Spaces by Peakflo

workflow_execute

Destructive

Starts one real run of a workflow's active (or trial) version with the inputs you give. The run performs exactly the steps shown by workflow_get for that workflow and nothing else. Those steps can act on connected systems, for example sending an email or writing to an ERP, so confirm with the user first. Each active workflow is also offered as its own wf_* tool with its own inputs. Requires an idempotencyKey that is new for each new request. Returns the run status and a link to the run.

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": {
      "workflowId": "<workflowId>"
    },
    "name": "workflow_execute"
  }
}

Input Schema

Name	Required	Description
`async`	No	Return a run handle through Inngest
`inputs`	No	A JSON STRING (not an object) of input key-value pairs matching the workflow input node outputs, for example "{\"month\":\"10/2026\"}". Leave empty if the workflow has no inputs.
`taskId`	No	Related task ID
`sessionId`	No	Related session ID
`versionId`	No	Pinned version UUID
`workflowId`	Yes	The workflow ID to execute
`idempotencyKey`	No	Stable key for the requested run

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Although the annotations already set destructiveHint=true and openWorldHint=true, the description goes beyond them by saying exactly how the run operates: it performs only the steps shown by workflow_get, and those steps can send email or write to an ERP. It adds the user-confirmation requirement, the idempotency-key rule, and what is returned (run status plus a link).

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?

It is front-loaded with the core action, and every following sentence adds a distinct fact: scope, side effects, confirmation, alternative tools, idempotency, and return values. Five sentences make it slightly long, but none are redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

It covers the run's scope, the safety obligation, and the return values even though there is no output schema. However, it does not explain how version selection interacts with the active or trial version, nor what the async mode does beyond the schema description, so some behavior is left to the annotation alone.

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 description coverage is 100%, so the baseline would be 3, but the description adds meaning that the schema cannot give: the idempotencyKey must be new for every request. It also tells the caller to pass inputs for the run, which the schema otherwise only describes as a JSON string.

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 description uses a specific verb and resource: 'Starts one real run of a workflow's active (or trial) version with the inputs you give.' The word 'real' separates it from the dry-run and test-run siblings, and it names workflow_get as the source of truth for what the run does.

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 tells the agent to confirm with the user before any side-effecting action and points out that each active workflow also has its own wf_* tool, which helps the agent choose between them. It does not explicitly compare this tool with workflow_dry_run, workflow_test_run, or workflow_run_wait, so the alternatives are incomplete.

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

All Spaces by Peakflo 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.