SAAX Protocol

Resume a commitment after the original agent terminated

resume_commitment

Lets an independently authorized replacement agent continue a commitment. Reconciles the authoritative state, verifies the caller's EIP-712 authority proof, and executes the requested nonfinancial transition through the canonical transition engine. The replacement agent must hold its OWN durable authorization (no automatic inheritance). Duplicate requests are idempotent. Financial transitions (settle/finalize with settlement, escrow release, refunds) are NOT exposed. For inspection first, use get_recovery_status or get_pending_actions.

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": {
      "commitmentId": "<commitmentId>",
      "agentId": "<agentId>",
      "role": "<role>",
      "proof": "<proof>",
      "action": "<action>"
    },
    "name": "resume_commitment"
  }
}

Input Schema

Name	Required	Description
`role`	Yes	The caller's role on this commitment
`proof`	Yes	EIP-712 AuthorityProof signed by the caller (issuer = signer)
`action`	Yes	The lifecycle action to execute: cancel, accept, authorize, execute, complete, submit, verify, fulfill, recover, dispute (nonfinancial subset)
`agentId`	Yes	The caller's durable agent identifier
`evidenceRef`	No	Optional evidence reference to bind to the transition
`authorityRef`	No	Optional external authority reference to record on the event
`commitmentId`	Yes	The commitment id
`idempotencyRef`	No	Caller-scoped idempotency reference (>= 8 chars) for safe retries
`expectedVersion`	No	Optimistic-concurrency guard: the state version the caller observed

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 14, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations supplied, the description carries the full disclosure burden and does well: it describes state reconciliation, EIP-712 proof verification, execution through a canonical transition engine, and idempotent duplicate handling. It stops short of saying what happens on a version conflict or what the caller receives back after the transition.

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?

Five front-loaded sentences with zero filler: actor requirement first, then mechanism, then exclusivity constraint, then the routing hint. Every sentence contributes information an agent needs before calling.

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 nine-parameter mutation with no annotations and no output schema, the description covers the critical behavioral facts (authorization model, nonfinancial scope, idempotency). The gap is the return contract and conflict behavior, which nothing else in the definition supplies.

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 nine parameters are already documented in the schema, including the action enum and the optimistic-concurrency guard. The description only reinforces meaning already present (proof authority, idempotency for safe retries) rather than adding new parameter-level detail.

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 pairs a specific verb ('continue a commitment') with the exact actor condition ('independently authorized replacement agent'), so the resource and scope are unmistakable. It also distinguishes itself from the inspection siblings by name, so an agent can tell them apart without opening a 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?

It names the inspection alternatives ('use get_recovery_status or get_pending_actions') and states a hard exclusion ('Financial transitions ... are NOT exposed'), plus a prerequisite ('must hold its OWN durable authorization'). What it does not spell out is the trigger condition versus calling a normal lifecycle tool like accept_commitment directly on the same commitment.

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

All SAAX Protocol 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.