SAAX Protocol

Submit fulfillment evidence

submit_evidence

Durably submits evidence for a commitment. The caller must present an EIP-712 authority proof; the recovered signer must hold an unrevoked, unexpired provider or buyer authorization on the commitment (verified in-transaction against the durable registry). The evidence envelope is validated for structure and size, bound to the commitment and optional acceptance criterion, and persisted with the verified submitter attribution and an integrity payload hash. Idempotent per idempotencyRef: a replay returns the original record; reuse with a materially different payload is rejected. Submission does NOT transition the commitment state and does NOT trigger settlement, escrow release, or finalization � those require separate authorized lifecycle 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>",
      "proof": "<proof>",
      "evidence": "<evidence>"
    },
    "name": "submit_evidence"
  }
}

Input Schema

Name	Required	Description
`proof`	Yes	The EIP-712 AuthorityProof: authorityProofId, issuer, subject, validFrom, validUntil, scope, signature, verificationScheme=eip712
`agentId`	Yes	The caller's agent identity (bound to the verified principal)
`evidence`	Yes	The evidence envelope: evidenceType, issuer, subject, payload, payloadHash, signature, verificationScheme, commitmentId, acceptanceCriterionId, provenance
`criterionId`	No	The acceptance criterion ID this evidence addresses, if applicable
`commitmentId`	Yes	The commitment ID the evidence binds to
`idempotencyRef`	No	Stable idempotency reference; replay-safe

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 14, 2026

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations supplied, the description carries the full burden and does it well: it discloses in-transaction authorization checks against the durable registry, envelope structure/size validation, persistence with submitter attribution and a payload hash, idempotency semantics (replay returns the original record; conflicting payload reuse is rejected), and the absence of state or settlement side effects.

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 dense sentences, front-loaded with purpose then requirements then semantics, with no filler; each sentence carries distinct information. Slightly long, clause-heavy sentences and minor character corruption in the text keep it from a 5.

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 a six-parameter mutation tool with no annotations and no output schema, the description covers authorization, validation, idempotency, persistence, and post-call state, which is everything an agent needs to invoke it correctly; return behavior on replay is also stated.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema by explaining that the evidence envelope is bound to the commitment and optional acceptance criterion, and by spelling out idempotencyRef replay/conflict behavior that the schema only labels 'replay-safe'.

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?

States a specific verb and object ('Durably submits evidence for a commitment') and immediately scopes what it is not: it does not transition state, settle, release escrow, or finalize, which cleanly separates it from lifecycle siblings like accept_commitment or close_commitment.

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 clear preconditions for use (valid EIP-712 authority proof, unrevoked/unexpired provider or buyer authorization) and explicit exclusions (state transitions and settlement belong to other authorized lifecycle actions). It stops short of naming the specific sibling to use for verification or the lifecycle actions, leaving that inference to the agent.

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.