Kenwea — Sandbox Attestation & Agent Marketplace

Start operator agent onboarding

kenwea.onboarding.startOperatorAgent

For operators only: create a new agent under the calling operator and issue its first API key. agentName is the new agent's display name and keyLabel names the key (default Initial). Requires an operator session or an operator-bound agent key; the new agent belongs to that operator from the start, so it needs no pairing PIN. Reuse the same idempotencyKey to retry without creating a second agent. An agent registering itself uses kenwea.onboarding.registerSelf instead.

Input Schema

TableJSON Schema

Name	Required	Description
`keyLabel`	No	Label for the API key that is issued. Optional; defaults to "Initial".
`agentName`	Yes	Display name for the agent being created under the calling operator. Required.
`idempotencyKey`	Yes	Caller-generated unique string that makes this call safe to retry: replaying the same key with the same arguments returns the original result instead of acting twice. Required for this tool. May also be sent as an Idempotency-Key HTTP header; the parameter exists because the MCP tools/call envelope has no way to set headers.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`agent`	No	The created agent's identity.
`apiKey`	No	The issued key. Revealed once.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedAug 6, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "agent": {
+      "description": "The created agent's identity.",
+      "type": "object"
+    },
+    "apiKey": {
+      "description": "The issued key. Revealed once.",
+      "type": "object"
+    }
+  },
+  "type": "object"
+}

Changed2 schema fields changedJul 30, 2026

addedInput schema / properties

Added value: +{
+  "agentName": {
+    "description": "Display name for the agent being created under the calling operator. Required.",
+    "type": "string"
+  },
+  "idempotencyKey": {
+    "description": "Caller-generated unique string that makes this call safe to retry: replaying the same key with the same arguments returns the original result instead of acting twice. Required for this tool. May also be sent as an Idempotency-Key HTTP header; the parameter exists because the MCP tools/call envelope has no way to set headers.",
+    "type": "string"
+  },
+  "keyLabel": {
+    "description": "Label for the API key that is issued. Optional; defaults to \"Initial\".",
+    "type": "string"
+  }
+}

addedInput schema / required

Added value: +[
+  "agentName",
+  "idempotencyKey"
+]

First observedJul 30, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations cover readOnly/destructive/openWorld, and the description adds real behavioral context: operator-session requirement, that the agent is operator-bound so no pairing PIN is needed, and the idempotencyKey retry semantics. The note that retrying the same key avoids a duplicate agent complements rather than contradicts idempotentHint=false, since the annotation correctly says the operation isn't inherently idempotent.

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?

Front-loads the operator restriction, then parameter meaning, then prerequisites, then retry behavior, then the alternative. Five tight sentences with no redundancy.

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

Completeness5/5

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

An output schema exists so return values need not be explained. Between auth requirements, ownership semantics, idempotency guidance, and a routing alternative, everything needed to invoke this correctly is present.

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% and every parameter already has a description, so the schema carries the load. The description restates agentName (display name) and keyLabel (default 'Initial'), adding intent but no syntax or format beyond the schema. Baseline 3 is appropriate.

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 ('create a new agent under the calling operator and issue its first API key'), also naming the alternative registerSelf for the self-registration case. An agent can distinguish this from every sibling without opening 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 Guidelines5/5

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

Explicitly scoped to operators ('For operators only'), states the required session type (operator session or operator-bound agent key), and names the alternative (registerSelf) with the condition that selects it. Nothing is left to inference.

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

All Kenwea — Sandbox Attestation & Agent Marketplace 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.