latency_budget
Split an end-to-end latency target across service hops and flag any hop exceeding its allocated share, based on caller-supplied estimates.
Instructions
Split an end-to-end latency objective across hops and show which hops exceed their share. Pure arithmetic over caller-supplied estimates.
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": {
"targetMs": "<targetMs>",
"hops": "<hops>"
},
"name": "latency_budget"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| hops | Yes | ||
| targetMs | Yes | ||
| percentile | No | p95 |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| hops | No | ||
| kind | No | ||
| sources | No | ||
| targetMs | No | ||
| validated | No | ||
| limitation | No | ||
| percentile | No | ||
| limitations | No | ||
| remainingMs | No | ||
| suggestions | No | ||
| withinBudget | No | ||
| parallelGroups | No | ||
| estimatedTotalMs | No | ||
| utilizationPercent | No |