get_citations

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

With no annotations, the description carries the transparency burden. It discloses direction semantics ('citations' is forward, 'references' is backward), accepted paper_id formats including DOI, and that limit is an upper bound. It does not describe output format or error behavior, but the core behavioral traits are covered.

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 compact, front-loaded with the core benefit, and the Args block is structured without redundancy. Every line contributes useful 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 tool with no annotations and no output schema, this description explains purpose, parameters, ID formats, and direction choices adequately. It stops short of specifying the exact return structure, which would round out the picture, but the tool is still safely invocable.

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?

Since the schema has 0% description coverage, the parameter explanations are essential and are fully provided: paper_id formats, direction values with mappings, and limit semantics. This adds clear meaning the raw schema lacks.

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 names a specific operation (citation snowballing) and the resource (a paper's cited/forward or citing/backward literature). It clearly distinguishes itself from sibling tools like read_paper and search_literature by framing the behavior as citation expansion.

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 '引文扩展（滚雪球）' gives a clear usage context: use this tool when you want to expand from a known paper via its citation graph. It does not explicitly list excluded cases or name alternatives, but the intended use case is evident.

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