Loafy: Sourdough Bread Baking

Bake Planner: bulk fermentation estimate

estimate_bulk_fermentation

Read-onlyIdempotent

Loafy's Bake Planner. Estimate how long the bulk fermentation of a sourdough bread dough (from mixing until shaping) takes at a given dough temperature and starter amount. Returns a range from several models with each model's figure and source: Bill Wraith's rise-time model (2007/08), the Loafy bakers (his model scaled by how long the bulk fermentations Loafy's bakers logged took) and, where the book names one, the figure from The Sourdough Framework. Every time is theoretical: the dough is done when it has grown, as the result's note says. For a whole bake planned backwards from when the bread should be ready, use plan_sourdough_bake.

Input Schema

Name	Required	Description	Default
`salt`	No	"yes" for a bread dough with about 2 % salt, "no" for a levain or the starter itself.	yes
`starter_percent`	Yes	Starter as a percentage of the flour weight: 100 g of starter on 500 g of flour is 20.
`dough_temperature_c`	Yes	The dough's temperature in °C, measured in the dough. Convert °F: 72 °F is 22 °C.
`starter_hydration_percent`	No	The starter's hydration in %: 100 for equal flour and water, 50 for a stiff one.

Output Schema

Name	Required	Description
`url`	No	The same answer, recipe or entry on loafy.ai.
`note`	No	A remark on the whole result, such as why nothing was found.
`salt`	No	Whether the dough has salt.
`tool`	No	The tool that answered.
`input`	No	The arguments as the tool used them, after any correction.
`notes`	No	What was corrected or left out, such as a value outside its range.
`range`	No	The range in words, such as "6 h 30 min to 10 h".
`models`	No	Every model that has a figure for this dough.
`to_hours`	No	The longest time any model gives: when it should be done.
`from_hours`	No	The shortest time any model gives: when to start checking the dough.
`starter_percent`	No	Starter as a share of the flour, in %.
`dough_temperature_c`	No	The dough temperature the estimate is for, in °C.
`inoculation_percent`	No	The flour already fermented, the flour in the starter, as a share of all the flour: what Bill Wraith's model counts.
`starter_hydration_percent`	No	The starter's hydration, in %.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 24, 2026

addedOutput schema / properties / models / items / properties / bakers

Added value: +{
+  "description": "The bakers behind the Loafy bakers' figure.",
+  "type": "integer"
+}

changedOutput schema / properties / models / items / properties / bakes / description

Previous value: -"The bakes behind the baker's own figure."New value: +"The bakes behind the Loafy bakers' or the baker's own figure."

changedOutput schema / properties / models / items / properties / model / description

Previous value: -"wraith, book or journal."New value: +"wraith, bakers, book or journal."

AddedOct 24, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already establish that this is a read-only, idempotent, non-destructive, closed-world calculation. The description adds useful behavioral context: the result is a range from several models, includes each model's figure and source, and the times are theoretical because dough is done when it has grown, as noted in the result.

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?

The description is front-loaded with the purpose and scope, then adds model-source and theoretical caveats. It is somewhat long but every sentence contributes to interpretation or transparency, with no obvious filler.

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?

With rich annotations, full schema descriptions, and an output schema, the remaining burden on the description is low. The description still supplies the essential caveat about theoretical times and the range-of-models return structure, making it complete for correct invocation and interpretation.

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%, so the schema already documents dough_temperature_c, starter_percent, salt, and starter_hydration_percent in detail. The description mentions dough temperature and starter amount but adds little parameter detail beyond the schema, so the high-coverage baseline of 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?

The description states a specific verb and resource: estimate bulk fermentation duration for sourdough dough from mixing until shaping, given dough temperature and starter amount. It also distinguishes itself from the sibling plan_sourdough_bake by naming that tool for whole-bake planning.

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

Usage Guidelines5/5

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

It clearly states when to use this tool and explicitly routes the whole-bake backward-planning case to plan_sourdough_bake. The scope 'from mixing until shaping' also helps prevent use for other fermentation stages.

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

All Loafy: Sourdough Bread Baking 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?