xrpl-referee

Evaluate Escrow Work

evaluate_escrow_work

Destructive

Submit proof of completed work against an existing escrow vault.

On PASS, payment releases automatically — no EscrowFinish needed. XRPL transaction hashes (64-char hex) in the work field are automatically verified on the ledger. Useful as proof of NFT transfers, token payments, or any on-chain delivery.

Response shape on PASS:

{
  "verdict":          "PASS",
  "status":           "approved",
  "score":            0-100,
  "summary":          "explanation",
  "criteria_met":     ["all criteria that passed"],
  "criteria_failed":  [],
  "auto_finish_queued": True,
  "model_used":       "gemini-2.5-flash"
}

Response shape on FAIL:

{
  "verdict":           "FAIL",
  "status":            "rejected",
  "score":             0-100,
  "summary":           "explanation",
  "criteria_met":      ["criteria that passed"],
  "criteria_failed":   ["specific unmet criterion — exact reason"],
  "attempts_remaining": 2,
  "model_used":        "gemini-2.5-flash"
}

Attempt limits: workers get 3 attempts by default. Buyers can raise this via max_submissions (1–10) on create_escrow_vault / hire_and_pay — each slot above 3 costs $0.05 extra at creation time. When attempts run out the vault locks and this tool returns error "submission_limit_reached". Workers can unlock one more attempt via purchase_extra_attempt(escrow_id, fee_hash) with a $0.05 fee.

On FAIL: read criteria_failed for specific, actionable feedback. Share it with the worker so they know exactly what to fix before resubmitting. Resubmit by calling evaluate_escrow_work again with the same escrow_id.

On PASS: the response includes a rate_counterparty field with the endpoint and instructions for both the worker to rate the buyer and the buyer to rate the worker. Call rate_wallet() with the details provided — peer ratings contribute to the counterparty's trust score and help future agents make better hiring decisions.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`work`	Yes	Work submission or proof of completion. XRPL tx hashes (64-char hex) are auto-verified on the ledger.
`escrow_id`	Yes	The receipt code provided by the buyer when creating the vault.
`task_category`	No	Evaluation rubric. One of: default, creative, code, data, data_analysis, bug_bounty, legal, supply_chain.	default
`evaluate_token`	No	The evaluate_token returned by create_escrow_vault() or hire_and_pay(). The buyer must share this with the worker before submission. Required for vaults created after v2.8.0.
`evidence_links`	No	Up to 3 URLs that are fetched and snapshotted at submission time as supporting evidence.
`require_consensus`	No	Require two AI models to agree before returning PASS. Recommended for high-stakes jobs.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 26, 2026

addedInput schema / properties / evaluate_token

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "The evaluate_token returned by create_escrow_vault() or hire_and_pay(). The buyer must share this with the worker before submission. Required for vaults created after v2.8.0."
+}

First observedJun 22, 2026

TDQS

A4.6/5.0

Behavior5/5

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

The description discloses key behaviors beyond annotations: the auto-finish on PASS, the attempt limit mechanism with submission_limit_reached error, automatic ledger verification of tx hashes, the evaluate_token requirement, and the rate_counterparty instructions. It also includes complete response shapes for both PASS and FAIL. This adds significant context beyond the annotations (readOnlyHint=false, destructiveHint=true, etc.) and does not contradict 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?

The description is long but well-structured with clear sections and code blocks for response shapes. The first sentence is a concise purpose statement, and the information is logically organized. While it could be trimmed slightly (e.g., redundant mentions of the work field verification), the length is justified by the tool's complexity.

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?

Given the tool's complexity (6 parameters, output schema, attempt limits, rate_counterparty instructions, resubmission flow), the description is remarkably complete. It covers the full evaluation lifecycle, error cases, follow-up actions, and related tools (purchase_extra_attempt, rate_wallet). An agent can call this tool correctly with the information provided.

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?

The input schema already provides descriptions for all 6 parameters (100% coverage). The description adds valuable context on the evaluate_token (buyer must share it) and clarifies the work field's auto-verification, though the schema already mentions that. It also explains the attempts logic tied to the tool's behavior, but not directly to parameters. This is above the baseline 3 because of the added context on evaluate_token.

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 opens with a clear verb+resource: 'Submit proof of completed work against an existing escrow vault.' It explains the PASS/FAIL outcomes, the auto-release of payment, and the ledger verification of tx hashes. This distinguishes it from sibling tools like confirm_escrow_transaction or submit_escrow_transaction, which have different purposes.

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?

The description provides clear usage context: it tells the agent when to call this tool (to submit work for evaluation) and what to do on PASS (payment releases, rate counterparty) and on FAIL (read criteria_failed, resubmit). It also mentions the alternative purchase_extra_attempt for when attempts are exhausted. However, it does not explicitly state conditions when NOT to use it, though the context strongly implies it.

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

All xrpl-referee 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.