paper_download

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

With no annotations provided, the description carries significant burden by disclosing the source priority chain (Unpaywall → arXiv → Sci-Hub) and return JSON structure (success, path, size_mb, source). However, it omits rate limiting behavior, network failure handling, and explicit confirmation that files are written to disk (though implied by '保存 PDF').

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 Args/Returns structure is logical and scannable. The essential information (action + source chain) appears in the first sentence. Minor deduction for including return field documentation when an output schema exists, though this redundancy aids readability given the tool's critical file-I/O nature.

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 moderate complexity (2 parameters, file I/O) and absence of annotations, the description adequately covers inputs, outputs, and sourcing behavior. The presence of an output schema reduces the burden to describe return values, yet it provides this detail anyway.

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?

Despite 0% schema description coverage (schema only contains titles), the description fully compensates by providing semantic meaning for both parameters: doi includes a concrete example ('10.1109/tim.2021.3106677'), and output_dir explains the purpose ('保存 PDF 的目录路径') and default behavior.

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 clearly states the specific action (download PDF via DOI), resource type (academic paper), and unique mechanism (multi-source fallback chain: Unpaywall → arXiv → Sci-Hub). This specificity naturally distinguishes it from siblings like paper_batch_download (single vs. multiple) and paper_search (retrieval vs. discovery).

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?

While the description implies single-paper usage through the singular '一篇论文' (a paper) and specific DOI parameter, it lacks explicit guidance on when to prefer paper_batch_download for multiple papers or prerequisites like needing a valid DOI upfront. Usage is inferred but not expressly stated.

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