get_cross_references

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

No annotations are provided, so the description carries the full burden. It usefully discloses provenance and a quality caveat ('Extracted automatically from explicit citations; not exhaustive'), which tells the agent results may be incomplete. However it omits pagination/limit behavior, performance characteristics, and the fact that the traversal is one-directional per call beyond the direction enum.

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?

Four short clauses, front-loaded with the core action and then the direction semantics. Slightly telegraphic but no wasted sentences; only the trailing provenance note is truly optional.

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?

An output schema exists so return values need not be explained, and the read-only nature is self-evident. The main gap is the required 'citation' parameter, whose expected format is undocumented in both the schema and the description for a 3-parameter tool.

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 description coverage is 0%, so the description must compensate. It does add real meaning for the direction enum (defining 'cites' vs 'cited_by'), which the schema lists only as bare values, but it says nothing about the required 'citation' string format or the 'limit' parameter's role.

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 opens with a specific verb+resource ('Follow citations') and immediately enumerates the two traversal directions, so the agent understands this is a citation-graph walker rather than a text search. It does not explicitly name or distinguish itself from any sibling (search, get_document), but the resource is unambiguous.

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?

Usage is implied by explaining which direction yields which set of provisions, which is enough to pick the right direction value, but there is no statement of when to prefer this tool over search or lookup_public_act, nor any prerequisites or exclusions.

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