Verify claim+source pairs: fetches each cited URL and returns a per-claim verdict (supported / partially_supported / contradicted / unsupported / uncertain / could_not_fetch) with a quoted evidence span from the source.
| Name | Required | Description | Default |
|---|---|---|---|
| claims | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations available, the description carries the full burden of behavioral disclosure. It transparently states that the tool fetches each cited URL and returns a per-claim verdict with a quoted evidence span. Minor omissions like network failure handling are partially covered by the 'could_not_fetch' verdict, but rate limits or side effects are not mentioned.
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?
A single sentence packs all essential information: input, action, output format, and outcome categories. There is no filler or redundant repetition of schema details, making it highly concise and front-loaded.
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?
The description is largely complete for a tool with moderate complexity and no output schema: it explains the input structure, the fetch process, the verdict taxonomy, and the evidence span. It could add operational context (e.g., latency, external request behavior, or what happens when no evidence is found), but the core functionality is sufficiently covered.
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 top-level schema description coverage is 0%, so the description is expected to compensate. It conveys that the input is a list of claim+source pairs, which maps to the 'text' and 'source' subfields, but it does not mention the optional 'context' field or array constraints. The nested schema descriptions help, but the description alone is incomplete for parameter understanding.
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 uses a specific verb ('Verify') and resource ('claim+source pairs'), and lists exact verdict categories, making its purpose immediately clear. It also distinguishes itself from sibling tools ('check_document', 'check_links') by focusing on per-claim verification with evidence spans.
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?
The description clearly implies when to use the tool: when you have claim+source pairs to verify. However, it does not explicitly state alternatives or exclusion criteria (e.g., 'use check_document for full-document checking'), so it lacks an explicit contrast with sibling tools.
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: check_document audits the entire document, check_links focuses solely on link liveness, and verify_claims evaluates individual claim-source pairs with detailed verdicts. There is no meaningful overlap that would cause an agent to pick the wrong tool.
All tool names follow the verb_noun pattern (check_document, check_links, verify_claims), but the mix of 'check' and 'verify' as verbs is a minor inconsistency. The structure is predictable and readable overall.
With 3 tools, the server is well-scoped for its purpose. Each tool earns its place and covers a distinct aspect of citation checking without unnecessary bloat.
The core workflows are covered: whole-document auditing, link validation, and claim verification. Minor gaps exist, such as no standalone URL liveness check or a tool to parse citations independently, but these are workable with the current set.