（批量优化版本 - 基于Europe PMC批量查询能力）' which translates to 'Get reference list by DOI (batch optimized version - based on Europe PMC batch query capability)'. It specifies the verb ('获取' - get), resource ('参考文献列表' - reference list), and distinguishes from siblings by emphasizing batch optimization and Europe PMC integration, unlike other tools like get_article_details or search_europe_pmc.

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 explicitly provides usage scenarios: '使用场景：大规模参考文献获取、高性能批量数据处理、时间关键的研究任务、文献数据库构建' (Usage scenarios: large-scale reference acquisition, high-performance batch data processing, time-critical research tasks, literature database construction). It also distinguishes when to use this tool by mentioning it's '特别适用于大量参考文献的快速获取' (especially suitable for rapid acquisition of large numbers of references) and '最适合处理大量参考文献的场景' (most suitable for scenarios handling large numbers of references), guiding users away from alternatives for small-scale tasks.

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