Skip to main content
Glama
tribeunal

Tribeunal Decision-Making Platform

Official
by tribeunal
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Await case activity

tribeunal_await_case_activity
Read-only

Blocks until a new event appears on a case via long-polling, returning events and a cursor to re-arm and continue watching without missing updates.

Instructions

Block until a NEW event appears on a case (long-poll, up to timeoutS seconds) — for a one-shot read use tribeunal_get_case_activity; for the final decision use tribeunal_await_verdict. Omit after to watch from now; on re-arm pass the previous latestCursor so nothing is missed. Returns {events, latestCursor, hasMore, caseUuid, caseState, caseEndsAt, verdict, timedOut, waitedS}. PROTOCOL: if timedOut is true, no event arrived yet — re-arm by calling again with after=latestCursor. Check caseEndsAt and STOP re-arming well past it (tell the human instead of looping forever).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
afterNoCursor to watch from (a previous latestCursor); omit to anchor at the current tail ("watch from now").
typesNoOnly wake for these event types — same enum as tribeunal_get_case_activity.
caseIdYesCase UUID to watch.
timeoutSNoSeconds to block, 5-170; defaults to 120. On timeout, re-arm with the returned latestCursor.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.2.0
    • changedInput schema / properties / types / items / enum
      Previous value: -[
-  "vote",
-  "vote_revoked",
-  "comment",
-  "evidence_marked",
-  "evidence_unmarked",
-  "jury_joined",
-  "jury_left",
-  "trial_closed",
-  "trial_reopened",
-  "trial_updated"
-]New value: +[
+  "vote",
+  "vote_revoked",
+  "comment",
+  "evidence_marked",
+  "evidence_unmarked",
+  "jury_joined",
+  "jury_left",
+  "trial_closed",
+  "trial_reopened",
+  "trial_updated",
+  "dispute_opened",
+  "appeal_filed",
+  "ruling_final"
+]
  2. Changed5 schema fields changedv2.0.0
    • changedInput schema / properties / after / description
      Previous value: -"Cursor to watch from; omit to anchor at the current tail (\"watch from now\")"New value: +"Cursor to watch from (a previous latestCursor); omit to anchor at the current tail (\"watch from now\")."
    • changedInput schema / properties / caseId / description
      Previous value: -"Case UUID to watch"New value: +"Case UUID to watch."
    • changedInput schema / properties / timeoutS / description
      Previous value: -"Seconds to block (5-170). On timeout, re-arm with the returned latestCursor."New value: +"Seconds to block, 5-170; defaults to 120. On timeout, re-arm with the returned latestCursor."
    • changedInput schema / properties / types / description
      Previous value: -"Only wake for these event types"New value: +"Only wake for these event types — same enum as tribeunal_get_case_activity."
    • changedInput schema / properties / types / items / enum
      Previous value: -[
-  "vote",
-  "vote_revoked",
-  "comment",
-  "evidence_marked",
-  "evidence_unmarked",
-  "jury_joined",
-  "trial_closed",
-  "trial_reopened"
-]New value: +[
+  "vote",
+  "vote_revoked",
+  "comment",
+  "evidence_marked",
+  "evidence_unmarked",
+  "jury_joined",
+  "jury_left",
+  "trial_closed",
+  "trial_reopened",
+  "trial_updated"
+]
  3. First observedv1.13.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only cover the safety profile (readOnlyHint, destructiveHint, openWorldHint, idempotentHint); the description adds the far more important behavior: long-poll blocking, the timeout/re-arm protocol, and the anti-infinite-loop guard tied to caseEndsAt. It also enumerates the return payload, which no structured field provides.

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 sibling routing, then a compact PROTOCOL block, with no filler sentences. It is dense and the inline return-shape list is slightly heavy, but each clause carries actionable information.

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?

For a long-poll tool with no output schema, the description supplies both the return shape and the loop-control protocol, including the failure mode (timedOut = true) and the escalation path to a human. Nothing needed for correct invocation 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 description coverage is 100%, so the baseline is 3. The description still adds operational meaning beyond the schema by explaining the re-arm contract for 'after' (pass the previous latestCursor so nothing is missed) and tying timeoutS to the returned cursor on timeout.

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 precise verb+resource ('Block until a NEW event appears on a case (long-poll...)') and explicitly distinguishes itself from two named siblings, tribeunal_get_case_activity and tribeunal_await_verdict. An agent can select this tool without inspecting 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?

Explicit routing: one-shot reads go to get_case_activity, final decisions to await_verdict. It also gives the operational rule for the two usage modes ('omit after to watch from now; on re-arm pass the previous latestCursor') and states when to stop ('Check caseEndsAt and STOP re-arming well past it').

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