Aeroz

register_ai_system

register_ai_system

Destructive

Register an AI system, by the rules of POST /v1/ai/systems. Name and purpose are fixed once registered. A high-risk system with no oversight is accepted with a warning (AI Act Art. 14). Classifying the system is the company's call; do not choose a risk class the user has not given you: leave it unassessed.

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": {
      "name": "<name>",
      "purpose": "<purpose>"
    },
    "name": "register_ai_system"
  }
}

Input Schema

Name	Required	Description
`name`	Yes
`model`	No
`purpose`	Yes	What the system decides or produces, in a sentence.
`provider`	No
`oversight`	No	Who can stop or override it, and how.
`risk_class`	No
`ai_act_role`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already flag destructive=true and non-idempotent, and the description adds substantive context beyond them: name and purpose are immutable after registration, and a high-risk system without oversight is accepted with a warning rather than rejected. It does not explain what a duplicate registration does (non-idempotency) or what the response contains.

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 tight sentences, front-loaded with the action and immediately followed by the consequences. The endpoint reference is mildly infrastructural but frames the immutability rules usefully; little waste overall.

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 7-parameter destructive mutation with low schema coverage and no output schema, the description covers the highest-stakes behaviors (immutability, risk-class defaults, warning-on-missing-oversight) but leaves half the parameters and the return value unaddressed.

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 only 29%, so the description needs to compensate. It adds meaning for name/purpose (immutability), oversight (implicitly tied to Art. 14), and risk_class (default to unassessed), but leaves model, provider, and ai_act_role entirely unexplained in both schema and description.

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?

States a specific verb ('register') and resource ('AI system') and anchors it to the backing endpoint. It is clearly distinct from the sibling list_ai_systems, though the description never names that sibling explicitly.

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 an explicit exclusion for the risk_class decision: 'do not choose a risk class the user has not given you: leave it unassessed.' That is real when/when-not guidance, but there is no guidance on when to call this versus list_ai_systems or record_ai_decision.

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

All Aeroz 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?