find_related_papers

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

Annotations already cover readOnly, openWorld, idempotent, and non-destructive behavior. The description adds value beyond that by disclosing the external Semantic Scholar dependency, the seed-based recommendation behavior, and the in_library flag on each result. It does not mention failure modes or external service limitations, but the annotation coverage lowers the burden.

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 sentences with no filler. The purpose is front-loaded, the usage trigger comes next, and the seed guidance and result flag are delivered succinctly. Every sentence contributes to correct invocation.

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 read-only recommendation tool with rich annotations and an output schema, the description covers purpose, usage trigger, seeding behavior, and a key output characteristic. It could more explicitly distinguish itself from search_items or get_citation_graph, but the core information needed to invoke it safely and correctly is present.

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 meaningful semantics for item_keys by framing them as seeds and noting that more seeds improve recommendations. However, it does not describe limit at all, leaving a common parameter to be inferred from its name and default value.

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 uses a specific verb ('Find papers related to items in your library') plus the mechanism ('via Semantic Scholar recommendations') and analogies to Connected Papers/ResearchRabbit. This clearly differentiates it from library search and citation-graph siblings, and the 'when the user wants to discover new papers' phrasing reinforces the intended purpose.

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 description explicitly states when to use the tool: 'Use this when the user wants to discover new papers on a topic.' It also gives seeding guidance ('the more seeds, the better the recommendations'). However, it does not explicitly state when not to use it or name competing sibling tools such as get_citation_graph or search_items.

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