Skip to main content
Glama
MCP-OpenStack-Ops

MCP-OpenStack-Ops

by call518

Get Gnocchi Aggregates

get_gnocchi_aggregates

Aggregate telemetry across current-project resources to compute project-wide averages, totals, top-N rankings, grouped metrics, or metric ratios.

Instructions

Aggregate measured telemetry across many current-project resources.

Use for cross-resource questions: project-wide averages or totals, top N resources, per-flavor or per-host groups, and ratios between metrics. For one resource's time series, use get_gnocchi_measures instead. For allocations, capacity, or quotas, use get_resource_monitoring.

Choose ONE mode:

  1. Simple mode (preferred): set metric and aggregation, plus optional reaggregation, groupby, and top. Leave operations empty.

    • Project-wide average CPU: metric="cpu", aggregation="rate:mean", reaggregation="mean"

    • Top 5 instances by CPU: metric="cpu", aggregation="rate:mean", top=5

    • Mean memory use per flavor: metric="memory.usage", reaggregation="mean", groupby="flavor_name"

  2. Expression mode: set operations only, for arithmetic between metrics or advanced Gnocchi functions. Leave metric and reaggregation empty. Write metric NAMES, never metric UUIDs, as (metric NAME AGGREGATION). Example ratio: (/ (metric memory.usage mean) (metric memory mean)) Arithmetic returns points only where every operand has data; memory (flavor size) is recorded sparsely, so this ratio has fewer points.

Units: cpu with rate:mean is CPU nanoseconds per granularity window; utilization fraction = value / (granularity * 1e9 * vCPUs). memory.usage is MB in use. vcpus and memory are flavor sizes, not usage.

Results are always limited to resources of the current project. The response echoes the executed operations expression.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_gnocchi_aggregates"
  }
}

Input Schema

NameRequiredDescriptionDefault
topNoReturn only the N series with the highest latest value (0 = all)
fillNoValue for missing points when combining series: a number, "null", or "dropna"
stopNoExclusive ISO 8601 stop time
limitNoMaximum latest rows per series (1-1000, default 20)
startNoInclusive ISO 8601 start time
metricNoMetric name for simple mode, such as cpu or memory.usage
filtersNoJSON object of attribute equality filters, for example {"flavor_name": "m1.small"}
groupbyNoComma-separated resource attributes, such as flavor_name or host; one result group per value
operationsNoExpression mode only; a Gnocchi operations expression
aggregationNoAggregation from the metric archive policy, such as mean or rate:mean (use rate:mean for cumulative cpu)mean
granularityNoGranularity in seconds from the archive policy
reaggregationNoCombine all matched resources into one series with mean, sum, min, max, or median. Empty keeps one series per resource
resource_typeNoGnocchi resource type to search (default instance)instance
needed_overlapNoPercent of aligned points required across series (Gnocchi default 100); lower it or set fill for uneven data

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.8.3

TDQS

A4.2/5.0
Behavior3/5

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

No annotations exist, so the description carries the behavioral load, and it does disclose real traits: results are always scoped to the current project, the response echoes the executed operations expression, and arithmetic produces fewer points because flavor memory is sparsely recorded. It also explains unit semantics (CPU nanoseconds per window, utilization formula, MB for memory.usage). It stops short of stating read-only status, permission requirements, or performance/cost characteristics of wide aggregation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then routing, then the two-mode decision tree with concrete examples, then unit caveats. Every block is functional: the mode rules and unit notes prevent concrete invocation errors on a 14-parameter tool, so the length is earned rather than padding.

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?

For a 14-parameter tool with no annotations it covers the make-or-break aspects: which parameters are mutually exclusive per mode, expression syntax, unit interpretation, and the sparse-data pitfall. Return values need not be described since an output schema exists. Remaining gaps are secondary (time range, limit/default row behavior, filters usage), all of which the schema documents.

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 100%, and the schema already describes each of the 14 parameters individually, so the baseline is 3. The description adds genuine mode-level semantics (metric+aggregation vs operations are mutually exclusive, reaggregation is what collapses many resources into one series, metric names never UUIDs in expressions), which is value beyond the schema, but it never covers start/stop/limit/filters/granularity behavior, so it doesn't fully supersede it.

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?

The opening sentence states a concrete verb and resource ('Aggregate measured telemetry') and a scope ('across many current-project resources'), which is precisely what separates it from the per-resource measures tool. It then explicitly names what it is not for, so an agent can route correctly without opening any schema.

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?

It gives explicit when-to-use cases (project-wide averages, top N, per-flavor/per-host groups, ratios), names two alternatives with the condition that selects each (get_gnocchi_measures for one resource's time series, get_resource_monitoring for allocations/capacity/quotas), and then decomposes usage into two mutually exclusive modes with worked examples.

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