get_citation_graph

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

Annotations already declare read-only and non-destructive behavior, and the description adds valuable algorithm details: BFS traversal, depth-limited expansion, and a hard node cap. This goes beyond the safe-read annotation by explaining execution behavior and limits, though it does not cover every edge case like open-world incompleteness.

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?

Three concise sentences, no filler. The first sentence states the core purpose, and the follow-ups add necessary algorithm and boundary details without fluff.

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 rich input schema (100% coverage), output schema, and safety annotations, the description sufficiently covers the tool's behavior. It explains the traversal algorithm, depth limit, and node cap—enough for an agent to invoke it correctly without needing further clarification.

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 100%, so the baseline is 3; the description adds extra semantic value by explaining how depth, max_nodes, and seed_ids work together in the BFS traversal. It does not repeat every parameter but clarifies the core mechanism that gives those parameters 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 uses a specific verb ('Traverse') and names a distinct resource ('the citation graph') with a clear scope: one or more seed papers. It differentiates itself from siblings like get_citations/get_references by emphasizing graph traversal and BFS, not simple list retrieval.

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 clearly conveys the intended use case: multi-hop citation graph traversal with controllable depth and node caps. It does not explicitly mention alternatives or when not to use it, but the BFS and graph-edge language strongly implies this tool is for relational exploration rather than basic lookup.

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