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

Annotations only say readOnly and openWorld; the description adds substantial operational context beyond them: the $0.001 USDC per successful call price via x402 across Base/Solana/Arc, that failed calls are not charged, and that unresolvable identifiers return not_found rather than erroring. It also discloses an asymmetry in the output (authors only for DOI and arXiv) and that ISBNs are checksum-validated first.

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 what it does and which registries it hits; pricing and payment detail are trailed at the end where they belong. It is a single dense paragraph using semicolons, so it stays compact but is slightly harder to scan than a bulleted or multi-sentence layout.

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 paid, multi-registry verification tool this covers everything an agent needs before calling: input formats and cap, per-type registry routing, what a success and a not_found look like, output artifacts (BibTeX, APA string, title/year/venue) and the billing model. An output schema exists, so the return-value detail is bonus rather than obligation.

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% and the single parameter is already documented, so the baseline is 3. The description still earns credit by sharpening the accepted formats (ISBN-10/13 explicitly, the arXiv:1706.03762 form) and noting checksum pre-validation, which tells the agent malformed ISBNs are rejected before any registry call.

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 (checks/verifies) and resource (references) plus the exact external registries used per identifier type: Crossref for DOI, arXiv API, Open Library for ISBN. The scope ('up to 5 references') and the verification target make it unmistakable against any sibling, none of which do bibliographic identifier resolution.

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?

Usage context is clear: pass DOIs, arXiv ids or ISBNs and get verified metadata back, which implies the when-to-use case (validating citations in a bibliography). The batch bound of 5 is stated, giving a practical constraint. It stops short of naming alternatives or exclusions (e.g. when to prefer a claim-checking sibling), so no 5.

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