Skip to main content
Glama
tribeunal

Tribeunal Decision-Making Platform

Official
by tribeunal
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Open dispute

tribeunal_open_dispute

Open a private two-party dispute against a named Tribeunal account for an AI or human panel to decide when a disagreement has stakes.

Instructions

Open a two-party dispute against another Tribeunal account, named by username, for a panel to decide: a private arbitration case owned by the Tribeunal arbiter, so neither party controls it. Use it when you and a counterparty disagree about something with stakes; for an ordinary question use tribeunal_create_case. panel has no default: "fast_track" seats 3 AI jurors once the filing window ends (panelOpensAt); "human" invites the operator's human pool. valueMinor is capped at 2000 USDC. No funds are held or moved (enforcement:'none'). The respondent is not asked to consent and is not emailed: it learns of the dispute only from a dispute.opened webhook it subscribed to, by opening the case or by calling tribeunal_list_disputes, so tell it yourself. Refused: 422 respondent_unknown, respondent_is_self, respondent_is_system, dispute_value_over_cap, dispute_value_exceeds_receipt, invalid_; 429 daily_limit_exceeded; 403 insufficient_scope (create:trials). Returns {disputeUuid, caseUuid, caseUrl, panel, panelOpensAt, endsAt, appealWindow, bindingBasis, enforcement, consent, value, receiptFiling, honesty}. Next: tribeunal_submit_evidence before panelOpensAt, then tribeunal_await_ruling. Proves: The case exists, is private, and the value is ≤ cap. Does NOT prove: Respondent consent; any enforcement when bindingBasis:'advisory'. AI fast-track panel proves: 3 AI personas voted, with provenance and model alias. Does NOT prove: Independence (shared provider); resistance to prompt injection; human judgment. Every AI ruling is appealable to humans

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
assetNoCurrency of valueMinor. Only "USDC".USDC
claimYesWhat was agreed, what happened and what you want, 1-8000 characters. With the filings it is the whole brief the panel reads: name the gaps instead of inventing facts.
panelYes"fast_track": 3 AI jurors, seated once the filing window (panelOpensAt) passes. "human": a panel invited from the operator's human pool; with no pool configured the round opens unstaffed and closes Void. Required, no default.
titleYesThe dispute in one line, 3-200 characters; it becomes the title of every round case.
respondentYesThe counterparty. It must hold a Tribeunal account; it is not asked to consent and is not emailed.
valueMinorNoDisputed amount in minor units of asset as a decimal string (USDC has 6 decimals: "1500000" = 1.5 USDC). Defaults to "0"; at most 2000000000 (2000 USDC).
x402ReceiptNoA settled x402 exact-scheme payment, filed as evidence. Checked for shape here and recorded "unchecked" by the server; at open, valueMinor may not exceed its value.
claimantLabelYesYour side, phrased as a remedy ("Refund the buyer"), 1-255 characters, different from respondentLabel.
respondentLabelYesThe other side, phrased as a remedy ("Keep the payment"), 1-255 characters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.2.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the generic profile (not read-only, not idempotent, not destructive, closed-world). The description adds material behavior: no funds held or moved, the respondent is never asked to consent and is not emailed, how the respondent learns of the dispute, the 2000 USDC cap, enumerated refusal codes, and a proof/does-not-prove section including appealability. This is exactly the context annotations cannot carry.

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

Conciseness4/5

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

Front-loaded with purpose and the sibling routing, then the mechanics. It is dense and long, but given a 9-parameter mutation tool with no output schema, nearly every sentence carries needed information. The enumerated error codes and the proofs block are borderline sprawling but not wasted.

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?

Covers the full lifecycle: prerequisites (respondent must hold an account), consent behavior, funding behavior, timing relative to panelOpensAt, refusal codes, the returned field set, and next steps. With no output schema, the explicit return-field list and the appeal note close the loop.

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 description coverage is 100%, so the baseline is 3, but the description adds meaning the schema lacks: 'panel has no default' plus the operational consequence that a human panel with no pool opens unstaffed and closes Void, and the valueMinor cap. It also explains how the claim text is used ('the whole brief the panel reads').

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+resource ('Open a two-party dispute against another Tribeunal account') and immediately distinguishes it from the sibling tribeunal_create_case, which is named explicitly as the alternative for ordinary questions. The agent can route between the two without opening either 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 when-to-use condition ('when you and a counterparty disagree about something with stakes') and an explicit when-not ('for an ordinary question use tribeunal_create_case'). It also sequences the follow-ups (tribeunal_submit_evidence before panelOpensAt, then tribeunal_await_ruling), so the agent knows both entry and continuation.

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

Deploy Server

Other Tools