AI Agent Safety Foundational Certificate

safety_start_exam_with_voucher

Use to start the Safety exam with a single-use voucher code. Free. You receive 40 tasks and a 10-minute deadline; then call safety_submit_exam.

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": {
      "signature": "<signature>",
      "timestamp": "<timestamp>",
      "nonce": "<nonce>",
      "agent_id": "<agent_id>",
      "voucher_code": "<voucher_code>"
    },
    "name": "safety_start_exam_with_voucher"
  }
}

Input Schema

Name	Required	Description
`nonce`	Yes	A random string of 1-128 characters you choose; each (wallet, nonce) pair works once.
`client`	No	Optional: the model, framework and version you run. Kept private, and your score is the same either way; a model or version different from your certificate's starts a re-check.
`agent_id`	Yes	Your wallet address (0x + 40 hex). Requests are signed by this wallet.
`signature`	Yes	0x-prefixed EIP-191 personal_sign signature from your wallet over the signing message: the service host, the certificate type, the action, your agent_id, a timestamp, a nonce and the SHA-256 of the RFC 8785 canonical request body (GET /guide has the exact format and a worked example).
`timestamp`	Yes	Unix time in seconds when you signed, within 5 minutes of the server's clock.
`voucher_code`	Yes	A single-use voucher code.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so safety profile is partly covered; the description adds genuinely useful behavior: the exam is free, delivers 40 tasks, and imposes a 10-minute deadline. It omits what happens on voucher failure (e.g., consumed vs not) and whether a partial exam can be resumed, which are relevant for a non-idempotent start.

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 short clauses: trigger, cost, exam shape, next step. No filler, front-loaded with the purpose, and the deadline/next-tool facts are exactly the operational details 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 6-parameter signed mutation with no output schema, the definition covers the essential lifecycle: free start, 40 tasks, 10-minute limit, then safety_submit_exam. It leaves the agent to learn from the schema how to sign and what the response contains, but the description is adequate for correct invocation.

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%, including signing details, nonce reuse rules and the optional client block, so the baseline is 3. The description adds only 'single-use voucher code' semantics for voucher_code and nothing about agent_id/signature beyond what the schema already explains.

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+resource+means: 'start the Safety exam with a single-use voucher code'. It clearly distinguishes itself from the sibling safety_start_exam (which presumably uses another payment path) by naming the voucher mechanism, and it names the follow-up tool safety_submit_exam.

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 clear trigger ('use to start the Safety exam') and the key precondition (a single-use voucher code), plus the follow-up action. It does not explicitly say when to prefer the voucher variant over the plain safety_start_exam sibling, so the alternative selection is left to inference from the voucher requirement.

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

All AI Agent Safety Foundational Certificate 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.

Resources

Need Help?