retry_workflow_runPrepare a safe retry attempt from the start or a failed node.
| Name | Required | Description | Default |
|---|---|---|---|
| run_id | Yes | Terminal workflow run ID. | |
| max_credits | No | New attempt spending ceiling; null removes it. Omit to inherit it. | |
| from_node_id | No | Optional failed node ID. Omit to retry from the start. | |
| idempotency_key | Yes | Required stable key for safe retries. |
Changes observed during successful MCP inspections.
Input schema / properties / max_creditsAdded value: +{
+ "description": "New attempt spending ceiling; null removes it. Omit to inherit it.",
+ "minimum": 0,
+ "type": [
+ "integer",
+ "null"
+ ]
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is a non-read-only, non-destructive, non-open-world write, so the safety profile is covered. The description adds the 'safe' framing (consistent with the required idempotency key) and the start-vs-failed-node choice, but is silent on what actually happens to the original run and whether a new attempt is created.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single short sentence with the retry scope front-loaded and no filler. It is efficient, though so terse that it borders on under-specification for a mutation tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a four-parameter write operation with no output schema and no annotations describing effects, the description omits critical behavior: whether a new run is created, what happens to the terminal run, and how credit ceilings interact with the parent. The schema documents parameters but not the mutation's consequences.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description echoes from_node_id semantics ('from the start or a failed node') but adds nothing about max_credits inheritance or the idempotency key's stability requirement beyond what the schema already states.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a clear verb (retry) and resource (workflow run) and adds scope ('from the start or a failed node'). It does not differentiate from close siblings like continue_workflow_run or get_workflow_run, but the core action is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use guidance, prerequisites, or alternatives are given. The agent must infer from the name and the schema's 'Terminal workflow run ID' hint that this applies only to finished/failed runs and is not the same as continue_workflow_run.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.