s2_citations

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

Annotations already indicate read-only, open-world, and idempotent behavior, so the description does not need to restate those. It adds valuable API quirk information: the endpoint reports no total, so result.total is the returned count (TOTAL_NOT_REPORTED). This goes beyond the annotations and helps the agent correctly interpret the response.

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?

Two focused sentences with no filler. The primary purpose is front-loaded, and the total-count caveat is presented as a separate, useful note. Every word earns its place.

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 presence of an output schema and comprehensive annotations, the description is largely sufficient. It covers the core operation and an important response quirk. However, it leaves out any mention of how to obtain or format the paper_id, and the phrase 'unified envelope' is unexplained, though the output schema may resolve this for the agent.

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 description only clarifies the 'citations' vs 'references' direction concept, which is already present in the schema's direction property. It does not explain paper_id format, limit/offset behavior, defaults, or the required params wrapper. With schema description coverage reported as 0%, the description fails to compensate for the lack of parameter-level meaning.

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 identifies the tool as retrieving papers that cite a given paper or are cited by it, distinguishing it from sibling tools that search, fetch, or recommend papers. It also states the return format ('unified envelope') and scope of the operation, making it easy for an agent to select this tool for citation graph traversal.

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 any guidance on when to use this tool versus alternatives such as s2_search_papers or s2_get_paper. It also does not mention when not to use it or what prerequisites exist (e.g., needing a valid paper identifier). No exclusions or alternative routing are given.

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