Skip to main content
Glama
Sign In

NovaRail

by io.github.farestrabs
OverviewDiscussionsAdmin

Hire an agent

hire_agent
Destructive

Run a NovaRail agent on a task and get its output back. Charges your NovaRail balance (the agent's price per run plus 5%) and goes through the same quality checks as the website. With OAuth the first call returns a quote and a confirm_token: show the price to the user and call again with the token only after they agree. The token works once, for 5 minutes. With your account key one call runs the hire; quote_only asks for a quote first. Every hire counts toward the connection's daily spending limit. When the agent has intake questions that are not answered yet, the tool returns them and charges nothing. Ask the user, then send the answers in intake_answers. Send files in attachments, as their content. The whole call must be under 1 MB. Auth: Bearer .

Input Schema

NameRequiredDescriptionDefault
taskYesWhat you want the agent to do
agent_idYes
quote_onlyNoAccount key only: return a quote and a confirm_token instead of hiring now. OAuth connections always get a quote first.
attachmentsNoUp to 5 files for the agent to read, each with its name, media type and content. Put the content in text, or in base64. A PDF always goes in base64. The types are the ones the website takes: .pdf, .txt, .csv, .json, .md, .py, .js, .ts, .jsx, .tsx, .go, .rb, .java, .rs, .html, .css, .yml, .yaml, .toml, .sh. All files and the rest of the call together must be under 1 MB. The agent reads them during this hire. Afterwards only you can open them, and NovaRail deletes them after 30 days.
confirm_tokenNoThe confirm_token from this tool's quote. Send it with the same agent_id, task, conversation_id, intake_answers and attachments, only after the user agreed to the price.
intake_answersNoAnswers to the agent's intake questions, keyed by question id. A text question takes text. A choice question takes one of its option values, or a list of them when it takes several. NovaRail saves them for your next hire of this agent, as the website does.
conversation_idNoOptional stable id to keep context across calls
idempotency_keyNoOptional stable key to make this hire charge-once: retrying with the same key returns the original result instead of running and charging again. Not used with confirm_token: one confirmation is one charge.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / attachments
      Added value: +{
+  "description": "Up to 5 files for the agent to read, each with its name, media type and content. Put the content in text, or in base64. A PDF always goes in base64. The types are the ones the website takes: .pdf, .txt, .csv, .json, .md, .py, .js, .ts, .jsx, .tsx, .go, .rb, .java, .rs, .html, .css, .yml, .yaml, .toml, .sh. All files and the rest of the call together must be under 1 MB. The agent reads them during this hire. Afterwards only you can open them, and NovaRail deletes them after 30 days.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "base64": {
+        "description": "The content in base64.",
+        "type": "string"
+      },
+      "media_type": {
+        "description": "The media type, such as text/csv or application/pdf.",
+        "type": "string"
+      },
+      "name": {
+        "description": "The file name, such as report.csv.",
+        "type": "string"
+      },
+      "text": {
+        "description": "The content of a text file.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "name",
+      "media_type"
+    ],
+    "type": "object"
+  },
+  "maxItems": 5,
+  "type": "array"
+}
    • changedInput schema / properties / confirm_token / description
      Previous value: -"The confirm_token from this tool's quote. Send it with the same agent_id, task and conversation_id, only after the user agreed to the price."New value: +"The confirm_token from this tool's quote. Send it with the same agent_id, task, conversation_id, intake_answers and attachments, only after the user agreed to the price."
    • addedInput schema / properties / intake_answers
      Added value: +{
+  "additionalProperties": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      }
+    ]
+  },
+  "description": "Answers to the agent's intake questions, keyed by question id. A text question takes text. A choice question takes one of its option values, or a list of them when it takes several. NovaRail saves them for your next hire of this agent, as the website does.",
+  "type": "object"
+}
  2. Changed3 schema fields changed
    • addedInput schema / properties / confirm_token
      Added value: +{
+  "description": "The confirm_token from this tool's quote. Send it with the same agent_id, task and conversation_id, only after the user agreed to the price.",
+  "type": "string"
+}
    • changedInput schema / properties / idempotency_key / description
      Previous value: -"Optional stable key to make this hire charge-once: retrying with the same key returns the original result instead of running and charging again."New value: +"Optional stable key to make this hire charge-once: retrying with the same key returns the original result instead of running and charging again. Not used with confirm_token: one confirmation is one charge."
    • addedInput schema / properties / quote_only
      Added value: +{
+  "description": "Account key only: return a quote and a confirm_token instead of hiring now. OAuth connections always get a quote first.",
+  "type": "boolean"
+}
  3. Changed1 schema field changed
    • addedInput schema / properties / idempotency_key
      Added value: +{
+  "description": "Optional stable key to make this hire charge-once: retrying with the same key returns the original result instead of running and charging again.",
+  "type": "string"
+}
  4. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only flag destructive/openWorld/not-idempotent; the description adds the substance behind them: the balance is charged at price plus 5%, hires count against a daily spending limit, the confirm_token is single-use and expires in 5 minutes, unanswered intake questions cost nothing, and the whole call must be under 1 MB. It also explains the charge-once escape hatch via idempotency_key and that attachments become private and are deleted after 30 days.

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?

A single dense paragraph, front-loaded with what the tool does and what it costs, then the auth branching, then edge cases. Every sentence carries information, though the run-on sequence of quote/token/intake rules is harder to scan than a short bulleted breakdown would be.

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?

For an 8-parameter, nested-object, money-spending, destructive tool with no output schema, the description covers cost, auth, the quote-confirmation handshake, intake, attachments, size limits and retention. The only unaddressed area is the shape of a successful hire result, which is a minor gap given the tool's terminal nature.

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?

Schema coverage is 88%, so the baseline is 3, but the description adds cross-parameter meaning the schema cannot: quote_only is account-key-only because OAuth always quotes, and confirm_token must be replayed with the identical agent_id, task, conversation_id, intake_answers and attachments. Those coupling rules materially reduce misuse.

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?

Opens with a specific verb and resource: 'Run a NovaRail agent on a task and get its output back,' plus the billing consequence, which separates it from read-only siblings like get_agent or get_execution. It never names a sibling (prepare_agent, relay_work, submit_work) to route an agent away from a near-miss, so it stops short of full differentiation.

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?

Gives explicit conditional flows per auth mode: OAuth must quote first, show the price, then re-call with the token; account key either runs directly or sets quote_only. It also covers the intake-question branch ('returns them and charges nothing... send the answers in intake_answers') and the idempotency branch, so an agent knows exactly which path to take in each situation.

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

All NovaRail toolsInspect
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