Spaces by Peakflo

workflow_save_version

Destructive

Save the open draft as one version. Call it once, when your work is complete; do not save before each test. If the workflow has no active version and the last draft test was clean, the save activates it. If it already has an active version, the save starts a trial of the new version and the current one keeps running; then call workflow_test_run twice (once for a cron that fires less than weekly) to make it live. Returns userSummary, panelUrl, summaryLink, and editorUrl.

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_save_version"
  }
}

Input Schema

Name	Required	Description	Default
`note`	No
`workflowId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations declare destructiveHint=true, and the description goes well beyond that by explaining the two possible state outcomes: activation when no active version exists and the last draft test was clean, versus a trial while the current version keeps running. It also lists the returned fields (userSummary, panelUrl, summaryLink, editorUrl), compensating for the absent output schema. It does not explain what the 'destructive' aspect actually destroys (e.g., overwritten prior draft state), which keeps it below a 5.

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?

Front-loaded with the action, then cadence, then branching state behavior, then follow-up calls, then return payload. Every sentence carries decision-relevant information and there is no filler.

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?

No output schema exists and the description compensates by enumerating the returned fields, and it fully covers the branching post-save workflows an agent must handle. The remaining hole is parameter-level meaning, particularly the undocumented note field and the workflowId binding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden, yet it never mentions workflowId or note. The 'note' parameter is completely unexplained, and it is unclear whether the save targets the workflow identified by workflowId or an implicit open draft. This is a meaningful gap for a two-parameter mutation tool.

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?

States a specific verb and resource ('Save the open draft as one version') and implicitly separates itself from siblings like workflow_test_run and workflow_validate by describing the state transition it performs. An agent can identify this as the commit step of the workflow authoring loop without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit cadence guidance ('Call it once, when your work is complete; do not save before each test') with a clear when-not rule, then names the required follow-up sibling calls ('call workflow_test_run twice'). This is exactly the routing information an agent needs in a multi-tool authoring workflow.

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.