citation_context

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

With no annotations, the description carries the full burden and does so well: it enumerates the five statuses (found, contexts_withheld, edge_absent_in_s2, citing_paper_unresolved, cited_paper_unresolved), the fallback chain when S2 lacks sentences, the context_source values, the 50-pair cap, the ID resolution order (DOI, MAG ID, title+year) and the reported route. This is unusually rich behavioral disclosure for a read tool.

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?

Dense but front-loaded: the purpose leads, then intent, then evidence framing, then operational details. Every sentence serves a purpose (statuses, fallback, cleaning/ranking), though the concentration of status and source enumerations makes it somewhat heavy to scan in one pass.

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?

For a tool with no annotations and no output schema, the description fills every gap an agent needs: what is returned (cleaned, ranked sentences with intent and source provenance), the possible result statuses, and the fallback path. Nothing material appears missing for correct invocation.

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, but the description adds real value beyond the schema: it specifies that citing/cited and pairs are alternate forms for single vs multiple edges, names the accepted ID systems, explains the resolution route, and states the 50-pair limit. It does not elaborate on construct_terms or max_contexts semantics beyond the schema wording.

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 precise verb+resource: 'How one paper cites another' with the specific outputs (citing sentences, citation intent categories, influential flag). This is clearly distinguishable from sibling tools like get_citing_papers (which lists citers) and get_references, since it targets the content and character of a single citation edge.

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?

It gives an implied use case ('Evidence for whether a citation edge carries the cited idea or is a passing mention'), which frames the decision context. But it never explicitly says when to use this over get_citing_papers, get_references, or fulltext_oa alternatives, nor any exclusions, so usage remains inferential.

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