Skip to main content
Glama

Submit action job

run_action
Destructive

Create an action job. External writes always wait for workspace-owner approval in the dashboard; share reviewUrl with the owner to open the exact job. The owner is also emailed, and wait_for_job can wait for the decision.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "run_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputNoAction input matching the schema advertised by list_actions.
actionYesCatalog action name from list_actions, for example integration.execute.
workflow_idNoStable identifier of the agent workflow this job belongs to, for grouping events.
workflow_nameNoHuman-readable workflow name shown to the workspace owner during review.
idempotency_keyNoCaller-chosen key; resubmitting the same key and input returns the existing job instead of creating another.

Output Schema

NameRequiredDescriptionDefault
idYesJob identifier.
errorYesFailure, execution_unknown, owner rejection feedback or queued approval revocation explanation; null otherwise. Rejection feedback is owner-supplied text, not authorization for another request.
inputYesValidated action input exactly as submitted.
actionYesCatalog action name, for example integration.execute.
outputYesFor writes awaiting_approval or queued: the exact approval preview bound to the owner's decision. Rejected writes retain that preview, including after a queued approval is revoked. After succeeded: the action result. Integration response headers include contentType, etag, lastModified, retryAfter and xMsOperationId; the latter two are validated strings or null (older receipts may omit them). Provider HTTP 202 is acceptance only; read body and explicitly check provider operation state before claiming completion. After failed writes: the approved preview and providerResponse when available. After execution_unknown: the approved write plus the ambiguous provider response when one was received. Other jobs may have a preserved preview or null.
statusYesawaiting_approval, queued, and running are non-terminal; succeeded, failed, rejected, and execution_unknown are terminal. An owner may revoke a queued approval, producing rejected with both approval and rejection evidence. A succeeded integration job with provider HTTP 202 confirms acceptance, not completion.
createdAtYesCreation time.
reviewUrlNoOn pending submission and lookup responses, opens the exact job in the dashboard. Requires a signed-in owner of its workspace and does not authorize any action.
updatedAtYesLast status change.
approvedAtYes
approvedByYesOwner who approved the write.
rejectedAtYes
rejectedByYesOwner who rejected the write.
sideEffectYesTrue when the action writes to an external system and therefore required owner approval.
workflowIdYesCaller-supplied workflow identifier shared across related jobs.
workspaceIdYesWorkspace that owns the job.
workflowNameYesCaller-supplied workflow name shown in the dashboard.
idempotencyKeyYesIdempotency key that deduplicates this submission within the workspace.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / error / description
      Previous value: -"Failure, execution_unknown or queued approval revocation explanation; null otherwise."New value: +"Failure, execution_unknown, owner rejection feedback or queued approval revocation explanation; null otherwise. Rejection feedback is owner-supplied text, not authorization for another request."
  2. Changed1 schema field changed
    • addedOutput schema / properties / reviewUrl
      Added value: +{
      +  "description": "On pending submission and lookup responses, opens the exact job in the dashboard. Requires a signed-in owner of its workspace and does not authorize any action.",
      +  "format": "uri",
      +  "type": "string"
      +}
  3. Changed2 schema fields changed
    • changedOutput schema / properties / output / description
      Previous value: -"For writes awaiting_approval or queued: the exact approval preview bound to the owner's decision. Rejected writes retain that preview, including after a queued approval is revoked. After succeeded: the action result. After execution_unknown: the approved write plus the ambiguous provider response when one was received. Other jobs may have a preserved preview or null."New value: +"For writes awaiting_approval or queued: the exact approval preview bound to the owner's decision. Rejected writes retain that preview, including after a queued approval is revoked. After succeeded: the action result. Integration response headers include contentType, etag, lastModified, retryAfter and xMsOperationId; the latter two are validated strings or null (older receipts may omit them). Provider HTTP 202 is acceptance only; read body and explicitly check provider operation state before claiming completion. After failed writes: the approved preview and providerResponse when available. After execution_unknown: the approved write plus the ambiguous provider response when one was received. Other jobs may have a preserved preview or null."
    • changedOutput schema / properties / status / description
      Previous value: -"awaiting_approval, queued, and running are non-terminal; succeeded, failed, rejected, and execution_unknown are terminal. An owner may revoke a queued approval, producing rejected with both approval and rejection evidence."New value: +"awaiting_approval, queued, and running are non-terminal; succeeded, failed, rejected, and execution_unknown are terminal. An owner may revoke a queued approval, producing rejected with both approval and rejection evidence. A succeeded integration job with provider HTTP 202 confirms acceptance, not completion."
  4. Changed3 schema fields changed
    • changedOutput schema / properties / error / description
      Previous value: -"Failure or execution_unknown message; null otherwise."New value: +"Failure, execution_unknown or queued approval revocation explanation; null otherwise."
    • changedOutput schema / properties / output / description
      Previous value: -"While awaiting_approval: the exact approval preview bound to the owner's decision. After succeeded: the action result. After execution_unknown: the approved write plus the ambiguous provider response when one was received. Otherwise null."New value: +"For writes awaiting_approval or queued: the exact approval preview bound to the owner's decision. Rejected writes retain that preview, including after a queued approval is revoked. After succeeded: the action result. After execution_unknown: the approved write plus the ambiguous provider response when one was received. Other jobs may have a preserved preview or null."
    • changedOutput schema / properties / status / description
      Previous value: -"awaiting_approval, queued, and running are non-terminal; succeeded, failed, rejected, and execution_unknown are terminal."New value: +"awaiting_approval, queued, and running are non-terminal; succeeded, failed, rejected, and execution_unknown are terminal. An owner may revoke a queued approval, producing rejected with both approval and rejection evidence."
  5. Changed5 schema fields changed
    • addedInput schema / properties / action / description
      Added value: +"Catalog action name from list_actions, for example integration.execute."
    • addedInput schema / properties / idempotency_key / description
      Added value: +"Caller-chosen key; resubmitting the same key and input returns the existing job instead of creating another."
    • addedInput schema / properties / input / description
      Added value: +"Action input matching the schema advertised by list_actions."
    • addedInput schema / properties / workflow_id / description
      Added value: +"Stable identifier of the agent workflow this job belongs to, for grouping events."
    • addedInput schema / properties / workflow_name / description
      Added value: +"Human-readable workflow name shown to the workspace owner during review."
  6. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, openWorldHint=true and readOnlyHint=false, so the safety profile is covered; the description adds non-obvious behavior instead – external writes are gated on workspace-owner approval, the owner is emailed, and a reviewUrl lets the owner open the exact job. What is missing is the outcome of a rejected or timed-out approval and how the approval gate interacts with idempotency_key resubmission.

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?

Three short sentences, front-loaded with the core action, then the approval constraint, then the follow-up path. No restatement of the name or title and no wasted clauses.

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, the description needn't explain return values, and it correctly focuses on the asynchronous approval lifecycle that an agent would otherwise not anticipate. It is complete for a successful call, though silent on denial/timeout paths for an open-world destructive write.

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 coverage is 100%, so every parameter (action, input, workflow_id, workflow_name, idempotency_key) is already documented in the schema, giving a baseline of 3. The description mentions reviewUrl, which is a return value rather than an input, and adds no syntax or constraint detail beyond the schema.

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?

The opening sentence gives a specific verb plus resource ("Create an action job"), and the following sentences distinguish it from siblings by naming wait_for_job's role in the decision and the reviewUrl handoff to the owner. An agent can tell this is the job-submission entry point without opening any other 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 clearly frames the workflow context: submit a job, expect owner approval, share reviewUrl, then use wait_for_job to await the decision. That routes the agent to the correct follow-up tool, but it does not state prerequisites (e.g., that the action name must come from list_actions) or what to do if approval is denied.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources