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

No annotations are supplied, so the description carries the full burden and does substantial work: it discloses the return shape (nodes with in-corpus citation counts and hop depth; edges with fuzzy match score and matched reference text), the ordering rule (inbound newest first, outbound competitors first), and the truncation consequence ('a truncated walk is the top of each side'). It omits auth/permission requirements and failure behavior (e.g., paper not in corpus), which keeps it short of a 5.

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?

Front-loaded with the core operation and its direction semantics, then usage routing, then ordering/truncation caveats, then a compact cost tag. Dense but nearly every clause carries information; the parenthetical definitions are slightly repetitive with the direction terms but aid parsing.

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?

With no output schema and no annotations, the description still explains what a caller gets back (nodes, edges, counts, depth) and how ordering and truncation behave, which is what an agent needs to decide and interpret results. Gaps are edge cases: errors for unknown papers and whether max_nodes or depth drives credit cost.

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 only 60%, and the bare enum values 'in'/'out'/'both' get no schema descriptions, so the description's mapping of forward/backward to direction adds real meaning. It also reinforces the 3-hop ceiling for depth and the drop-below-threshold behavior for min_match_score, though max_nodes and paper_id formats are left entirely to the schema.

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+resource ('Multi-hop citation traversal ... from a paper') with scope ('up to 3 hops') and immediately disambiguates direction ('forward (papers citing it), backward (its references) or both'). It also names the sibling it is not ('citation_graph for a flat one-hop page'), so an agent can separate the two without opening a schema.

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?

Gives concrete use cases ('trace lineage, find follow-up work, or build a reading graph') and an explicit alternative with the selecting condition ('use citation_graph for a flat one-hop page'). That is a when-to-use plus a when-to-use-something-else in one clause.

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