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

Annotations already mark it read-only and open-world, but the description adds substantial context they cannot: the 10-citation cap, the price ($0.005 USDC per call via x402 on named chains), auto-payment behavior for x402 clients, and the upstream data sources (Crossref, OpenAlex, DataCite). It also discloses retraction flagging via Retraction Watch.

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?

Purpose and per-citation outputs are front-loaded before pricing, sources and the worked example. The multi-reference free-sample input is verbose relative to the rest, but each sentence carries operational information rather than 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 fully carries the return-value burden, enumerating status, matched record fields (authors, year, venue, DOI, OA link), corrected issues, APA reference and retraction notice date. Nothing an agent needs to call or interpret the result is missing.

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 60%, and the description compensates meaningfully: it explains that citations may be reference strings 'in any style', bare DOIs, or {title, authors, year, doi} objects, which goes beyond the schema's terse typing. The single-DOI/title alternatives are only lightly tied to their parameters, keeping it from a 5.

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 ('Verify references') and resource (citations), and enumerates the exact per-citation outputs (status verified/mismatch/uncertain/not_found, matched record, retraction flag). This is clearly distinguished from siblings like paper_search or answer_with_sources, which retrieve or generate rather than validate.

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?

'Verify references before you publish or rely on them' plus 'Built for agents that write reports, papers or answers with sources' gives clear when-to-use context. It does not, however, explicitly name or exclude an alternative sibling tool, so it stops short of the 5-level routing guidance.

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