simulation.recover_resourceRequires simulationId and resourceId from simulation.create. Requests reversible resource recovery; success does not prove healthy. Next tool is simulation.step, then simulation.metrics to inspect resource health. No API key required; demo limits apply. Read resource cwm://guides/public/simulation.recover_resource
| Name | Required | Description | Default |
|---|---|---|---|
| resourceId | No | ||
| resourceName | No | ||
| simulationId | No | ID returned by simulation.create. |
Changes observed during successful MCP inspections.
Input schema / properties / simulationId / descriptionAdded value: +"ID returned by simulation.create."Input schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"Input schema / properties / resourceId / descriptionRemoved value: -"ID of the failed resource to recover"Input schema / properties / resourceName / descriptionRemoved value: -"Exact case-insensitive name of the failed resource to recover"Input schema / properties / simulationId / descriptionRemoved value: -"Simulation ID returned by simulation.create. Preserve Mcp-Session-Id to omit this field and use the session's current simulation; if your connector starts a fresh MCP session for each call (for example Grok Bot or Cursor), pass this explicit ID after every fresh initialization. A fresh session has no current-simulation pointer and returns NO_ACTIVE_SIMULATION when the ID is omitted. Anonymous capabilities are short-lived (30 minutes by default), unguessable, and revoked when the demo expires or is deleted; proxy IP changes do not invalidate them. Do not treat the ID as a durable share link."Output schema / (root)Previous value: -{
- "$schema": "http://json-schema.org/draft-07/schema#",
- "additionalProperties": true,
- "properties": {
- "deactivatedFailureIds": {
- "items": {
- "type": "string"
- },
- "type": "array"
- },
- "previousHealth": {
- "type": "string"
- },
- "recoveryProgress": {
- "additionalProperties": false,
- "properties": {
- "cooldown": {
- "additionalProperties": false,
- "properties": {
- "completedSteps": {
- "type": "number"
- },
- "remainingSteps": {
- "type": "number"
- },
- "requiredSteps": {
- "type": "number"
- },
- "target": {
- "anyOf": [
- {
- "enum": [
- "warning",
- "healthy"
- ],
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- }
- },
- "required": [
- "target",
- "completedSteps",
- "requiredSteps",
- "remainingSteps"
- ],
- "type": "object"
- },
- "parkWindow": {
- "additionalProperties": false,
- "properties": {
- "completedSteps": {
- "type": "number"
- },
- "remainingSteps": {
- "type": "number"
- },
- "totalSteps": {
- "type": "number"
- }
- },
- "required": [
- "totalSteps",
- "completedSteps",
- "remainingSteps"
- ],
- "type": "object"
- },
- "state": {
- "enum": [
- "parked",
- "blocked",
- "cooling_down",
- "healthy"
- ],
- "type": "string"
- }
- },
- "required": [
- "state",
- "parkWindow",
- "cooldown"
- ],
- "type": "object"
- },
- "recoveryState": {
- "type": "string"
- },
- "resolvedResourceId": {
- "type": "string"
- },
- "resolvedResourceName": {
- "type": "string"
- },
- "simulationId": {
- "type": "string"
- },
- "simulationIdSource": {
- "enum": [
- "explicit",
- "session_default"
- ],
- "type": "string"
- },
- "stepsToHealthy": {
- "type": "number"
- },
- "stepsToHealthyIsLowerBound": {
- "type": "boolean"
- }
- },
- "type": "object"
-}New value: +nullOutput schema / properties / recoveryProgress / properties / state / enumPrevious value: -[
- "parked",
- "cooling_down",
- "healthy"
-]New value: +[
+ "parked",
+ "blocked",
+ "cooling_down",
+ "healthy"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, and the description usefully adds that recovery is reversible and that success does not prove health, plus demo-limit and no-API-key context. However, it omits whether the request is asynchronous, whether repeat calls on an already-recovering resource are safe (relevant given idempotentHint=false), and what the response looks like with no output schema to lean on.
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?
Four short, front-loaded sentences: prerequisite, semantics, workflow, constraints. Each carries information an agent needs, with only the trailing guide pointer being of marginal value.
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 non-idempotent mutation with no output schema, the description supplies the key missing pieces: required inputs, reversibility, and the caveat that success is not proof of health, plus the follow-up inspection path. The unexplained resourceName parameter and the absence of failure-handling guidance keep it from being complete.
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 coverage is only 33%, and the description compensates partially by naming simulationId and resourceId as required and tracing them to simulation.create — notably the schema marks zero required parameters, so this is genuine added information. The third parameter, resourceName, is left unexplained in both schema and description, and it is unclear whether it is an alternative to resourceId.
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 specific verb+resource combination ('Requests reversible resource recovery') that is clearly distinct from siblings like simulation.inject_failure or simulation.delete. It also anchors the tool in the simulation lifecycle, though it never explains mechanically what 'recovery' does to a failed resource.
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?
Explicitly says to call simulation.step next and then simulation.metrics to inspect resource health, and names simulation.create as the source of the required IDs. It stops short of saying when NOT to call it (e.g. on a healthy resource) or what to do if recovery fails.
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.