Control Plane

Workload — Start a Cron Run

workload_start_cron

Destructive

Trigger an immediate run of a cron workload (useful when the schedule is suspended or you need an out-of-band execution). Each call starts another run with real side effects; confirm with the user.

Input Schema

TableJSON Schema

Name	Required	Description
`gvc`	Yes	GVC slug. If the user named none, list_resources (kind "gvc") and let them choose.
`org`	No	Organization slug.
`name`	Yes	Workload name. Immutable: renaming is delete and recreate, which loses the URL and internal DNS.
`location`	Yes	Location where this job should execute. Must be one of the locations where this workload is deployed — call list_deployments to list the workload's locations.
`containerOverrides`	No	Omit to run the job as configured. To change a container for this run only (command, image, env): one entry per existing container, by name; get_resource (kind "workload") shows them.

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes
`data`	No	The full result. Read this, not only the summary.
`details`	No
`summary`	Yes
`nextSteps`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed37 schema fields changedSep 30, 2026

removedInput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

removedInput schema / additionalProperties
```
Removed value: -false
```

changedInput schema / properties / containerOverrides / description

Previous value: -"OPTIONAL. Most manual runs need no overrides — omit this entirely to run the job exactly as configured. Provide it only to change a container for this single run (e.g. a one-off command, image, or env). It is an array because a workload can have multiple containers; add one entry per container you want to change, each targeting an existing container by `name`. Call get_resource (kind=\"workload\") first to see the workload’s containers (names, image, command, env) so you know what to set."New value: +"Omit to run the job as configured. To change a container for this run only (command, image, env): one entry per existing container, by name; get_resource (kind \"workload\") shows them."

removedInput schema / properties / containerOverrides / items / additionalProperties
```
Removed value: -false
```
removedInput schema / properties / containerOverrides / items / properties / command / maxLength
```
Removed value: -256
```
removedInput schema / properties / containerOverrides / items / properties / cpu / maxLength
```
Removed value: -20
```
removedInput schema / properties / containerOverrides / items / properties / cpu / pattern
```
Removed value: -"^([0-9]+)(m|(\\.[0-9]{1,3}))?$"
```
removedInput schema / properties / containerOverrides / items / properties / env / items / additionalProperties
```
Removed value: -false
```
removedInput schema / properties / containerOverrides / items / properties / env / items / properties / name / maxLength
```
Removed value: -120
```
removedInput schema / properties / containerOverrides / items / properties / env / items / properties / name / minLength
```
Removed value: -1
```
removedInput schema / properties / containerOverrides / items / properties / env / items / properties / name / pattern
```
Removed value: -"^[-._a-zA-Z][-._a-zA-Z0-9]*$"
```

changedInput schema / properties / containerOverrides / items / properties / env / items / properties / value / description

Previous value: -"Literal value, or a secret reference like cpln://secret/<name>.<key>. Secret refs require the workload identity to have reveal permission or the deployment PAUSES — after create_workload, grant it with grant_workload_secret_access."New value: +"Non-sensitive literal value, or a secret reference like cpln://secret/<name>.<key>. Never send passwords, API keys, or tokens. The workload identity needs reveal permission on a referenced secret, or the deployment PAUSES."

removedInput schema / properties / containerOverrides / items / properties / env / items / properties / value / maxLength
```
Removed value: -4096
```
removedInput schema / properties / containerOverrides / items / properties / memory / maxLength
```
Removed value: -20
```
removedInput schema / properties / containerOverrides / items / properties / memory / pattern
```
Removed value: -"^[0-9]+(\\.[0-9]{1,3})?(G|M|k|Gi|Mi|Ki)?$"
```
removedInput schema / properties / containerOverrides / items / properties / name / minLength
```
Removed value: -1
```

changedInput schema / properties / gvc / description

Previous value: -"GVC slug (lowercase kebab-case). Use the GVC the user named; otherwise discover with list_resources (kind=\"gvc\") and let them choose — never guess (a wrong GVC targets the wrong environment)."New value: +"GVC slug. If the user named none, list_resources (kind \"gvc\") and let them choose."

removedInput schema / properties / gvc / maxLength
```
Removed value: -63
```
removedInput schema / properties / gvc / minLength
```
Removed value: -1
```

removedInput schema / properties / gvc / pattern

Removed value: -"^[a-z0-9]([a-z0-9-]{0,61}[a-z0-9])?$"

removedInput schema / properties / location / minLength
```
Removed value: -1
```

changedInput schema / properties / name / description

Previous value: -"Workload name (lowercase kebab-case, must start with a letter, max 49 chars, cannot end with -headless). The name is IMMUTABLE — \"renaming\" requires delete + recreate (loses public URL, internal DNS, policy targetLinks)."New value: +"Workload name. Immutable: renaming is delete and recreate, which loses the URL and internal DNS."

removedInput schema / properties / name / maxLength
```
Removed value: -49
```
removedInput schema / properties / name / minLength
```
Removed value: -2
```
removedInput schema / properties / name / pattern
```
Removed value: -"^[a-z]([-a-z0-9])*[a-z0-9]$"
```

changedInput schema / properties / org / description

Previous value: -"Organization slug (lowercase kebab-case). NEVER guess — if the user has not named one, ask. On org-not-found, stop and ask; do not retry variants."New value: +"Organization slug."

removedInput schema / properties / org / maxLength
```
Removed value: -63
```
removedInput schema / properties / org / minLength
```
Removed value: -1
```

removedInput schema / properties / org / pattern

Removed value: -"^[a-z0-9]([a-z0-9-]{0,61}[a-z0-9])?$"

changedInput schema / required

Previous value: -[
-  "org",
-  "gvc",
-  "name",
-  "location"
-]New value: +[
+  "gvc",
+  "name",
+  "location"
+]

removedOutput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

removedOutput schema / additionalProperties
```
Removed value: -false
```

changedOutput schema / properties / data / description

Previous value: -"The full machine-readable result — list rows, the resource object, query results. Read THIS, not just the summary."New value: +"The full result. Read this, not only the summary."

addedOutput schema / properties / details
```
Added value: +{
+  "type": "string"
+}
```

removedOutput schema / properties / nextSteps / description

Removed value: -"Recommended follow-up actions for this task, in order."

removedOutput schema / properties / ok / description
```
Removed value: -"Whether the call succeeded."
```
removedOutput schema / properties / summary / description
```
Removed value: -"One-line summary of the result."
```

AddedAug 14, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=false, readOnlyHint=false and openWorldHint=true. The description reinforces this usefully by warning that each call starts another run with real side effects and advising confirmation with the user — added value beyond the annotation flags, though it doesn't cover permissions or what a run produces.

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 tight sentences: the action and its trigger condition come first, the side-effect warning second. No filler, no restating of the title.

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 an output schema present and a fully documented input schema plus rich annotations, the short description covers what an agent needs to decide and call. It omits any mention that runs accept per-run container overrides, but that is fully documented in the schema, so the gap is minor.

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%, including detailed per-field notes on containerOverrides, secret references, and the pause-on-missing-reveal caveat, so the schema carries all parameter meaning. The description adds nothing parameter-specific; baseline 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?

States a specific verb and resource — 'Trigger an immediate run of a cron workload' — which is far more precise than a generic 'start'. The scope phrase 'out-of-band execution' implicitly separates it from restart_workload/promote_workload, but no sibling is named explicitly, so it falls short of a 5.

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?

Gives a clear use case: when the schedule is suspended or an out-of-band run is needed. It does not name alternatives (e.g. restart_workload) or state when NOT to use this tool, so it is clear context without explicit routing.

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

All Control Plane 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.