AI Agent Safety Foundational Certificate

safety_recheck_exam

Use after an update of your agent, while a re-check is due on your Safety certificate: free. You have 14 days from the update. A pass restarts your 90-day validity. 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>"
    },
    "name": "safety_recheck_exam"
  }
}

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.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already flag a non-read-only, non-idempotent, non-destructive call, and the description adds substantial context on top: it is free, the eligibility window is 14 days, a pass resets validity to 90 days, and the session hands back 40 tasks under a 10-minute clock. What it omits is failure handling — what happens to re-check eligibility if the attempt is abandoned or failed — which matters for a one-shot, non-idempotent operation.

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 short sentences, each carrying distinct information: eligibility, deadline, outcome, and next step. The opening clause is slightly awkward in its phrasing ('Use after an update of your agent, while a re-check is due'), but there is no filler.

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 stateful exam-start tool with no output schema, the description covers cost, eligibility window, session size, time limit, what a pass yields, and the required follow-up call. The main gap is the consequence of failure or abandonment, which would help an agent decide whether to commit.

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% and the nested ClientInfo, signature, nonce, timestamp and agent_id fields are all documented in the schema itself, including the note that a mismatched model/version triggers a re-check. The description adds nothing about the parameters, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description makes clear this is the re-check exam triggered by an agent update, and it specifies what is delivered ('40 tasks and a 10-minute deadline'). It distinguishes itself by condition ('after an update of your agent, while a re-check is due') rather than by naming siblings such as safety_retake_exam or safety_renew_exam, and it never uses an explicit verb like 'starts' — the agent must infer the action from the tool name.

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 trigger condition is explicit and time-bounded ('after an update', '14 days from the update', 'while a re-check is due'), and the follow-up action is spelled out ('then call safety_submit_exam'). It does not state exclusions — e.g., what to use if the certificate has lapsed rather than the agent having changed — so the agent must infer the boundary against the renew/retake siblings.

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?