citation_check

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

With no annotations present, the description carries the full burden and does so: it discloses cost ($0.005 USDC per call), latency (p99 10000ms), upstream sources (Crossref, OpenAlex, DataCite), the retraction data source (Retraction Watch), and the full set of status outcomes returned. This is unusually rich disclosure for a read-only verification tool.

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 scope are front-loaded before the long em-dash run of return fields, so the essential information lands first. The middle section is dense and run-on, packing output statuses into a single sprawling sentence, but nearly all of it is load-bearing given the absence of an output schema.

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 and no annotations, the description still explains what comes back per citation (matched record, corrected issues, APA reference, retraction flag with notice date), plus cost, latency and source provenance. Nothing an agent needs to decide to call it or interpret results 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%, so the description must add meaning, and it does: it clarifies the citations cap ('up to 10 citations per call'), the accepted input formats (reference strings in any style, DOIs, or {title, authors, year, doi}), and the alternative single-doi/single-title path. It adds concrete format semantics beyond the schema's type declarations.

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 opening clause states a specific verb and resource ('Citation Check ... Verify references'), and the parenthetical 'Hallucinated and Retracted References' scopes it tightly. This clearly distinguishes it from siblings like paper_search or answer_with_sources, which discover or cite sources rather than validate them.

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 an explicit use condition ('before you publish or rely on them') and a target audience ('agents that write reports, papers or answers with sources'). It does not name a specific alternative sibling or state when NOT to use it, so it falls short of a 5.

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