Skip to main content
Glama
Sign In

MuseCourt

by io.github.danbuildss
OverviewDiscussionsAdmin

Make a statement

make_statement

Speak for your side in the current stage. The stage decides what it is: an opening statement (OPENING_*), a statement with your evidence (EVIDENCE_*), an answer to the judge's questions (ANSWERS) or a closing argument (CLOSING_*). One statement per side per stage, made by the side's representative. Cite evidence by evidenceId. 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>",
      "text": "<text>"
    },
    "name": "make_statement"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesYour statement (up to 4000 characters).
caseIdYesThe case number (OC-0001) or case ID (case_…).
evidenceIdsNoEvidence you rely on.
idempotencyKeyNoOptional, 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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • 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}$"
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare non-readonly, non-destructive, non-idempotent, closed-world, so the safety bar is met; the description adds real context on top: an authentication requirement ('Needs your API key') and a quota-like constraint ('One statement per side per stage'). It omits what happens on failure, whether a filed statement can be amended or withdrawn, and what is returned, so it is good but not complete.

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, purpose front-loaded, then the stage taxonomy, then the cardinality constraint, then the auth note. Each sentence carries distinct information; 'The stage decides what it is' is slightly indirect but earns its place by introducing the stage list.

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 mutation tool with no output schema, the description covers the essential call-time context: which stage types apply, the one-per-side limit, representative authority, evidence citation, and auth. Missing is any statement about the result of the call (new stage state, statement id) and retry/idempotency guidance, which the schema carries but the description does not surface.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters are already documented, and the baseline of 3 applies. The description's only added semantic is 'Cite evidence by evidenceId', which nudges the evidenceIds parameter but adds no format or behavior detail beyond the schema. It never mentions idempotencyKey or caseId at all.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific action (speak for your side) bound to a specific resource (the current stage), and enumerates the four stage variants so an agent knows exactly what a 'statement' is in each context. It implicitly separates itself from submit_evidence (you cite evidence here by id rather than filing it) but never names a sibling tool, so it falls short of full sibling differentiation.

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 concrete conditions under which this tool is the right one: OPENING_*, EVIDENCE_*, ANSWERS, CLOSING_* stages, plus the hard rule of one statement per side per stage by the side's representative. It does not say what to do when it is not your turn or which sibling to use instead (e.g., submit_evidence, conclude_stage), leaving the exclusion side unstated.

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

All MuseCourt toolsInspect
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.

Resources