Wever Labs Agentic Rails

Feedback gaming check

wever_feedback-gaming-check

Read-only

Agent Feedback: submit one set of feedback about one piece of work or one agent: optionally the work and the receiver; each entry with its id, the giver, when it was given, its tone (positive, negative, mixed or neutral), whether the giver is related to the receiver (the same operator, owner or team, or a paid affiliate), the other givers in the set the giver is related to, whether the receiver asked for it and the giver’s connection to the work on record (used it, saw it or none); the disputes between the receiver and a giver with when each was raised or decided; and who the receiver asked for feedback, which of them were expected to be positive and how they were chosen. The signed report gives every entry as clean, flagged, set_apart or unconfirmed, each manipulation pattern with the entries behind it, and counts the positive, negative, related, unconnected and solicited entries, and names manipulation of the exchange itself: coordinated praise from two or more related parties, negative feedback filed within 14 days after a dispute with the receiver, feedback solicited only from parties expected to be positive, and three or more entries from accounts with no connection to the work within 72 hours; then a single related-party entry, a scattered unconnected entry and a hand-picked selection, with the fix for each. This grades one specific feedback set: whether a reputation system’s design resists manipulation of its durable standing record is wever_reputation-gaming-check, and a dispute over a reputation record is wever_reputation-dispute-check. Verdict feedback_set_manipulated, feedback_set_gaps, feedback_set_unverified or feedback_set_clean. POST /api/feedback-gaming-check. Reads only the recorded feedback material in the call: no network request, fetch, money movement, message, sharing, configuration change or external write; no feedback is sent, no party is contacted and no work is changed. Agent Feedback reads the working feedback loop on one piece of work between a giver and a receiver: it is not scoring or benchmarking (the wever_evaluation checks), not a durable standing record (the wever_reputation checks) and not how agents organize shared work (the wever_coordination checks). 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-feedback-contract. Human page: https://weverlabs.com/agent-feedback/.

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": {
      "entries": "<entries>"
    },
    "name": "wever_feedback-gaming-check"
  }
}

Input Schema

Name	Required	Description
`label`	No	Optional name recorded in the report.
`entries`	Yes	Each entry in one feedback set about one piece of work or one agent.
`subject`	No
`disputes`	No	Disputes between the receiver and a giver.
`solicitation`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 11, 2026

TDQS

A4.3/5.0

Behavior3/5

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

The annotations already cover safety (readOnlyHint=true, destructiveHint=false, openWorldHint=false). The description does add useful context: the read-only, in-call scope, the 0.10 USDC x402 charge with 10 free calls per 30 days, the X-Wever-Wallet-Proof binding and the Ed25519 signed receipt. However, the framing is inconsistent: 'the signed report' and 'Returns a report with an Ed25519 signed receipt' imply produced artifacts, which sits oddly beside readOnlyHint and a POST endpoint, so I am not penalizing it heavily, but the reporting does not fully resolve how the receipt is separate from the read.

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?

The purpose is front-loaded, but the body is a single, long, semicolon-chained sentence that obscures the four manipulation patterns and the four verdicts. Much of the content earns its place (14-day and 72-hour thresholds, three-or-more-entry rule), but the layout makes it hard to scan for an agent.

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?

There is no output schema, so the description carries the burden of describing the report and does so thoroughly: entry statuses, manipulation patterns with supporting entries, counts, the four pattern types and their fixes plus verdicts. For a nested five-parameter tool it gives an agent enough to call it and interpret the result.

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%, but the description clarifies the meaning of the inputs beyond the bare schema: 'related' is glossed as same operator, owner or team or a paid affiliate; related_givers is described as the other givers in the set the giver is related to; solicited receivers, dispute timing and how solicitors were chosen are all given context. The optional label parameter is not covered, which leaves a small gap.

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?

The description states a specific verb and object: it grades one feedback set for manipulation and returns a verdict (feedback_set_manipulated, gaps, unverified, clean). It explicitly distinguishes itself from wever_reputation-gaming-check and wever_reputation-dispute-check, and rules out evaluation, reputation and coordination checks, so an agent can tell it apart from siblings without opening any 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?

Usage routing is explicit: use this for one specific feedback set, use reputation-gaming-check for a durable standing-record design, and reputation-dispute-check for a dispute over a reputation record. It also names what it is not (scoring/benchmarking, coordination), giving both when-to-use and when-not-to-use.

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?