Skip to main content
Glama
tribeunal

Tribeunal MCP Server

Official
by tribeunal

Create case

tribeunal_create_case

Create a new case, advice request, or poll on Tribeunal to settle disputes, gather opinions, or put choices to a community vote with configurable jury, privacy, and voting rules.

Instructions

Create a new case on Tribeunal for community decision-making (case = jury decides, advice = creator decides, poll = opinion gathering). Use this directly when the user wants to start, decide, settle, or put something to a vote and no specific existing case is referenced — do NOT search first. Set visibility to "private" to keep a case visible only to you, your invited jurors and admins (a private case runs an invited jury). Add allowsGuestVotes to a private case to make a link-poll instead: unlisted everywhere, but readable and votable by anyone you send the link to. A private case answers with a shareUrl — a view-only link (no voting/joining) you can send to anyone; rotate it from the case web page to revoke every old link at once.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoUp to 4 tags for categorization
typeYesCase type — case (binding jury decision), advice (input for the creator), or poll (opinion gathering)
sidesYesThe choices/options voters pick between (2-10)
titleYesCase title — the question or statement to be decided
juryTypeNoWho can participate — public (anyone) or invited onlypublic
minVotesNoFewest votes this case needs before it can reach a verdict (0-100, default 0 = no minimum). Close it with fewer and it ends with a Void verdict carrying voidReason "quorum_not_met" rather than deciding on a turnout of one or two.
caseLengthNoVoting duration in seconds (min: 1 minute, max: 30 days, default: 1 day)
jurorCountNoNumber of jurors the case asks for (2-100, default 12). It gates opening only when openImmediately is false, where the case waits until this many jurors have joined. For a small invited panel, set this to the number of people you invite.
visibilityNoCase visibility — public (anyone can find and read it) or private (only you, your invited jurors and admins). A private case must use an invited jury; omit juryType and it is set to invited automatically. One exception: set allowsGuestVotes on a private case and it becomes a link-poll — still absent from every listing, search and feed, but readable and votable by anyone you send the link to — which takes a public jury instead.public
descriptionYesContext, background, and criteria for the case
arbitrationModeNoBind this case to arbitration rules, for a verdict someone outside the case has to rely on (default false). You cannot vote on, join the jury of, or close early a case you created in this mode — an admin closes it, or it closes at its deadline; evidence marks freeze once it closes so the record it was decided on stops moving; and the early-vote and decisive-vote reward multipliers are switched off, so timing your vote no longer multiplies your payout. Requires minVotes of at least 2 (omit it and 3 is used) and cannot be combined with allowsGuestVotes. Use it when the case settles something with stakes — a dispute, a payout, a contract term — rather than gathering opinion.
openImmediatelyNoOpen the case for voting straight away (default true). Invited jurors are still invited and can view, join and vote while it is already open. Set false to hold the case in jury selection until jurorCount jurors have joined, and only then open it.
allowsGuestVotesNoLet visitors without a Tribeunal account vote on this case (default false). Guest votes count in full — they enter the tallies, percentages and the verdict exactly like a registered juror's. Requires a public jury; visibility may be either, and pairing it with visibility "private" makes a link-poll: unlisted everywhere, but votable by whoever holds the link. Guests are deduplicated per browser, so a returning visitor changes their vote rather than adding one, but someone determined can still vote again from another browser — enable it where reach matters more than strict one-person-one-vote.
decisionRequirementNoThe weakest outcome this case will accept as a verdict (default "any"). "any" takes whatever the tally gives, down to a plurality. "simple" needs at least half, "qualified" at least 66%, "unanimous" every vote on one side. A case that reaches a stronger result than required still reports the stronger one. On any value other than "any", missing the requirement closes the case with a Void verdict carrying voidReason "requirement_not_met"; an "any" case that merely ties stays Undecided.
maxAiJurorPercentageNoMaximum percentage of jurors that may be AI personas (0 = none allowed, 100 = all; default 50)

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observedv1.13.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations are minimal (readOnlyHint=false, openWorldHint=false, destructiveHint=false), so the description carries the transparency burden and rises to it: it discloses that private cases return a view-only shareUrl, that link-polls are "unlisted everywhere, but readable and votable by anyone you send the link to," and that rotating the shareUrl revokes all old links. This adds genuine post-call behavior the annotations cannot convey, with no contradiction.

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?

Four sentences, each earning its place: what the tool does, when to use it, private-visibility behavior, and the link-poll/shareUrl behavior. It is front-loaded with purpose before usage guidance. It loses one point because the private/link-poll content partially duplicates the already-rich visibility and allowsGuestVotes schema descriptions.

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

Completeness4/5

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

For a 15-parameter creation tool with 4 required fields and no output schema, the description covers the selection-critical and invocation-critical facts: type semantics, the no-search rule, private-case jury requirements, link-poll behavior, and the private-case shareUrl return value. The exceptionally detailed input schema carries the remaining parameter burden, though the general success response shape (e.g., returned case ID) is not disclosed anywhere.

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 100%, so the baseline is 3, but the description adds meaning beyond per-field schema text: it explains what the type enum actually means in practice (jury decides / creator decides / opinion gathering) and surfaces the cross-parameter interaction that private visibility + allowsGuestVotes = link-poll. It doesn't enumerate all 15 parameters, but it enriches the two most consequential ones.

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?

"Create a new case on Tribeunal for community decision-making" is a specific verb+resource statement, and the parenthetical disambiguation (case = jury decides, advice = creator decides, poll = opinion gathering) gives the type parameter real semantic meaning beyond the title. The explicit "do NOT search first" line also distinguishes this from tribeunal_search_cases and tribeunal_get_case.

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?

"Use this directly when the user wants to start, decide, settle, or put something to a vote and no specific existing case is referenced — do NOT search first" gives explicit when-to-use conditions, a clear boundary condition (no referenced existing case), and an explicit when-not directive against searching. This is exactly the routing decision an agent faces against the search/get siblings, and it is answered directly.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tribeunal/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server