Skip to main content
Glama

Quantum Expectations

Compare Hardware Scenarios

compare_hardware_scenarios
Read-onlyIdempotent

Run the same circuit against several current state-of-the-art hardware entries in one call and return one result block per entry, computed at that entry's error rate and connectivity class (the result blocks carry no minimum runtime and take no connectivity override). Defaults to every entry in list_current_quantum_computers when hardwareIds is omitted. Answers "which platform runs this circuit best?".

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": {
      "numQubits": "<numQubits>",
      "compDepth": "<compDepth>"
    },
    "name": "compare_hardware_scenarios"
  }
}

Input Schema

NameRequiredDescriptionDefault
compDepthYes
numQubitsYes
hardwareIdsNoSubset of the ids in list_current_quantum_computers to compare, at most 50; a repeated id is compared once. Omit to compare every entry.
useErrorCorrectionNo
distanceSurfaceCodeNoSurface code distance: odd integer in [3, 31]. Required when useErrorCorrection=true and the surface code is selected; ignored when a qLDPC code is selected.
errorCorrectionCodeNoEither "surface" (default when useErrorCorrection=true) or a qLDPC code id. "surface-code" is accepted as an alias for "surface".

Output Schema

NameRequiredDescriptionDefault
resultsYes
scenarioYes
unresolvedHardwareIdsYesRequested hardwareIds that match no current-hardware entry.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / hardwareIds / description
      Previous value: -"Subset of the ids in list_current_quantum_computers to compare. Omit to compare every entry."New value: +"Subset of the ids in list_current_quantum_computers to compare, at most 50; a repeated id is compared once. Omit to compare every entry."
    • addedInput schema / properties / hardwareIds / maxItems
      Added value: +50
  2. Changed1 schema field changed
    • addedOutput schema / properties / results / items / properties / result / properties / qldpcInstructionComparison
      Added value: +{
      +  "additionalProperties": {},
      +  "description": "qLDPC codes with published architecture data only, at the scenario p: memoryDerivedOp is one block's memory-fit error over one logical operation (roundsPerLogicalOp x per-cycle rate; logicalErrorRatePerGate is this x blocks / numQubits); inModuleMeasurement and interModuleMeasurement are the architecture's published rates for one in-module measurement and one measurement joining two neighbouring blocks (per block pair). Published rates are fitted, extrapolated or assumed per point (list_qldpc_codes, architecture.errorPoints[].basis; assumedRates). The fields are reported side by side; no direction between them is implied.",
      +  "properties": {
      +    "assumedRates": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "inModuleMeasurement": {
      +      "type": "number"
      +    },
      +    "interModuleMeasurement": {
      +      "type": "number"
      +    },
      +    "memoryDerivedOp": {
      +      "type": "number"
      +    },
      +    "withinPublishedRange": {
      +      "type": "boolean"
      +    }
      +  },
      +  "required": [
      +    "memoryDerivedOp",
      +    "inModuleMeasurement",
      +    "interModuleMeasurement",
      +    "withinPublishedRange",
      +    "assumedRates"
      +  ],
      +  "type": "object"
      +}
  3. Changed1 schema field changed
    • changedInput schema / properties / hardwareIds / description
      Previous value: -"Subset of QUANTUM_COMPUTERS ids to compare. Omit to compare every entry."New value: +"Subset of the ids in list_current_quantum_computers to compare. Omit to compare every entry."
  4. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "https://json-schema.org/draft/2020-12/schema",
      +  "additionalProperties": {},
      +  "properties": {
      +    "results": {
      +      "items": {
      +        "additionalProperties": {},
      +        "properties": {
      +          "hardware": {
      +            "additionalProperties": {},
      +            "properties": {
      +              "connectivity": {
      +                "enum": [
      +                  "all-to-all",
      +                  "reconfigurable",
      +                  "2d-lattice"
      +                ],
      +                "type": "string"
      +              },
      +              "errorRate": {
      +                "type": "number"
      +              },
      +              "errorRateDisplay": {
      +                "type": "string"
      +              },
      +              "hardwareType": {
      +                "type": "string"
      +              },
      +              "id": {
      +                "type": "string"
      +              },
      +              "physicalQubits": {
      +                "maximum": 9007199254740991,
      +                "minimum": -9007199254740991,
      +                "type": "integer"
      +              }
      +            },
      +            "required": [
      +              "id",
      +              "hardwareType",
      +              "physicalQubits",
      +              "errorRate",
      +              "errorRateDisplay",
      +              "connectivity"
      +            ],
      +            "type": "object"
      +          },
      +          "qubitErrorRateUsed": {
      +            "type": "number"
      +          },
      +          "result": {
      +            "additionalProperties": {},
      +            "properties": {
      +              "effectiveErrorRate": {
      +                "description": "Probability that at least one gate fails over the (routed) circuit.",
      +                "type": "number"
      +              },
      +              "logicalErrorRatePerCycle": {
      +                "description": "Per-syndrome-cycle logical error rate as the calibration source reports it; null without error correction.",
      +                "type": [
      +                  "number",
      +                  "null"
      +                ]
      +              },
      +              "logicalErrorRatePerGate": {
      +                "description": "Per-logical-qubit, per-logical-operation error rate; null without error correction.",
      +                "type": [
      +                  "number",
      +                  "null"
      +                ]
      +              },
      +              "minimumClockRuntimeSeconds": {
      +                "description": "Lower bound on wall-clock runtime; present only when hardwareId was supplied.",
      +                "type": "number"
      +              },
      +              "physicalQubitsPerLogicalQubit": {
      +                "type": [
      +                  "number",
      +                  "null"
      +                ]
      +              },
      +              "routedDepth": {
      +                "description": "compDepth after routing: the depth the effective-error formula consumed.",
      +                "type": "number"
      +              },
      +              "routingOverheadFactor": {
      +                "description": "Multiplier the connectivity class applied to compDepth (1 for all-to-all and reconfigurable).",
      +                "type": "number"
      +              },
      +              "successProbability": {
      +                "description": "1 - effectiveErrorRate.",
      +                "type": "number"
      +              },
      +              "totalPhysicalQubits": {
      +                "type": [
      +                  "number",
      +                  "null"
      +                ]
      +              }
      +            },
      +            "required": [
      +              "effectiveErrorRate",
      +              "successProbability",
      +              "routingOverheadFactor",
      +              "routedDepth",
      +              "logicalErrorRatePerGate",
      +              "logicalErrorRatePerCycle",
      +              "physicalQubitsPerLogicalQubit",
      +              "totalPhysicalQubits"
      +            ],
      +            "type": "object"
      +          }
      +        },
      +        "required": [
      +          "hardware",
      +          "qubitErrorRateUsed",
      +          "result"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "scenario": {
      +      "additionalProperties": {},
      +      "properties": {
      +        "compDepth": {
      +          "type": "number"
      +        },
      +        "distanceSurfaceCode": {
      +          "type": [
      +            "number",
      +            "null"
      +          ]
      +        },
      +        "errorCorrectionCode": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "numQubits": {
      +          "type": "number"
      +        },
      +        "useErrorCorrection": {
      +          "type": "boolean"
      +        }
      +      },
      +      "required": [
      +        "numQubits",
      +        "compDepth",
      +        "useErrorCorrection",
      +        "distanceSurfaceCode",
      +        "errorCorrectionCode"
      +      ],
      +      "type": "object"
      +    },
      +    "unresolvedHardwareIds": {
      +      "description": "Requested hardwareIds that match no current-hardware entry.",
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "scenario",
      +    "results",
      +    "unresolvedHardwareIds"
      +  ],
      +  "type": "object"
      +}
  5. Changed1 schema field changed
    • changedInput schema / properties / errorCorrectionCode / enum
      Previous value: -[
      -  "surface",
      -  "bb-144-12-12",
      -  "surface-code"
      -]New value: +[
      +  "surface",
      +  "bb-144-12-12",
      +  "bb-288-12-18",
      +  "surface-code"
      +]
  6. Changed4 schema fields changed
    • changedInput schema / properties / distanceSurfaceCode / description
      Previous value: -"Required when useErrorCorrection=true and errorCorrectionCode=\"surface\" (odd integer)."New value: +"Surface code distance: odd integer in [3, 31]. Required when useErrorCorrection=true and the surface code is selected; ignored when a qLDPC code is selected."
    • removedInput schema / properties / distanceSurfaceCode / maximum
      Removed value: -31
    • removedInput schema / properties / distanceSurfaceCode / minimum
      Removed value: -3
    • changedInput schema / properties / distanceSurfaceCode / type
      Previous value: -"integer"New value: +"number"
  7. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  8. Changed2 schema fields changed
    • changedInput schema / properties / errorCorrectionCode / description
      Previous value: -"Either \"surface\" (default when useErrorCorrection=true) or a qLDPC code id."New value: +"Either \"surface\" (default when useErrorCorrection=true) or a qLDPC code id. \"surface-code\" is accepted as an alias for \"surface\"."
    • changedInput schema / properties / errorCorrectionCode / enum
      Previous value: -[
      -  "surface",
      -  "bb-144-12-12"
      -]New value: +[
      +  "surface",
      +  "bb-144-12-12",
      +  "surface-code"
      +]
  9. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add computation-specific behavior — and it does: each block is computed at that entry's own error rate and connectivity class, and result blocks carry no minimum runtime and accept no connectivity override. That parenthetical is exactly the kind of non-obvious constraint an agent would otherwise get wrong. It does not, however, disclose anything about cost, latency, or behavior when error correction is enabled.

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?

Front-loaded with the core action and output shape, then defaults, then the motivating question. The parenthetical about minimum runtime and connectivity override is dense but earns its place; the trailing quoted question is slightly decorative but cheap.

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 formatting needn't be explained, and the default-set behavior is covered. But for a six-parameter tool whose distinctiveness hinges on error correction, the description never says what changes when useErrorCorrection/distanceSurfaceCode/errorCorrectionCode are supplied, leaving a meaningful complexity gap.

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?

With schema coverage at 50%, the schema already documents hardwareIds, errorCorrectionCode, and distanceSurfaceCode; the description's added value is mainly reinforcing that omitting hardwareIds means all entries from list_current_quantum_computers. The three error-correction parameters (useErrorCorrection, distanceSurfaceCode, errorCorrectionCode) receive no mention in the description, so the interaction between enabling error correction and the comparison semantics is left unexplained.

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?

States a specific verb and resource ('run the same circuit against several current state-of-the-art hardware entries') plus the output shape ('one result block per entry'), and distinguishes itself from the single-target compute_* siblings by being a batch comparison. It also names the framing question ('which platform runs this circuit best?'), which makes the intent unmistakable.

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 clearly establishes when to reach for this tool (cross-hardware comparison) and documents the default path when hardwareIds is omitted, referencing list_current_quantum_computers as the source set. It stops short of any explicit when-not guidance, e.g. that a single-platform run should use a compute_* sibling instead.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources