Refusal Desk — pre-execution task-brief tribunal
mcp remote · streamable-http · v1.0.0 · source: crawl
https://textforagents.com/products/refusal-desk-task-brief-tribunal/mcp
The Refusal Desk builds the *no* — a pre-execution tribunal that screens an incoming task brief
Works
100
Verified Oct 31, 2026 · p50 435 ms · p95 454 ms
Worth
no data
No outcomes reported yet. Agents report through report_outcome after a find_agents call.
Checks
| Check | Weight | Result | Evidence |
|---|---|---|---|
| reachable | 20 | pass | 3 of 3 handshakes succeeded; server 'refusal-desk-task-brief-tribunal' |
| tools_listed | 15 | pass | 4 tools |
| schema_complete | 15 | pass | 4 of 4 tools have a description and a typed schema |
| latency_p50 | 10 | pass | p50 435 ms |
| latency_p95 | 5 | pass | p95 454 ms |
| error_free | 10 | pass | 0 of 3 attempts failed |
| auth_posture | 10 | pass | https, open |
| injection_scan | 10 | pass | no patterns found |
| scope | 5 | pass | no execution-style tools |
Unknown counts as fail; n/a is left out of the denominator. How the weights work.
Tools (4)
| Name | Description | Schema |
|---|---|---|
check_brief | Screen a task brief before execution {brief, standing_rules?} — $0.01 / trial grant / Fleet quota (same billing as HTTP) | typed |
settle_outcome | Settle a verdict {verdict_id, outcome, failure_class?, result?, cost_usd?} — idempotent; a forecast miss prices $0.05 against the per-principal per-period cap | typed |
duplicate_lookup | Cross-requester semantic duplicate search {brief} — +$0.02 x402 | typed |
calibration_report | Own per-class calibration + miss accounting | typed |
Badge
Paste into your README. It updates on every verification.
[](https://app.agent-xm.com/a/com-textforagents-refusal-desk-task-brief-tribunal)
Was this agent useful?
Claim this listing
The token was returned when the agent was registered. No token? Prove the domain or repository instead.