Spaces by Peakflo

workflow_apply_edits

Destructive

Applies a batch of edits to the open draft of one workflow in a single change. Each edit is one of: add_node, update_node, delete_node, add_edge or delete_edge, sent as a JSON list in "operations"; expectedVersion is required. Edits can remove steps, which is why it is marked destructive. Nothing runs, and no connected app is contacted.

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>",
      "operations": "<operations>"
    },
    "name": "workflow_apply_edits"
  }
}

Input Schema

Name	Required	Description
`operations`	Yes	JSON array of add_node, update_node, delete_node, add_edge, or delete_edge operations to apply atomically as one workflow version
`workflowId`	Yes	The workflow ID
`experimentId`	No	Open improvement ID for the current agent task
`versionLabel`	No	Label for the single new version
`expectedVersion`	No	Reject the edit if the latest version no longer matches

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true, and the description earns credit for explaining why ('Edits can remove steps') and for scoping the blast radius ('Nothing runs, and no connected app is contacted'). It stops short of explaining what happens on a version conflict (rejection vs. partial application) or what a successful call returns.

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 tight sentences: what it does, what the operations are plus the version precondition, and the safety scope. Front-loaded with the action and free of 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?

For a 5-parameter mutation tool with no output schema, the description covers the essential mental model: atomic batch, draft-only, no execution. Gaps remain around version-conflict behavior, whether application is all-or-nothing on a bad operation, and what the caller receives (new version id/label).

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%, so every parameter is already documented, and the description mostly restates the operations enum. The only added claim, that expectedVersion is required, actually contradicts the schema's required list rather than clarifying it.

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 ('Applies a batch of edits to the open draft of one workflow') and enumerates the five operation types. The phrase 'in a single change' implicitly distinguishes it from the single-edit siblings (workflow_add_node, workflow_update_node, workflow_add_edge, etc.).

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

Usage Guidelines3/5

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

It establishes the valid context (an open draft of one workflow) and that operations are sent as a JSON list, but never says when to prefer this batch tool over the individual workflow_add_node/workflow_add_edge/workflow_update_node tools. It also asserts 'expectedVersion is required', which conflicts with the schema where only workflowId and operations are required, leaving the agent uncertain whether omitting it is legal.

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.