AI Agent Safety Foundational Certificate

safety_delete_reported_data

Use to delete the model, framework and version you reported about your agent. Free, for your wallet alone (action delete-reported-data). Your certificate stays as it is; a later report starts a new baseline.

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_delete_reported_data"
  }
}

Input Schema

Name	Required	Description
`nonce`	Yes	A random string of 1-128 characters you choose; each (wallet, nonce) pair works once.
`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

A3.8/5.0

Behavior4/5

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

Beyond the annotations, it discloses three useful behaviors: the call is free, it affects only your own wallet's data, and your certificate is untouched so the deletion is recoverable by re-reporting. That recoverability framing explains why destructiveHint=false is plausible even for a delete, though the description does not state whether the deleted report disappears immediately or becomes readable elsewhere.

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?

Two compact sentences with the operation and scope front-loaded and no filler; the parenthetical action id is marginally useful for debugging. Sentence two bundles two distinct facts (certificate unaffected, new baseline) but remains readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a four-parameter, fully-signed mutation with no output schema, the description covers scope and side effects but says nothing about what happens on success or failure, nor about the single-use nonce/replay implication at the behavioral level. Adequate but leaves the agent to rely entirely on the schema for the signing workflow.

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 signature, timestamp, nonce and agent_id are already fully documented in the schema, including the signing message components and the GET /guide pointer. The description adds no additional meaning about these parameters, which is acceptable at this coverage level but not value-adding.

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 resource: delete the model, framework and version previously reported for the agent, and names the internal action id (delete-reported-data). This is clearly distinguishable from the exam/certificate siblings such as safety_renew_exam or declare_certificate_update, which manage the certificate rather than the reported agent data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the use case (you want to clear your reported model/framework/version) and adds the consequence that a later report starts a new baseline, plus the cost note 'Free, for your wallet alone'. It never explicitly says when to use this versus keeping the existing report, and names no alternative tool or prerequisite beyond the certificate staying intact.

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?