SwarmIO

runs.get

Read-only

A run's status and metadata. Poll until status is completed/failed/cancelled.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`run_id`	Yes	The run_id returned by runs.launch.

Output Schema

TableJSON Schema

Name	Required	Description
`meta`	No	Run metadata: id, mode, title, timing.
`error`	No	Failure detail when status is failed, else null.
`usage`	No	Token meters for the run — null while the run is still running, an object once it settles.
`status`	No	running \| completed \| failed \| cancelled.
`cancelling`	No	A stop was requested but the run has not unwound yet.
`has_report`	No	True once runs.report will answer with the report.
`finished_at`	No	RFC 3339 completion time; null while running.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 14, 2026

addedOutput schema / properties / error / type

Added value: +[
+  "string",
+  "object",
+  "null"
+]

addedOutput schema / properties / finished_at

Added value: +{
+  "description": "RFC 3339 completion time; null while running.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / properties / usage / description

Previous value: -"Token meters for the run."New value: +"Token meters for the run — null while the run is still running, an object once it settles."

changedOutput schema / properties / usage / type

Previous value: -"object"New value: +[
+  "object",
+  "null"
+]

First observedSep 1, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds meaningful behavioral context by naming the terminal statuses (completed/failed/cancelled) and indicating that the tool is meant for polling.

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?

Two short sentences communicate the purpose, resource, and polling behavior with no filler. The key information is front-loaded and every word earns its place.

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?

With one required parameter, a full output schema, and safety annotations, the description covers the main lifecycle context an agent needs. It does not mention not-found or error behavior, but that is a minor gap given the low complexity and available structured metadata.

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?

The input schema fully documents run_id as the value returned by runs.launch, giving 100% schema description coverage. The tool description adds no additional parameter nuance, so the baseline 3 is appropriate.

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 identifies the resource (a run) and the data returned (status and metadata), and the polling instruction signals a read operation. It is specific enough to distinguish this from siblings like runs.cancel and runs.launch, though it lacks an explicit verb such as 'get' or 'retrieve'.

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?

The description clearly states the intended usage pattern: poll until the run reaches a terminal status. It does not explicitly contrast with runs.report or runs.cancel, but the polling context is unambiguous and actionable.

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

All SwarmIO 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?