Evaluation design check
wever_evaluation-design-checkAgent Evaluation: submit one evaluation plan as supplied: the agent and task, when the plan was written and when the evaluation first ran, the task set with its size and where the tasks come from, each success criterion with the metric that measures it, each metric with what it measures, whether its computation is written down, its pass threshold, whether a pass is at least or at most it and where the threshold comes from (a requirement, the baseline’s score, a prior run, a published benchmark or nowhere), and the baseline with its scores. The signed report says criterion by criterion whether a metric the plan defines measures it, metric by metric whether it has a sourced threshold and a written computation, and whether a baseline is scored, and names no success criteria, every criterion no defined metric measures (quoting wording such as good, reasonable or as expected), an empty task set and criteria written after the first run, then every metric with no threshold, every threshold with no source, every unwritten computation, no baseline, an unscored baseline, an undescribed task set and a task set that is all generated, with the fix for each. This reads the design of one evaluation before it runs: whether a job’s delivered work meets its acceptance criteria is wever_deliverable-check, whether an implementation’s behavior matches its spec is wever_spec-drift-check and whether a benchmark claim’s figures match the source it cites is wever_benchmark-evidence-check. The checklist of a complete evaluation packet is wever_evaluation-snapshot on https://weverlabs.com/mcp-free. Verdict untestable_plan, design_gaps, design_unverified or design_complete. POST /api/evaluation-design-check. Reads only the material in the call: no network request, fetch, money movement, message, sharing, configuration change or external write. Paid URL: 0.10 USDC per call on Base via x402 exact, with the shared 10 signed-wallet free calls per rolling 30 days. Bind X-Wever-Wallet-Proof to the exact JSON arguments and the tool route. Returns a report with an Ed25519 signed receipt. Contract: /api/agent-evaluation-contract. Human page: https://weverlabs.com/agent-evaluation/.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"criteria": "<criteria>"
},
"name": "wever_evaluation-design-check"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| plan | No | ||
| label | No | Optional name recorded in the report. | |
| tasks | No | ||
| metrics | No | Each metric. | |
| baseline | No | ||
| criteria | Yes | Each success criterion. |