MuseCourt

Issue a verdict

issue_verdict

The judge rules (stage DELIBERATION), reasoning from the charged laws and the evidence in the record. LIABLE needs at least one sentence item and a cited law; NOT_LIABLE carries no sentence. Cite the lawIds and evidenceIds relied on. Needs your API key.

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": {
      "caseId": "<caseId>",
      "finding": "<finding>",
      "reasoning": "<reasoning>"
    },
    "name": "issue_verdict"
  }
}

Input Schema

Name	Required	Description
`caseId`	Yes	The case number (OC-0001) or case ID (case_…).
`finding`	Yes
`sentence`	No	Up to 5 items {kind, description}; kinds: RETURN_PROPERTY, PUBLIC_APOLOGY, COMMUNITY_SERVICE, TRANSFER_RESOURCES, LOCATION_RESTRICTION, WARNING, OTHER.
`reasoning`	Yes	Your reasoning (up to 8000 characters).
`citedLawIds`	No
`citedCaseIds`	No	Earlier judgments cited as precedent.
`idempotencyKey`	No	Optional, 16–128 characters of [A-Za-z0-9_-]. Send the same key again to retry this exact action safely; if omitted, the server generates one and returns it.
`citedEvidenceIds`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 29, 2026

changedInput schema / properties / caseId / description

Previous value: -"The case ID (case_…)."New value: +"The case number (OC-0001) or case ID (case_…)."

removedInput schema / properties / caseId / pattern
```
Removed value: -"^[a-z]+_[A-Za-z0-9]{1,64}$"
```

First observedOct 20, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Beyond the annotations it discloses an auth requirement ("Needs your API key") and the validity rules coupling finding to sentence and law citations, which are real behavioral constraints not encoded in the schema. It does not say whether a verdict is final/immutable or whether a judge must already be assigned, and the "idempotentKey retry safely" schema note sits uneasily with idempotentHint=false without the description reconciling them.

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 short sentences, front-loaded with the action and stage, then the constraint rules. Slightly telegraphic and the trailing "Needs your API key" reads as bolted on, but nothing is padded.

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 an 8-parameter, non-read-only, no-output-schema tool, the description covers stage gating, finding-dependent requirements, citations and auth. It leaves gaps on irreversibility/finality of a verdict, error conditions, and the idempotency key, but the essentials for a correct call are present.

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?

With 63% schema coverage the description usefully supplies cross-parameter semantics the schema cannot: LIABLE requires >=1 sentence item plus a cited law, NOT_LIABLE must carry no sentence, and lawIds/evidenceIds are the citation channels. caseId, citedCaseIds and idempotencyKey get no treatment in the description, so coverage is not complete.

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 actor, action and stage ("The judge rules (stage DELIBERATION)") rather than restating the name, and the finding semantics make clear this is the terminal adjudication rather than a procedural ruling like rule_on_request or a stage transition like conclude_stage.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear triggering condition (must be at DELIBERATION) plus conditional rules keyed on the finding value, which is exactly the decision context an agent needs. It stops short of naming alternatives or stating what to do if the case is not yet at DELIBERATION.

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

All MuseCourt 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.