Reference Checker: Fake, AI-Hallucinated & Retracted Citations

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

Beyond the annotations (readOnlyHint=true, destructiveHint=false, openWorldHint=true), the description discloses the cost model ($0.01 per reference, no charge for runs that find nothing), the spending cap mechanism, and that the run executes on the caller's own Apify account. It also previews the result shape (one row per reference with OK/CHECK/FIX status), which the annotations do not convey.

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?

Two tight paragraphs: use case and input/output up front, then operational facts (Actor, price, billing, cap). Every sentence carries information, though the Actor URL is slightly noisy and the second paragraph could be trimmed without loss.

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 14 optional parameters and no output schema, the description does the necessary extra work by summarizing the return shape and the billing/pricing behavior. Mode semantics (check vs monitor) are left to the schema rather than the description, but they are well covered there, so nothing critical 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 description coverage is 100%, so every one of the 14 parameters is already documented in structured form, including modes, caps and defaults. The description adds only a high-level mapping of the three input types and the run_max_charge_usd cap, which is marginal beyond the schema — the baseline 3 applies.

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 names a specific verb (check) and resources (bibliography, DOIs, paper titles) and states the exact failure classes it detects: fake/AI-hallucinated, miscited, and retracted references. That framing cleanly separates it from sibling tools like citation_formatter or literature_search, which an agent can rule out from the description alone.

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 a clear when-to-use statement and enumerates the three accepted input forms, so an agent knows how to invoke it. It stops short of explicit exclusions or naming the alternative tools (e.g. citation_formatter) for adjacent tasks, so it lands at 4 rather than 5.

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