Skip to main content
Glama
Sign In

MuseCourt

by io.github.danbuildss
OverviewDiscussionsAdmin

Withdraw evidence

withdraw_evidence

Withdraw evidence your side submitted, giving a reason. It stays in the record, marked withdrawn. 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>",
      "evidenceId": "<evidenceId>",
      "reason": "<reason>"
    },
    "name": "withdraw_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
caseIdYesThe case number (OC-0001) or case ID (case_…).
reasonYesWhy (up to 1000 characters).
evidenceIdYesThe evidence ID (ev_…).
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

A3.8/5.0
Behavior4/5

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

Adds real behavioral context beyond the annotations: 'It stays in the record, marked withdrawn' discloses that this is a soft, non-removing mutation, and 'Needs your API key' flags the auth requirement. Annotations already declare non-destructive/non-idempotent, so the remaining gap is minor — no mention of retry semantics in prose, though the schema's idempotencyKey covers it.

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

Conciseness5/5

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

Three short sentences, zero filler, with the core action and its ownership constraint front-loaded ahead of the retention and auth notes.

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 4-param mutation with no output schema, the description covers action, ownership, retention effect and auth. It leaves unaddressed edge cases such as withdrawing an already-withdrawn item or deadline cutoffs, which keeps it short of complete.

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 coverage is 100% with per-parameter descriptions for caseId, evidenceId, reason and idempotencyKey. The description adds only that a reason must be given, which the required array already enforces; baseline 3 is appropriate when the schema does the work.

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 verb and resource ('Withdraw evidence') plus an ownership scope ('your side submitted') that separates it from submit_evidence. It does not name the sibling explicitly, but the counterpart operation is obvious from the name pair.

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

Usage Guidelines3/5

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

'your side submitted' implies a precondition (you can only withdraw evidence your party filed), and 'giving a reason' implies a reason is mandatory. There is no explicit when-not guidance, no mention of what to do if the evidence is already withdrawn, and no named alternative.

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