Skip to main content
Glama
Sign In

SAAX Protocol

by io.github.bryantrudy24
OverviewDiscussionsAdmin

Verify or reject submitted evidence

verify_evidence

Sets the verification status of a submitted evidence record to verified or rejected. The caller must present an EIP-712 authority proof and hold an unrevoked, unexpired EVALUATOR authorization on the commitment (verified in-transaction). Idempotent per verdict: re-verifying with the same verdict replays the original outcome; changing a verified record to rejected (or vice versa) is rejected without a dispute path. Does NOT auto-transition the commitment state � the caller must perform the authorized lifecycle transition separately. Rejection requires a reason.

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": {
      "evidenceId": "<evidenceId>",
      "verdict": "<verdict>",
      "agentId": "<agentId>",
      "proof": "<proof>"
    },
    "name": "verify_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
proofYesThe EIP-712 AuthorityProof
reasonNoRequired when verdict=rejected
agentIdYesThe caller's agent identity
verdictYesThe evaluator verdict
evidenceIdYesThe evidence record ID to verify
expectedVersionNoOptimistic-concurrency expected version

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so well: authorization is verified in-transaction, verdicts are idempotent but cannot be flipped between verified and rejected, and there is no dispute path for such flips. It also flags that rejection requires a reason, so an agent knows a missing reason will fail.

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?

Dense and front-loaded: purpose first, then authorization, then idempotency, then the scope exclusion. Every sentence carries operational information, though the corrupted dash character ('') and the run-on final clause slightly hurt polish.

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?

Covers authorization, idempotency, conflict handling, and the state-transition boundary for a six-parameter mutation with no output schema. The remaining gap is that it never says what a successful call returns or how a failed proof/version check surfaces, which an agent calling blind would want to know.

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%, so all six parameters are already documented, and the description largely restates them. It adds real meaning for verdict (idempotency per verdict, no flip without dispute) and reinforces the reason-when-rejected constraint, but says nothing about expectedVersion or its optimistic-concurrency failure mode beyond what the schema line states.

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?

Opens with a specific verb and resource plus the two possible outcomes: 'Sets the verification status of a submitted evidence record to verified or rejected.' This clearly separates it from siblings like submit_evidence (creation) and get_evidence_verification (read-only lookup) without needing to open 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?

Gives a strong precondition set (EIP-712 proof plus an unrevoked, unexpired EVALUATOR authorization) and an explicit when-not: it does not transition commitment state, so the caller must do that separately. It stops short of naming the sibling tool that performs the lifecycle transition or the one to use for reading current status, leaving the agent to infer those routes.

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

All SAAX Protocol 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