download_scihub

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

With no annotations, the description carries full burden. It discloses that the tool downloads and saves a PDF, and returns success/failure messages. However, it does not mention potential unreliability of Sci-Hub, rate limits, or legal/copyright issues. The 'fallback connector' is vaguely described.

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 concise and well-structured: a one-line summary followed by Args and Returns sections. Every sentence is informative with no redundancy. It maximizes brevity while covering key points.

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 complexity of Sci-Hub (legal issues, variable availability) and the presence of many sibling download tools, the description lacks completeness. It does not explain the fallback behavior, potential access issues, or how to handle failures. The output is indicated but not detailed. For a tool with no annotations and many siblings, more context is needed.

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 0%, so the description provides essential meaning. It explains that 'identifier' can be a DOI, title, PMID, or URL; 'save_path' is a directory; 'base_url' is a Sci-Hub mirror URL. This adds significant value beyond the schema's defaults and types.

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 that the tool downloads paper PDFs via Sci-Hub, which distinguishes it from siblings like download_arxiv (which is for arXiv) and download_with_fallback (a generic fallback). The verb 'download' and resource 'paper PDF' are specific. However, it does not explicitly differentiate from other download_* tools beyond naming Sci-Hub.

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 guidance on when to use this tool versus alternatives such as download_arxiv or download_pubmed. It mentions an 'optional fallback connector' but does not explain its purpose or when to use it. No prerequisites or context for appropriate use are given.

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