Barbaro

Calculate dough

calculate_dough

Read-onlyIdempotent

Calculate a dough formula from explicit gram sizing, percentages and published or custom flours. Returns quantities, warnings, source information and a Dough continuation link. No persistence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`dmp`	No
`oil`	No
`pff`	No
`ndmp`	No
`salt`	No
`honey`	No
`sugar`	No
`units`	Yes
`buffer`	No
`flours`	Yes
`sizing`	Yes
`prefIdy`	No	Instant dry yeast mass as a percentage of total flour, not preferment flour. Convert a Dough preferment-page percentage with pagePercent * effectiveBigaFlour / totalFlour, using actual allocated preferment flour from results. Only without an allocation shortfall is pagePercent * pff / 100 equivalent. A zero actual preferment-flour weight makes its stage percentage unavailable. Example with full allocation: 1.60 * 15 / 100 = 0.24, giving 4.8 g at 2000 g total flour.
`prefIsd`	No	Instant sourdough mass as a percentage of total flour, not preferment flour. Convert a Dough preferment-page percentage with pagePercent * effectiveBigaFlour / totalFlour, using actual allocated preferment flour from results. Only without an allocation shortfall is pagePercent * pff / 100 equivalent. A zero actual preferment-flour weight makes its stage percentage unavailable. Example with full allocation: 1.60 * 15 / 100 = 0.24, giving 4.8 g at 2000 g total flour.
`finalIdy`	No	Final-mix instant dry yeast mass as a percentage of total flour. No stage-basis conversion is required.
`finalIsd`	No	Final-mix instant sourdough mass as a percentage of total flour. No stage-basis conversion is required.
`hydration`	Yes
`ascorbicAcid`	No
`bigaHydration`	No	Preferment water as a percentage of preferment flour.
`nonfatDryMilk`	No
`starterPrefPct`	No	Preferment sourdough starter mass (including its flour and water) as a percentage of total flour, not preferment flour. Convert a Dough preferment-page percentage with pagePercent * effectiveBigaFlour / totalFlour, using actual allocated preferment flour from results. Only without an allocation shortfall is pagePercent * pff / 100 equivalent. A zero actual preferment-flour weight makes its stage percentage unavailable. Example with full allocation: 1.60 * 15 / 100 = 0.24, giving 4.8 g at 2000 g total flour.
`reserveWaterPct`	No
`starterFinalPct`	No	Final-mix sourdough starter mass (including its flour and water) as a percentage of total flour. No stage-basis conversion is required.
`customAdjustments`	No	Optional baker-named final-mix ingredients, up to 8, each a percentage of total flour. They count by weight only: they add to batch weight and ball sizing, never to hydration or flour absorption. Row IDs are c followed by five lowercase letters or digits, unique within the formula. Names are sent trimmed, 1 to 40 characters, unique ignoring case, and may not repeat one of Dough's own ingredient names such as Water, Salt, Oil or Sugar, or contain control, hidden or bidirectional characters or a web address. Any refused row fails the whole request.
`starterFlourSource`	No	blend or a supplied flour row ID. Inactive starter normalizes to blend and 100% hydration.	blend
`starterHydrationPct`	No	Starter water as a percentage of starter flour, not total flour or starter mass.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 1, 2026

changedInput schema / description

Previous value: -"Percentages refer to total flour, except bigaHydration and starterHydrationPct. Flour rows are ratios, including empty/zero blends. Unique row IDs required. Named starter source must be a supplied row. Preferment leavening requires positive pff. No temperature inputs; preparation fixes DDT at 72 F and friction at 15 F. Buffer defaults off and non-off buffer requires balls sizing. Flour mode has no ball target: prepared ballCount/ballWeight are zero, ballsTotal is zero, bufferG is the whole batch and pizzaSize is unavailable. The 100000 g flour bound applies to direct flour inputs, not the balls solver result."New value: +"Percentages refer to total flour, except bigaHydration and starterHydrationPct. Flour rows are ratios, including empty/zero blends. Unique row IDs required. Named starter source must be a supplied row. Preferment leavening requires positive pff. No temperature inputs; preparation fixes DDT at 72 F and friction at 15 F. Buffer defaults off and non-off buffer requires balls sizing. Flour mode has no ball target: prepared ballCount/ballWeight are zero, ballsTotal is zero, bufferG is the whole batch and pizzaSize is unavailable. The 100000 g flour bound applies to direct flour inputs, not the balls solver result. Custom ingredients count by weight only and never in hydration."

addedInput schema / properties / customAdjustments

Added value: +{
+  "description": "Optional baker-named final-mix ingredients, up to 8, each a percentage of total flour. They count by weight only: they add to batch weight and ball sizing, never to hydration or flour absorption. Row IDs are c followed by five lowercase letters or digits, unique within the formula. Names are sent trimmed, 1 to 40 characters, unique ignoring case, and may not repeat one of Dough's own ingredient names such as Water, Salt, Oil or Sugar, or contain control, hidden or bidirectional characters or a web address. Any refused row fails the whole request.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "id": {
+        "maxLength": 6,
+        "minLength": 1,
+        "pattern": "^c[0-9a-z]{5}$",
+        "type": "string"
+      },
+      "name": {
+        "maxLength": 40,
+        "minLength": 1,
+        "pattern": "^\\S(?:[\\s\\S]*\\S)?$",
+        "type": "string"
+      },
+      "pct": {
+        "maximum": 100,
+        "minimum": 0,
+        "type": "number"
+      }
+    },
+    "required": [
+      "id",
+      "name",
+      "pct"
+    ],
+    "type": "object"
+  },
+  "maxItems": 8,
+  "type": "array"
+}

Changed1 schema field changedSep 22, 2026
- addedInput schema / properties / units / type
```
Added value: +"string"
```
First observedSep 22, 2026

TDQS

A3.6/5.0

Behavior4/5

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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint false, and closed-world behavior. The description adds useful return-content information (quantities, warnings, source information, a Dough continuation link) and states 'No persistence,' which goes beyond the structured fields. No contradiction.

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?

Three tight sentences, front-loaded with the core action, followed by return information and a persistence note. Every sentence earns its place and there is no filler.

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?

Given a 25-parameter tool with no output schema, the description gives a brief return summary but omits key behavioral constraints such as fixed temperature assumptions, buffer requirements, and flour-mode ball-target behavior. Those details appear only in the schema description, making the tool description minimally adequate but not rich.

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?

The description only broadly gestures at 'gram sizing, percentages and published or custom flours.' With 25 parameters and only 40% schema description coverage, it fails to compensate for undocumented parameters like dmp, pff, buffer, oil, salt, and many others. The schema carries the burden, but the description adds almost no parameter meaning.

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 description uses a specific verb ('Calculate') and resource ('dough formula'), and names the input basis (explicit gram sizing, percentages, published or custom flours). This clearly identifies the domain apart from siblings like calculate_balance, get_flour, or plan_bake.

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?

No when-to-use or when-not-to-use guidance is provided, and no alternatives or prerequisites are mentioned. The agent must infer usage solely from the capability statement, with no routing help among the many sibling tools.

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

All Barbaro 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?