Galatic.ai

Control flow run

control_flow_run

Change a Flow Studio run (flowRunId from run_flow; watch it with get_flow_run). "stop" stops the run, marks it cancelled and returns { refundedCredits, actualCost }. "resume" restarts a paused, failed or budget_exceeded run (409 otherwise) from the nodes that did not succeed, using the flow as saved now, so it can spend credits again; newBudgetCap replaces the cap. "approve" decides a node waiting for approval: nodeId plus decision "approve" or "reject" are both required, and reject fails the whole run (409 if the node is not waiting). "rerun" starts a NEW run from nodeId and everything after it, reusing earlier outputs, and returns { newFlowRunId, estimatedCost }; it spends credits.

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>",
      "flowRunId": "<flowRunId>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "control_flow_run"
  }
}

Input Schema

Name	Required	Description
`action`	Yes
`nodeId`	No	Required for approve and rerun: a node id from get_flow_run nodeStatuses.
`context`	Yes	Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
`decision`	No	approve only, required: "approve" or "reject".
`flowRunId`	Yes	From run_flow, or newFlowRunId from a rerun.
`llm_model`	Yes	The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
`newBudgetCap`	No	resume only: new credit cap.
`conversation_id`	No	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 27, 2026

addedInput schema / properties / decision / description

Added value: +"approve only, required: \"approve\" or \"reject\"."

addedInput schema / properties / flowRunId / description

Added value: +"From run_flow, or newFlowRunId from a rerun."

addedInput schema / properties / newBudgetCap / description
```
Added value: +"resume only: new credit cap."
```

addedInput schema / properties / nodeId / description

Added value: +"Required for approve and rerun: a node id from get_flow_run nodeStatuses."

First observedOct 24, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only say it is a non-readonly, non-idempotent mutation, but the description adds the economically important behavior: resume can spend credits again, rerun spends credits, stop refunds credits and returns { refundedCredits, actualCost }, and reject fails the whole run. It also discloses the failure surface (409 conditions) and the return shapes for stop and rerun.

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?

The verb+resource leads, then one compact sentence per action, each packed with the condition, effect, and return value. No filler, no restatement of the name, and the quoted action tokens make it scannable despite being a single dense paragraph.

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 four-action mutation tool with no output schema, the description covers effects, return payloads for stop and rerun, and error conditions. Minor gaps remain: what resume returns and whether these operations are synchronous are not stated, though annotations already cover the safety profile.

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 88%, so the schema already documents most parameters; the description adds marginal but real meaning by tying nodeId and decision to the approve action, stating both are required, and explaining that newBudgetCap replaces the existing cap on resume. It stops short of clarifying nodeId semantics for rerun beyond 'from nodeId and everything after it', which the schema only says must come from get_flow_run nodeStatuses.

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 ('Change a Flow Studio run') and immediately enumerates the four actions with their distinct effects. It explicitly names the siblings it must be distinguished from (flowRunId from run_flow; watch it with get_flow_run), so an agent can route correctly without opening schemas.

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?

Each action carries its own applicability condition: resume applies to a paused, failed or budget_exceeded run and 409s otherwise; approve applies only when a node is waiting for approval and 409s if not; rerun is for starting a new run from a node. It also points to run_flow for starting and get_flow_run for monitoring, giving explicit alternatives.

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

All Galatic.ai 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.