download_paper

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

With no annotations supplied, the description carries the full burden and does substantial work: it discloses the resolution chain (institutional subscription browser session → Unpaywall OA copy → publisher page), the PDF→CAJ fallback rule, the policy that paywalled content is not bypassed, and that unknown outcomes are not automatically replayed without retry=true. It stops short of saying what authentication is needed for the institutional-session path or what a failed download returns, but the behavioral profile is far above 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?

Four short lines, front-loaded with the purpose and the primary usage gate, then falling back to behavioral detail. Almost every clause earns its place; the '(知网常见)' parenthetical is the only mildly expendable fragment.

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?

An output schema exists, so return values need not be described, and the complex resolution logic is well covered. However, for a tool with 8 optional parameters and zero annotation coverage, the description never says which identifier combinations are valid, where the file is written (subdirectory is undocumented), or what wait_seconds controls, leaving an agent to guess at invocation details.

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% across 8 parameters, so the description must compensate, and it meaningfully explains only format ('auto 优先 PDF，站点只提供 CAJ 时回落 CAJ') and retry semantics, plus an oblique hint that site relates to 知网. The remaining parameters — doi, title, record_ref, subdirectory, wait_seconds — get no explanation of meaning, mutual exclusivity, or which one identifies the paper, leaving real gaps for an 8-parameter tool.

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 opens with a specific verb+resource: '下载全文（PDF/CAJ）' (download full text as PDF/CAJ), which is immediately distinguishable from metadata-oriented siblings such as get_metadata, search, and export_citations. It lacks an explicit naming of those siblings, but the resource and output form are 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?

'仅在用户确实需要文件时调用' is a genuine when-to-use constraint that steers the agent away from this expensive tool when a metadata lookup would do. It also states the condition for retrying (explicit retry=true), though it never names a concrete alternative tool for the case where only metadata is needed.

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