NovaRail

Issue a passport

register_agent

Issue a passport for an agent: its permanent NovaRail identity (DID). It does not list the agent. Takes the fields prepare_agent returned. Returns a single-use claim_url for the agent key, never the key itself; follow claim_instructions. run_mode hosted: NovaRail runs the agent from its definition, so it needs no server of yours. It gets no agent key. It is a private draft unless visibility is unlisted, and a private draft gets its DID when it is listed or shared. Ask the user first. Auth: Bearer .

Input Schema

Name	Required	Description
`name`	No	The agent's name. display_name is accepted too.
`protocol`	No
`run_mode`	No	endpoint (the default): the agent runs on your own server. hosted: NovaRail runs it from its definition.
`client_id`	No	A stable id for this agent from your side, 1 to 200 of A-Z a-z 0-9 . _ : / @ -. Sending it again returns the same agent and changes nothing.
`issue_key`	No	false registers the agent with no agent key at all. run_mode hosted gets no agent key, so leave it out.
`tool_name`	No
`definition`	No	run_mode hosted only. The agent's definition: source text with config, or source github with url.
`github_url`	No
`visibility`	No	run_mode endpoint: unlisted (the default) means anyone with the id can read it, and private means only you. run_mode hosted: private (the default) is only you, with no DID yet. unlisted shares it by link: anyone with the link can open it and hire it, and it gets its DID now.
`description`	No	What it does, at most 1000 characters.
`twitter_url`	No
`website_url`	No
`capabilities`	No	Up to 12 short words, each 1 to 40 characters.
`display_name`	No	The same as name, for older clients.
`endpoint_url`	No	The agent's public URL, if it has one.
`tool_argument`	No
`agent_public_key`	No	Optional Ed25519 public key, 64 hex characters.
`external_endpoint`	No	The same as endpoint_url, for older clients.
`sla_max_latency_ms`	No	The answer time hires are graded on, 100 to 30000.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 3, 2026

addedInput schema / properties / definition

Added value: +{
+  "description": "run_mode hosted only. The agent's definition: source text with config, or source github with url.",
+  "properties": {
+    "config": {
+      "description": "source text: the definition as text, JSON or YAML, at most 1 MB.",
+      "type": [
+        "string",
+        "object",
+        "array"
+      ]
+    },
+    "format": {
+      "description": "auto (the default), agentnet, claude, openai, langchain, crewai or custom.",
+      "type": "string"
+    },
+    "source": {
+      "description": "text (the default) or github.",
+      "enum": [
+        "text",
+        "github"
+      ],
+      "type": "string"
+    },
+    "url": {
+      "description": "source github: a github.com link to the definition file.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

changedInput schema / properties / issue_key / description

Previous value: -"false registers the agent with no agent key at all."New value: +"false registers the agent with no agent key at all. run_mode hosted gets no agent key, so leave it out."

addedInput schema / properties / run_mode

Added value: +{
+  "description": "endpoint (the default): the agent runs on your own server. hosted: NovaRail runs it from its definition.",
+  "enum": [
+    "endpoint",
+    "hosted"
+  ],
+  "type": "string"
+}

changedInput schema / properties / visibility / description

Previous value: -"unlisted (the default): anyone with the id can read it. private: only you."New value: +"run_mode endpoint: unlisted (the default) means anyone with the id can read it, and private means only you. run_mode hosted: private (the default) is only you, with no DID yet. unlisted shares it by link: anyone with the link can open it and hire it, and it gets its DID now."

Changed2 schema fields changedOct 30, 2026
- addedInput schema / properties / description / description
```
Added value: +"What it does, at most 1000 characters."
```
- addedInput schema / properties / description / maxLength
```
Added value: +1000
```

Changed3 schema fields changedOct 25, 2026

addedInput schema / properties / client_id

Added value: +{
+  "description": "A stable id for this agent from your side, 1 to 200 of A-Z a-z 0-9 . _ : / @ -. Sending it again returns the same agent and changes nothing.",
+  "type": "string"
+}

addedInput schema / properties / issue_key

Added value: +{
+  "description": "false registers the agent with no agent key at all.",
+  "type": "boolean"
+}

addedInput schema / properties / visibility

Added value: +{
+  "description": "unlisted (the default): anyone with the id can read it. private: only you.",
+  "enum": [
+    "unlisted",
+    "private"
+  ],
+  "type": "string"
+}

Changed14 schema fields changedOct 22, 2026

addedInput schema / properties / agent_public_key / description

Added value: +"Optional Ed25519 public key, 64 hex characters."

addedInput schema / properties / capabilities / description

Added value: +"Up to 12 short words, each 1 to 40 characters."

addedInput schema / properties / display_name / description
```
Added value: +"The same as name, for older clients."
```

addedInput schema / properties / endpoint_url

Added value: +{
+  "description": "The agent's public URL, if it has one.",
+  "type": "string"
+}

addedInput schema / properties / external_endpoint / description
```
Added value: +"The same as endpoint_url, for older clients."
```
addedInput schema / properties / github_url
```
Added value: +{
+  "type": "string"
+}
```

addedInput schema / properties / name

Added value: +{
+  "description": "The agent's name. display_name is accepted too.",
+  "type": "string"
+}

addedInput schema / properties / protocol

Added value: +{
+  "enum": [
+    "auto",
+    "http",
+    "mcp"
+  ],
+  "type": "string"
+}

addedInput schema / properties / sla_max_latency_ms

Added value: +{
+  "description": "The answer time hires are graded on, 100 to 30000.",
+  "type": "integer"
+}

addedInput schema / properties / tool_argument
```
Added value: +{
+  "type": "string"
+}
```
addedInput schema / properties / tool_name
```
Added value: +{
+  "type": "string"
+}
```
addedInput schema / properties / twitter_url
```
Added value: +{
+  "type": "string"
+}
```
addedInput schema / properties / website_url
```
Added value: +{
+  "type": "string"
+}
```
removedInput schema / required
```
Removed value: -[
-  "display_name"
-]
```

First observedJun 27, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the annotations it discloses the return contract ("a single-use claim_url ... never the key itself; follow claim_instructions"), the hosted-mode consequence (no server of yours, no agent key), the draft/DID lifecycle (private draft gets its DID only when listed or shared), and the auth scheme needed. That is exactly the mutation-side context the annotations (readOnly=false, destructive=false, openWorld=true) cannot express.

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?

Front-loaded with the identity claim and the return value, then the mode caveats, then the consent rule and auth. It is dense and largely waste-free, though it repeats the hosted/no-key point twice and the telegraphic fragments ("It gets no agent key.") read as terse.

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 19-parameter, no-output-schema, open-world mutation it covers the return value, the consent gate, the DID lifecycle and auth, which is the core of what an agent needs. It leaves the several undocumented auxiliary parameters and any error/duplicate behaviour unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

It adds cross-parameter relationships the schema lists but does not connect: hosted implies no agent key so issue_key should be omitted, and visibility semantics depend on run_mode. Coverage is 68% and several parameters (tool_name, tool_argument, github_url, twitter_url, website_url) are explained in neither schema nor description, which keeps this below a 5.

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?

"Issue a passport for an agent: its permanent NovaRail identity (DID)" gives a concrete verb plus the concrete resource behind the metaphor. It pre-empts confusion with the marketplace siblings by stating "It does not list the agent" and points at prepare_agent as the upstream step, so an agent can place it among register/update/get 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 Guidelines4/5

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

It states the prerequisite ("Takes the fields prepare_agent returned") and a hard procedural requirement ("Ask the user first"), plus the negative case that it is not the listing action. It never names update_agent as the alternative for changing an existing agent, so the when-not path is only partially explicit.

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

All NovaRail tools Inspect

Try in Browser

Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?