Runcrate

List jobs

list_jobs

Read-onlyIdempotent

List jobs, newest first, with status, command, GPU, exit_code and cost_usd. A job runs one command on its own GPU machine (run_job starts one). Filter by tag, a name substring (q) or a group (group_id) to find earlier runs. cost_usd covers the machine's whole time, not only the command's: from when its machine came up until it stopped, so setup before the command (pulling the image, waiting for the GPU driver, unpacking code) is included, at each machine's hourly rate (cost_per_hour is the current one's) and with every attempt added up. It is in USD to six decimal places, so a short run is not shown as $0, and while the job runs it is the cost so far. The charge on the billing page can differ slightly: machines billed by the minute are charged whole minutes, including about 30 seconds of teardown, and time some hosts report offline is not charged.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_jobs"
  }
}

Input Schema

Name	Required	Description
`q`	No	Only jobs whose name contains this
`tag`	No	Only jobs with this tag, as key:value, e.g. "team:ml"; a list needs every one
`limit`	No	How many jobs (default 20, max 100)
`status`	No	Only these statuses, comma separated: queued, starting, running, succeeded, failed, cancelled, timed_out
`group_id`	No	Only the jobs of this group (from run_job with count or params)
`workspace`	No	Workspace ID (optional: defaults to the authenticated workspace)
`environment`	No	Environment name (optional: defaults to the environment this session acts in)

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 21, 2026

removedInput schema / properties / env

Removed value: -{
-  "description": "Environment name (optional — defaults to main)",
-  "type": "string"
-}

addedInput schema / properties / environment

Added value: +{
+  "description": "Environment name (optional: defaults to the environment this session acts in)",
+  "type": "string"
+}

changedInput schema / properties / workspace / description

Previous value: -"Workspace ID (optional — defaults to authenticated workspace)"New value: +"Workspace ID (optional: defaults to the authenticated workspace)"

Changed3 schema fields changedOct 21, 2026

addedInput schema / properties / group_id

Added value: +{
+  "description": "Only the jobs of this group (from run_job with count or params)",
+  "type": "string"
+}

addedInput schema / properties / q

Added value: +{
+  "description": "Only jobs whose name contains this",
+  "type": "string"
+}

addedInput schema / properties / tag

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  ],
+  "description": "Only jobs with this tag, as key:value, e.g. \"team:ml\"; a list needs every one"
+}

First observedOct 20, 2026

TDQS

A4/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it states the sort order, that cost_usd is cumulative across attempts and includes machine setup time, that it is a running figure while the job is active, and that it can differ from the billing page because of per-minute rounding and uncharged offline time. That is unusually rich behavioral context for a read tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The first two sentences are well front-loaded and efficient, but roughly two-thirds of the text is a deep dive into cost_usd accounting that concerns a returned field rather than selecting or invoking this tool. That material is accurate but disproportionate here and would sit better on a cost or get_job definition.

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 seven-parameter, all-optional list tool with full schema coverage and no output schema, the description covers ordering, returned fields, filtering, and cost interpretation, which is enough to call it correctly. The only gap is that it does not point to siblings for single-job detail or artifacts.

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 the schema already documents all seven parameters, including tag's key:value form and the status enum list. The description only restates the filter intent ('find earlier runs') without adding syntax or format detail beyond the schema, so the baseline of 3 applies.

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?

The description opens with a specific verb and resource ('List jobs') and names the returned fields (status, command, GPU, exit_code, cost_usd) plus the default ordering (newest first). It also distinguishes itself from run_job by noting that run_job starts a job, though it never contrasts with get_job or list_job_artifacts, which are the closest siblings.

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 gives concrete guidance on how to narrow results: filter by tag, by name substring via q, or by group_id 'to find earlier runs'. That is clear usage context, but there is no explicit when-not guidance (e.g. use get_job for a single job's detail, or list_job_artifacts for outputs).

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

All Runcrate 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.