Skip to main content
Glama
reciprocal-ruler-mcp
by hwcho310

Reciprocal Ruler - free trial reconciliation

ruler_trial_reconcile
Read-only

Run a free settlement reconciliation between AI agents: compare expected and actual KRW amounts to get a deterministic SETTLED_OK, COMPENSATED, or PENDING_RECONCILIATION judgment.

Instructions

Run a settlement reconciliation between two AI agents for free (up to 3 calls per client). Compares the expected amount with what actually settled and returns a deterministic judgment: SETTLED_OK, COMPENSATED (shortfall covered from the holdback), or PENDING_RECONCILIATION (half-open timeout, left pending). Use it to evaluate whether Reciprocal Ruler fits your agent-to-agent transaction flow before paying. Amounts are KRW integers.

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": {
      "expected_amount_krw": "<expected_amount_krw>",
      "actual_settled_krw": "<actual_settled_krw>"
    },
    "name": "ruler_trial_reconcile"
  }
}

Input Schema

NameRequiredDescriptionDefault
tx_idNoYour transaction or order id. Defaults to the idempotency key.
event_typeNoPOST_TRADE_REFUND for a refund/shortfall after the trade; HALF_OPEN_TIMEOUT for an unfinished settlement when the timer expires.POST_TRADE_REFUND
quote_hashNoquote_hash from ruler_quote_lock for this trade, when one was issued.
holdback_krwNoHoldback reserved from the payment, the pool used to compensate a shortfall (KRW).
idempotency_keyNoOptional on the free trial; generated when omitted.
trial_client_idNoStable id for your agent (sent as X-Trial-Client) so the 3 free calls follow this id instead of the shared IP address.
actual_settled_krwYesAmount that actually settled (KRW).
expected_amount_krwYesAmount the buyer and supplier agreed the supplier should receive (KRW).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

With readOnlyHint and openWorldHint supplied, the description adds real value: the 3-call free-tier limit, the X-Trial-Client header behavior that scopes the quota to a stable id rather than a shared IP, and the semantics of each judgment including that a half-open timeout is deliberately left pending. It does not describe what happens on the 4th call (error vs. rejection), and the "COMPENSATED / shortfall covered from the holdback" wording sits in mild tension with readOnlyHint, though it reads as a computed judgment rather than an actual fund transfer.

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 tight sentences, front-loaded with the action and the free-trial constraint, followed by the outcome enumeration and the evaluation-purpose rationale. No filler or repetition of the schema.

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 an 8-parameter tool with no output schema, the description fully covers the return values by naming and explaining all three judgment states in parentheticals. Combined with 100% schema coverage, an agent has everything needed to call it and interpret the result.

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 every parameter including the event_type enum and quote_hash linkage is already documented in the schema. The description only restates the unit convention ("Amounts are KRW integers"), adding essentially nothing beyond the structured fields; baseline 3 applies.

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 the specific verb and resource ("Run a settlement reconciliation between two AI agents") and names its scope (free trial), its inputs (expected vs. actual settled amount), and its three outcomes (SETTLED_OK, COMPENSATED, PENDING_RECONCILIATION). An agent can distinguish this trial tool from ruler_reconcile and ruler_quote_lock without opening either schema.

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 gives clear when-to-use guidance: evaluate fit "before paying" as a free trial capped at 3 calls per client, and it references ruler_quote_lock via quote_hash. It does not explicitly say when to move to ruler_reconcile or what happens once the trial is exhausted, but the trial-vs-paid framing is clear.

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