Skip to main content
Glama

capacity_plan

Read-onlyIdempotent

Calculate partial capacity scenarios from requests per second without inventing missing duration or payload, labeling caller-reported provenance; results are not service sizing guarantees.

Instructions

Calculate partial capacity scenarios without inventing missing duration or payload. Label caller-reported provenance; no service sizing guarantee.

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": {
      "requestsPerSecond": "<requestsPerSecond>"
    },
    "name": "capacity_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
headroomNo
rateTypeNounspecified
payloadKBNo
durationMsNo
inputProvenanceNo
requestsPerSecondYes

Output Schema

NameRequiredDescriptionDefault
kindNo
statusNo
sourcesNo
formulasNo
rateTypeNo
validatedNo
limitationNo
provenanceNo
assumptionsNo
limitationsNo
dailyRequestsNo
dailyPayloadGBNo
averageConcurrencyNo
insufficientInputsNo
plannedConcurrencyNo
provenanceLimitationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed13 schema fields changedv0.5.0
    • removedInput schema / properties / headroom / default
      Removed value: -1.3
    • addedInput schema / properties / inputProvenance
      Added value: +{
      +  "additionalProperties": false,
      +  "default": {},
      +  "properties": {
      +    "durationMs": {
      +      "enum": [
      +        "provided",
      +        "assumed",
      +        "measured"
      +      ],
      +      "type": "string"
      +    },
      +    "headroom": {
      +      "enum": [
      +        "provided",
      +        "assumed",
      +        "measured"
      +      ],
      +      "type": "string"
      +    },
      +    "payloadKB": {
      +      "enum": [
      +        "provided",
      +        "assumed",
      +        "measured"
      +      ],
      +      "type": "string"
      +    },
      +    "requestsPerSecond": {
      +      "enum": [
      +        "provided",
      +        "assumed",
      +        "measured"
      +      ],
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / rateType
      Added value: +{
      +  "default": "unspecified",
      +  "enum": [
      +    "peak",
      +    "sustained",
      +    "unspecified"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "requestsPerSecond",
      -  "durationMs",
      -  "payloadKB",
      -  "headroom"
      -]New value: +[
      +  "requestsPerSecond"
      +]
    • addedOutput schema / properties / formulas
      Added value: +{
      +  "type": "array"
      +}
    • addedOutput schema / properties / insufficientInputs
      Added value: +{
      +  "type": "array"
      +}
    • addedOutput schema / properties / limitation
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / provenance
      Added value: +{
      +  "additionalProperties": true,
      +  "properties": {
      +    "durationMs": {
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "headroom": {
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "payloadKB": {
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "requestsPerSecond": {
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    }
      +  },
      +  "type": "object"
      +}
    • addedOutput schema / properties / provenanceLimitation
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / rateType
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / sources
      Added value: +{
      +  "type": "array"
      +}
    • addedOutput schema / properties / status
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / validated
      Added value: +{
      +  "type": [
      +    "boolean",
      +    "null"
      +  ]
      +}
  2. First observedv0.4.1

TDQS

C2.7/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: it will not fabricate absent duration/payload inputs, it labels caller-reported provenance, and it explicitly disclaims a service sizing guarantee. That is real added context, though it stops short of explaining edge behavior when inputs are entirely absent.

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

Conciseness4/5

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

Two short sentences with no filler, and the computational constraint (no invented inputs) is front-loaded before the disclaimer. The trade-off is that terseness comes at the cost of clarity for terms like "partial capacity scenarios", which are never unpacked.

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

Completeness2/5

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, and the description does convey the tool's epistemic stance about missing inputs. But for a six-parameter tool with zero schema coverage and a nested provenance object, the description leaves too much undefined for an agent to invoke it confidently, especially around rateType and headroom.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across six parameters including a required requestsPerSecond, an enum rateType with a default of "unspecified", a bounded headroom, and a nested inputProvenance object. The description only alludes to duration and payload being optional; it never explains headroom, rateType semantics, or how the provenance sub-object should be populated, so it does not compensate for the documentation gap.

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?

It names a verb and resource ("Calculate partial capacity scenarios"), but "partial capacity scenarios" is not defined, and the description never distinguishes this from siblings like queue_sizing, storage_growth, or latency_budget that also perform sizing math. An agent can tell it is a computation tool but not precisely what it computes or returns.

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

Usage Guidelines2/5

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

The phrase "without inventing missing duration or payload" implies the tool is intended for cases where inputs are incomplete, but this is never stated as an explicit trigger condition and no alternative tool is named. There is no when-not-to-use guidance despite several adjacent sizing/planning siblings.

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