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

No annotations, so the description must carry the behavioral burden. It discloses the return shape ('ranked candidates and the evaluated pool size') and mode behavior, but says nothing about cost, latency, or permissions/API-key needs for what is likely a paid research operation.

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 tight sentences, front-loaded with the tool's action, then parameter semantics, then the return contract. Every clause adds information; no repetition of the name or filler.

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?

No output schema exists, and the description supplies the return contract plus key parameter meaning. Gaps remain around k's default/max behavior and what the two-ID anchoring actually does to results, but the core call decision is fully supported.

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?

With only 20% schema coverage, the description carries most of the load and does so well: it defines seed_ids' cardinality and ordering, all three mode values, and intent's ranking role. It leaves k and the optional rerank flag unexplained (rerank only has schema text), so it nearly but not fully compensates.

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?

States a specific verb and resource: find citation-graph candidates from seed papers. It distinguishes itself implicitly from sibling search_papers through 'citation-graph', but never names an alternative tool to route away from.

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?

Explains the seed ordering rule (first = primary, later = anchors) and defines each mode with when it applies: 'similar' for co-citation/bibliographic coupling, 'citers' for papers citing a seed, 'references' for papers cited by a seed. No explicit exclusion vs search_papers, but usage context is clear.

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