Verify that one or more cited URLs (a) resolve, (b) match the cited claim text, and (c) aren't retracted. Useful when an LLM produced inline citations and you want to confirm they're real and on-point. Pass DOIs directly (e.g. '10.1038/nature12373') or full URLs. Up to 25 per call.
| Name | Required | Description | Default |
|---|---|---|---|
| citations | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description discloses the three verification actions, the optional claim parameter yielding a match_score, and the batch limit. It implies a read-only operation without explicitly stating it.
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 efficient sentences followed by a concise list of checks. Every clause adds value, no redundancy, and the critical purpose is immediately clear.
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?
Lacks details on the full return format (e.g., whether it returns per-item status, error handling, or response fields beyond match_score). For a tool with no output schema, this leaves agents guessing about the response structure.
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?
The description adds meaningful context beyond the schema: explains that DOIs are accepted, that claim elicits a match_score, and caps at 25. Schema descriptions already cover param roles, so this is additive.
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 clearly states the tool verifies cited URLs against three criteria (resolve, match claim, not retracted). This specific verb-resource combination distinguishes it from siblings fact_check and source_freshness.
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?
Provides a concrete use case ('when an LLM produced inline citations') and input format guidance (DOIs or URLs, up to 25). Does not explicitly mention when not to use, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: cite_check verifies URL resolution and claim match, fact_check verifies factual claims against authoritative sources, and source_freshness checks URL liveness and modification date. No overlap or ambiguity.
All tools follow a consistent snake_case pattern with a verb (check, check, source) and noun (cite, fact, freshness), making the naming predictable and easy to understand.
With 3 tools, the server is well-scoped for its purpose of citation verification. Each tool serves a distinct function without being excessive or insufficient.
The server covers the core aspects of citation verification: URL validity, claim fact-checking, and source freshness. A minor gap might be the lack of a tool to retrieve citation metadata (e.g., author, date), but the current set is sufficient for typical use cases.