Utility Matrix

Compute Rightsizing Calculator

rightsizing-calculator

Read-onlyIdempotent

Use when a user asks about instance rightsizing or overprovisioned compute.

Input Schema

Name	Required	Description
`hourly_cost`	No	hourly cost used by the calculation; monetary values are in USD unless stated otherwise.
`p99_cpu_pct`	Yes	p99 cpu expressed as a percentage.
`current_vcpu`	Yes	current vcpu used by this deterministic tool.
`instance_count`	No	instance count used by this deterministic tool.
`p99_memory_pct`	Yes	p99 memory expressed as a percentage.
`current_memory_gb`	Yes	current memory in gigabytes.

Output Schema

Name	Required	Description	Default
`next_step`	Yes
`do_savings`	Yes
`needed_vcpu`	Yes
`output_tier`	Yes
`monthly_cost`	Yes
`signal_value`	Yes
`next_step_url`	Yes
`why_follow_up`	Yes
`annual_savings`	Yes
`instance_count`	Yes
`interpretation`	Yes
`savings_factor`	Yes
`needed_memory_gb`	Yes
`affiliate_context`	No
`computation_basis`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 1, 2026
- addedInput schema / properties / current_memory_gb / exclusiveMinimum
```
Added value: +0
```
- removedInput schema / properties / current_memory_gb / minimum
```
Removed value: -0
```
- addedInput schema / properties / current_vcpu / exclusiveMinimum
```
Added value: +0
```
- removedInput schema / properties / current_vcpu / minimum
```
Removed value: -0
```
Changed12 schema fields changedSep 28, 2026
- addedInput schema / properties / current_memory_gb / description
```
Added value: +"current memory in gigabytes."
```
- addedInput schema / properties / current_memory_gb / examples
```
Added value: +[
+  1
+]
```
- addedInput schema / properties / current_vcpu / description
```
Added value: +"current vcpu used by this deterministic tool."
```
- addedInput schema / properties / current_vcpu / examples
```
Added value: +[
+  1
+]
```
- addedInput schema / properties / hourly_cost / description
```
Added value: +"hourly cost used by the calculation; monetary values are in USD unless stated otherwise."
```
- addedInput schema / properties / hourly_cost / examples
```
Added value: +[
+  1
+]
```
- addedInput schema / properties / instance_count / description
```
Added value: +"instance count used by this deterministic tool."
```
- addedInput schema / properties / instance_count / examples
```
Added value: +[
+  1
+]
```
- addedInput schema / properties / p99_cpu_pct / description
```
Added value: +"p99 cpu expressed as a percentage."
```
- addedInput schema / properties / p99_cpu_pct / examples
```
Added value: +[
+  1
+]
```
- addedInput schema / properties / p99_memory_pct / description
```
Added value: +"p99 memory expressed as a percentage."
```
- addedInput schema / properties / p99_memory_pct / examples
```
Added value: +[
+  1
+]
```

Changed1 schema field changedJul 15, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "affiliate_context": {
+      "additionalProperties": false,
+      "properties": {
+        "affiliate": {
+          "type": "string"
+        },
+        "cta_label": {
+          "type": "string"
+        },
+        "disclosure": {
+          "type": "string"
+        },
+        "framing": {
+          "type": "string"
+        },
+        "posture": {
+          "enum": [
+            "secondary"
+          ],
+          "type": "string"
+        },
+        "slot_id": {
+          "type": "string"
+        },
+        "url": {
+          "type": "string"
+        },
+        "variant": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "affiliate",
+        "cta_label",
+        "disclosure",
+        "framing",
+        "posture",
+        "slot_id",
+        "url",
+        "variant"
+      ],
+      "type": "object"
+    },
+    "annual_savings": {
+      "type": "number"
+    },
+    "computation_basis": {
+      "type": "string"
+    },
+    "do_savings": {
+      "type": "number"
+    },
+    "instance_count": {
+      "type": "number"
+    },
+    "interpretation": {
+      "type": "string"
+    },
+    "monthly_cost": {
+      "type": "number"
+    },
+    "needed_memory_gb": {
+      "type": "number"
+    },
+    "needed_vcpu": {
+      "type": "number"
+    },
+    "next_step": {
+      "type": "string"
+    },
+    "next_step_url": {
+      "type": "string"
+    },
+    "output_tier": {
+      "type": "string"
+    },
+    "savings_factor": {
+      "type": "number"
+    },
+    "signal_value": {
+      "type": "number"
+    },
+    "why_follow_up": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "annual_savings",
+    "computation_basis",
+    "do_savings",
+    "instance_count",
+    "interpretation",
+    "monthly_cost",
+    "needed_memory_gb",
+    "needed_vcpu",
+    "next_step",
+    "next_step_url",
+    "output_tier",
+    "savings_factor",
+    "signal_value",
+    "why_follow_up"
+  ],
+  "type": "object"
+}

Changed1 schema field changedJul 13, 2026
- addedInput schema / additionalProperties
```
Added value: +false
```
First observedJun 29, 2026

TDQS

B3/5.0

Behavior2/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds nothing behavioral beyond that — no note that the calculation is deterministic, no required-input prerequisites, no unit or cost caveats. With the low bar set by annotations it still fails to contribute any additional context.

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

Conciseness3/5

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

A single sentence with no filler and the trigger front-loaded, so there is no waste. However, at this length the brevity reads as under-specification rather than tightness — the one sentence does not carry the load a 6-parameter calculator requires.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained. But for a deterministic 4-required-parameter calculator the description omits what inputs are mandatory in practice, what units/assumptions drive the result, and how it differs from cost-oriented siblings. Adequate to recognize the tool, thin for calling it correctly with confidence.

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 description coverage is 100% across all six parameters, so the baseline is 3. The description mentions no parameter at all — not the required p99 inputs, not the units of hourly_cost, not instance_count — so it adds no meaning beyond the schema. Note the schema text itself is largely templated ('used by this deterministic tool'), but the description does nothing to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the domain ('instance rightsizing', 'overprovisioned compute') but never states what the tool actually does — compute recommended vCPU/memory from p99 utilization inputs — or what it returns. It is framed entirely as a usage trigger rather than a verb+resource statement. It loosely separates from siblings like ec2-cost-calculator, but not from cloud-waste-calculator, which plausibly covers the same overprovisioning territory.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a concrete trigger condition ('when a user asks about instance rightsizing or overprovisioned compute'), which is exactly the context an agent needs to route here. It stops short of naming when NOT to use it or pointing to overlapping siblings such as cloud-waste-calculator or cluster-capacity-calculator, so it is clear context without exclusions.

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

All Utility Matrix tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?