healthFree. Returns AMR service status, provider health and cache metrics.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | ||
| version | Yes | ||
| providers | Yes | ||
| timestamp | No | ||
| cache_hits | Yes | ||
| error_rate | Yes | ||
| environment | Yes | ||
| error_count | Yes | ||
| cache_misses | Yes | ||
| redis_backend | Yes | ||
| request_count | Yes | ||
| cache_hit_rate | Yes | ||
| uptime_seconds | Yes | ||
| redis_connected | Yes |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "description": "Response for ``GET /health``.",
+ "properties": {
+ "cache_hit_rate": {
+ "title": "Cache Hit Rate",
+ "type": "number"
+ },
+ "cache_hits": {
+ "title": "Cache Hits",
+ "type": "integer"
+ },
+ "cache_misses": {
+ "title": "Cache Misses",
+ "type": "integer"
+ },
+ "environment": {
+ "title": "Environment",
+ "type": "string"
+ },
+ "error_count": {
+ "title": "Error Count",
+ "type": "integer"
+ },
+ "error_rate": {
+ "title": "Error Rate",
+ "type": "number"
+ },
+ "providers": {
+ "items": {
+ "properties": {
+ "avg_latency_ms": {
+ "title": "Avg Latency Ms",
+ "type": "number"
+ },
+ "capability": {
+ "title": "Capability",
+ "type": "string"
+ },
+ "circuit_open": {
+ "title": "Circuit Open",
+ "type": "boolean"
+ },
+ "consecutive_failures": {
+ "title": "Consecutive Failures",
+ "type": "integer"
+ },
+ "healthy": {
+ "title": "Healthy",
+ "type": "boolean"
+ },
+ "name": {
+ "title": "Name",
+ "type": "string"
+ },
+ "requests": {
+ "title": "Requests",
+ "type": "integer"
+ },
+ "success_rate": {
+ "title": "Success Rate",
+ "type": "number"
+ }
+ },
+ "required": [
+ "name",
+ "capability",
+ "healthy",
+ "circuit_open",
+ "consecutive_failures",
+ "success_rate",
+ "avg_latency_ms",
+ "requests"
+ ],
+ "title": "ProviderHealth",
+ "type": "object"
+ },
+ "title": "Providers",
+ "type": "array"
+ },
+ "redis_backend": {
+ "title": "Redis Backend",
+ "type": "string"
+ },
+ "redis_connected": {
+ "title": "Redis Connected",
+ "type": "boolean"
+ },
+ "request_count": {
+ "title": "Request Count",
+ "type": "integer"
+ },
+ "status": {
+ "enum": [
+ "ok",
+ "degraded",
+ "down"
+ ],
+ "title": "Status",
+ "type": "string"
+ },
+ "timestamp": {
+ "format": "date-time",
+ "title": "Timestamp",
+ "type": "string"
+ },
+ "uptime_seconds": {
+ "title": "Uptime Seconds",
+ "type": "number"
+ },
+ "version": {
+ "title": "Version",
+ "type": "string"
+ }
+ },
+ "required": [
+ "status",
+ "version",
+ "environment",
+ "uptime_seconds",
+ "redis_connected",
+ "redis_backend",
+ "request_count",
+ "error_count",
+ "error_rate",
+ "cache_hits",
+ "cache_misses",
+ "cache_hit_rate",
+ "providers"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotation readOnlyHint=true already indicates this is a safe read operation. The description adds the 'Free' note, which is useful context about cost. It also specifies what the tool returns (service status, provider health, cache metrics), which adds behavioral context beyond the annotation. However, it doesn't disclose details like rate limits, response format specifics, or what 'health' means in terms of potential error states.
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?
The description is a single sentence that is concise and front-loaded. It states the key facts: free, returns service status, provider health, and cache metrics. Every word earns its place, and there is no fluff or repetition.
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 zero-parameter, read-only tool with an output schema, the description is fairly complete. It tells the agent what the tool does and that it's free. The output schema likely describes the return structure, so the description doesn't need to. The only minor gap is not explaining when to use this over other monitoring tools, but given the tool's simplicity, this is adequate.
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?
The tool has zero parameters, and the schema coverage is 100% (empty schema). The description doesn't need to explain parameters since there are none. The baseline for 0 params is 4, and the description appropriately doesn't add unnecessary parameter information. It does clarify the scope of what the health check covers, which is useful.
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?
The description clearly states the tool's function: it returns AMR service status, provider health, and cache metrics. The verb 'returns' and the specific resources (service status, provider health, cache metrics) make the purpose clear. It doesn't explicitly differentiate from siblings, but the name 'health' and the specific metrics make it distinguishable from the other tools.
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?
The description implies usage context: it's a free health check tool, likely to be used when checking service status or monitoring. However, it doesn't explicitly state when to use this tool versus alternatives, nor does it mention any exclusions or alternative tools. The 'Free' note is a small usage hint but not a full guideline.
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.