Skip to main content
Glama

Second Wind AI

stack stuck rollback failed

cfn-stuck-stack-recovery-plan
Read-onlyIdempotent

Send the stack events of a stack stuck in UPDATE_ROLLBACK_FAILED, DELETE_FAILED or ROLLBACK_FAILED, including nested stack events. Separates the failure that started the rollback from the ones that blocked it, classifies each blocker, and returns the exact continue-update-rollback or delete command with only the resources that are safe to skip, plus how to reconcile each skipped resource afterwards. Use when the error reads: UPDATE_ROLLBACK_FAILED | Stack is in UPDATE_ROLLBACK_FAILED state and can not be updated | DELETE_FAILED | ROLLBACK_FAILED | ROLLBACK_COMPLETE state and can not be updated. Covers: Works from supplied stack events for one stack and its nested stacks. Does not call AWS. StackSets operations are not covered. Price: 5.00 USDC on Base via x402, charged only when the case is solved.

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": {
      "stack_name": "<stack_name>",
      "events": "<events>"
    },
    "name": "cfn-stuck-stack-recovery-plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
eventsYesStackEvents from aws cloudformation describe-stack-events --stack-name NAME, newest operation included. Any order.
stack_nameYes
service_role_arnNoThe stack's service role, if it uses one.
nested_stack_eventsNoFor nested stacks that failed: their StackEvents keyed by the nested stack's LogicalResourceId in the parent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), and the description adds genuinely non-inferable behavior: it operates purely on supplied events without calling AWS, and it is a paid call (5.00 USDC on Base via x402, charged only when the case is solved). The charge-on-success condition is exactly the kind of context an agent must know before invoking.

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?

Front-loads the core action and trigger error strings before the cost and scope notes, which is the right ordering. The 'Covers:' fragment is slightly awkward and the exclusion 'Does not call AWS' is buried mid-sentence, but there is little genuine 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?

With no output schema, the description carries the return-value burden and does describe the payload: the classified blockers, the exact continue-update-rollback/delete command with only safe-to-skip resources, and per-resource reconciliation guidance. What it omits is the shape of the response (fields, ordering, how the command is presented), which an agent would need to parse results reliably.

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 coverage is 75%, so the schema already documents events, nested_stack_events, and service_role_arn; the description only adds the relationship that nested stack events are included and that everything is scoped to one stack. It says nothing about stack_name, event volume limits, or ordering expectations beyond what the schema states. Baseline 3 is appropriate since the schema does most of the work.

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 ('Send the stack events of a stack stuck in UPDATE_ROLLBACK_FAILED, DELETE_FAILED or ROLLBACK_FAILED, including nested stack events') and then specifies the transformation performed: separating the initiating failure from blocking failures, classifying blockers, and emitting the exact continue-update-rollback/delete command. It also scopes itself ('one stack and its nested stacks', 'StackSets operations are not covered'), which separates it from the sibling recovery/analysis tools.

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 trigger conditions by quoting the literal error strings an agent would see ('Stack <name> is in UPDATE_ROLLBACK_FAILED state and can not be updated', 'ROLLBACK_COMPLETE state and can not be updated'). It also states exclusions: does not call AWS, StackSets not covered, single stack plus nested stacks only.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources