Wever Labs Agentic Rails

Evaluation cost check

wever_evaluation-cost-check

Read-only

Agent Evaluation: submit one evaluation run’s cost and latency figures with its stated budget: the total budget, the per-task cost cap, the task time cap and the percentile it applies to (median, 95th or slowest), the run’s task count, total cost and median, 95th percentile and slowest task times, each cost component (agent model calls, judge model calls, tool calls, compute, human review, storage or other) with its cost, and optionally each task’s cost and time. The signed report compares the total, the cost per task and the task time with the budget and caps, adds up the components against the total, and names a total over budget, tasks over the cost cap and task time over its cap, then every component with no cost, components that differ from the total by more than one part in a hundred, tasks with no recorded cost and single tasks over the time cap, with the fix for each. This reads one evaluation run’s cost against its own budget: an agent budget setup’s controls are wever_budget-controls-check, transactions against spending rules are wever_spending-anomaly-check and a forecast of spend is wever_budget-forecast-brief. Verdict over_budget, cost_gaps, cost_unverified or within_budget. POST /api/evaluation-cost-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": {
      "budget": "<budget>"
    },
    "name": "wever_evaluation-cost-check"
  }
}

Input Schema

Name	Required	Description
`run`	No
`label`	No	Optional name recorded in the report.
`tasks`	No	Per-task figures.
`budget`	Yes
`components`	No	Each cost component.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 10, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this with 'no network request, fetch, money movement, message, sharing, configuration change or external write'. It adds context annotations cannot carry: the 0.10 USDC x402 paid URL, the 10 signed-wallet free calls per rolling 30 days, the X-Wever-Wallet-Proof binding to the exact JSON arguments and route, and the Ed25519 signed receipt. Slightly dense but genuinely beyond the structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Content is dense and nearly all of it earns its place, but the input enumeration is delivered as one enormous comma-chained sentence, which makes it harder to parse than a short bulleted mapping would be. Front-loading is good (purpose first, then report, then verdicts, then commerce terms), but readability suffers from the run-on construction.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and a nested five-parameter input, the description carries the full burden and meets it: it explains what the report compares, what findings it names (over-budget total, tasks over cost cap, time over cap, missing components, component sums off by more than 1%, tasks with no cost, single tasks over the time cap) and that each comes with a fix. Nothing an agent needs to call this correctly or interpret the result is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 60%, so the description has to compensate, and it does: it enumerates budget total, per-task cost cap, the time cap plus the percentile it applies to (mapping median/95th/slowest to p50/p95/max), run task count, total cost and the three latency figures, and the component kinds (agent model, judge model, tools, compute, human review, storage, other). It also supplies unit examples ('such as 612 USDC', '30 seconds') that the schema only partially hints at.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: submit one evaluation run's cost and latency figures against its stated budget. It then explicitly contrasts itself with wever_budget-controls-check, wever_spending-anomaly-check and wever_budget-forecast-brief, so an agent can separate it from the nearest siblings without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit routing rule ('This reads one evaluation run's cost against its own budget') and names the three alternatives with the condition each covers (budget setup controls, transactions against spending rules, spend forecast). It also states the verdict space, which signals what kind of question this tool answers.

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

All Wever Labs Agentic Rails tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?