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

With no annotations, the description carries the full burden and does disclose the underlying data source (co-citation among citing papers), the returned signals (co-citation frequency, citations, hype, code flag), and the cost ('Free · 1 credit'). It omits error behavior for invalid or non-existent paper IDs and does not explain result-count/pagination behavior.

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: mechanism first, differentiating value second, use cases third, with cost as a trailing tag. No filler, and the most decision-relevant information is front-loaded.

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, the description does the work of enumerating returned fields, which is the main gap it needed to fill for a 2-parameter tool. Remaining omissions (how limit shapes output, failure modes for unknown IDs) are minor but real.

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 50%: paper_ids is documented in the schema and the description adds the useful '1-20 seed papers' range matching the maxItems cap. The limit parameter (default 15, max 50) is never mentioned in the description, so how result volume is controlled is 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?

The description states a precise mechanism (papers co-cited by the papers that cite the seed paper) rather than just restating the name, and it explicitly contrasts with keyword-based discovery: 'the neighbours keyword search misses because they use different terminology.' An agent can tell this apart from citation_graph or search without opening either 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?

It gives concrete use cases ('what else should I read with X', growing a reading list) and the accepted seed range (1-20 papers), which sets a clear context for invocation. It stops short of explicitly naming an alternative tool or stating when not to use it.

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