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

No annotations are supplied, so the description carries the full burden and does reasonably well: it discloses pagination, ordering (best-matched first), the full shape of each entry, and even cost ('Free · 1 credit'). It does not say whether unresolved references are included or whether resolution happens on demand (latency/coverage implications), which is the main remaining gap for a tool whose core concept is 'resolved'.

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?

Front-loaded with the identity and ordering of the resource, then use cases, then cost. The parenthetical entry-field enumeration is dense but every clause conveys real information about the return payload; nothing is filler.

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 properly takes on the job of describing the return entries (matched corpus paper, printed title/authors/year, raw text, match method/score/verified). Pagination and cost are covered; only edge-case behavior for unmatched references and total-count semantics are unaddressed.

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 only 33% — only paper_id ('Paper UUID or arXiv id') is documented in the schema. The description mentions 'paginated' but adds no meaning for page/page_size beyond their self-evident names and schema defaults/bounds, so it does not compensate for the undocumented parameters, though the parameter names are conventional enough that little is needed.

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 the exact resource ('A paper's resolved reference list'), its pagination and ordering semantics ('best-matched first'), and then enumerates what each entry contains. An agent can distinguish this backward-looking reference audit from forward-looking siblings like citation_walk without opening the 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?

Gives two concrete use cases ('audit what a paper builds on' and 'pick seeds for citation_walk'), which ties it to a specific sibling workflow. There is no explicit when-not guidance, but the backward-vs-forward framing is clear enough to route correctly.

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