expand_citation_graph

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

With no annotations, the description carries the full disclosure burden; it does add real value by naming the provider fallback order and the return payload (nodes, typed edges, search_id). It says nothing about failure handling for unresolvable seeds, whether results can be partial, latency/rate-limit behavior, or that the operation is purely read-only.

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 core action, followed by the source cascade and then the return value. No filler or restatement of the tool name.

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 five-parameter, no-annotation, no-output-schema tool, the description covers the action and return shape but leaves two parameters undefined and omits any note on limitations of one-hop expansion or seed resolution. Adequate to call it, not fully sufficient to call it correctly.

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 40%, so the description should compensate more. It does clarify that directions mean references/citing/related and that search_id enables export or hydration, but recordView ('short' vs 'full') and limitPerSeed are left entirely to the bare schema, and the relationship between searchId and seeds is not explained.

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 ('Expand one hop from seed papers') plus the three edge types traversed, which clearly separates it from single-source siblings like get_citations or get_webofscience_related_records. It does not explicitly name those siblings as alternatives, so the differentiation is implicit rather than stated.

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 source cascade ('WoS Expanded first when the seed has a WoS UID, then OpenAlex, then Crossref') tells the agent how the tool behaves but not when to choose it over the many per-source search/citation siblings. There are no exclusions or prerequisites, so selection guidance is implied rather than prescribed.

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