Verify factual claims against provided evidence, identifying unsupported statements and retaining uncertainty.
Check claims against supplied evidence, retaining uncertainty and unsupported claims.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | ||
| claims | Yes | Factual claims to check; at most 1000 per request | |
| evidence | Yes | Source text, or a list of {id, text} documents | |
| auto_accept | No |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only and open-world hints; the description adds a meaningful behavioral trait beyond that: unsupported claims are retained and uncertainty is preserved. This helps the agent avoid expecting every claim to be definitively resolved or dropped, though it does not cover response format or other operational details.
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?
The description is a single terse sentence with no filler. The core action and the key behavioral caveat are front-loaded, so it is efficiently scannable.
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 four parameters and no output schema, the description omits the result shape, the behavior of `auto_accept`, and guidance on model selection. Given the many sibling tools, the lack of return semantics and optional-parameter context makes the definition less than fully actionable.
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 schema documents the required `claims` and `evidence` parameters for roughly 50% coverage. The description names those same inputs but adds no extra meaning, and it leaves the optional `model` and `auto_accept` parameters completely unexplained, so an agent cannot confidently set them.
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 ('Check') and names the resource ('claims against supplied evidence'), and it adds a distinguishing nuance by noting that uncertainty and unsupported claims are retained. It does not explicitly contrast with sibling tools like jev_evaluate or jev_review, so it falls short of full differentiation.
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 phrase 'Check claims against supplied evidence' implies the intended context: use it when factual claims must be checked against source text or documents. It does not state when to avoid it or point to an alternative sibling, so the routing guidance is implicit rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.