Quantum Expectations

Fit Historic Series (log-linear)

fit_historic_series

Read-onlyIdempotent

Fit a log-linear trend (ln(value) = slope * year + intercept) to one historic series — fidelity or qubit-count — for one hardware type. Atomic primitive: compose with list_current_quantum_computers, compute_required_error_rate, or your own modelling to answer "when might hardware reach X?". residualStdDev is the BIASED (maximum-likelihood) RMS — divides by n, not (n - 2); on small series (n ≈ 3–5) inflate by √(n / (n - 2)) before building confidence intervals.

Input Schema

Name	Required	Description
`seriesType`	Yes	Which historic series to fit: "fidelity" (2-qubit gate error rate) or "qubit-count" (physical qubits).
`targetValue`	No	Optional. When supplied, the response includes yearAtTargetValue — the extrapolated year the fit crosses this value (error rate for fidelity series, qubit count for qubit-count series). Null if slope is flat.
`hardwareType`	Yes	Hardware platform as used by get_historic_series.

Output Schema

Name	Required	Description
`model`	Yes
`slope`	Yes
`formula`	Yes
`nPoints`	Yes
`intercept`	Yes
`yearRange`	Yes
`seriesType`	Yes
`hardwareType`	Yes
`residualStdDev`	Yes	Biased (divide-by-n) RMS of the ln residuals.
`yearAtTargetValue`	No	Present only when targetValue was supplied.
`halvingPeriodYears`	Yes	Non-null iff slope < 0.
`doublingPeriodYears`	Yes	Non-null iff slope > 0.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 23, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "properties": {
+    "doublingPeriodYears": {
+      "description": "Non-null iff slope > 0.",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "formula": {
+      "const": "ln(value) = slope * year + intercept",
+      "type": "string"
+    },
+    "halvingPeriodYears": {
+      "description": "Non-null iff slope < 0.",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "hardwareType": {
+      "type": "string"
+    },
+    "intercept": {
+      "type": "number"
+    },
+    "model": {
+      "const": "log-linear",
+      "type": "string"
+    },
+    "nPoints": {
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "residualStdDev": {
+      "description": "Biased (divide-by-n) RMS of the ln residuals.",
+      "type": "number"
+    },
+    "seriesType": {
+      "enum": [
+        "fidelity",
+        "qubit-count"
+      ],
+      "type": "string"
+    },
+    "slope": {
+      "type": "number"
+    },
+    "yearAtTargetValue": {
+      "description": "Present only when targetValue was supplied.",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "yearRange": {
+      "items": false,
+      "maxItems": 2,
+      "minItems": 2,
+      "prefixItems": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "number"
+        }
+      ],
+      "type": "array"
+    }
+  },
+  "required": [
+    "seriesType",
+    "hardwareType",
+    "model",
+    "formula",
+    "slope",
+    "intercept",
+    "nPoints",
+    "residualStdDev",
+    "yearRange",
+    "halvingPeriodYears",
+    "doublingPeriodYears"
+  ],
+  "type": "object"
+}

Changed1 schema field changedAug 20, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

First observedJul 2, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the readOnly/idempotent annotations with a substantive statistical caveat: residualStdDev is biased (divides by n, not n-2) and should be inflated by √(n/(n-2)) on small series before building confidence intervals. This is exactly the kind of usage-affecting behavior an agent cannot infer from structured fields.

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-loads the model definition and scope in the first sentence, then the residualStdDev caveat. Dense but every clause carries information; only minor cost is the second sentence's parenthetical density.

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

Completeness5/5

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

Output schema exists, so return values like yearAtTargetValue needn't be explained, yet the description still adds the crucial biased-residual note that the schema likely omits. For a read-only fit primitive, nothing an agent needs to call or interpret it correctly is missing.

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%, so seriesType, hardwareType, and targetValue are already fully documented in the schema. The description restates the two series types but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 with the exact model form (ln(value) = slope * year + intercept) and the two series it covers. An agent can immediately tell this is a curve-fit primitive for one historic series, distinct from siblings like get_historic_series (raw data) or compute_required_error_rate.

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?

Explicitly frames the tool as an 'atomic primitive' and names composition partners (list_current_quantum_computers, compute_required_error_rate) plus the motivating question ('when might hardware reach X?'). It does not explicitly say when NOT to use it or contrast directly with get_historic_series as the data source, but the usage context is clear.

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

All Quantum Expectations tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?