Simba MCP Server

Official

by getsimba-ai

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

Publish Recipe Draft

publish_recipe_draft

Idempotent

Publish a saved MMM or VAR draft as immutable recipe revisions, either as new brand recipes or as a new revision of an existing recipe. Replays return identical revisions.

Instructions

Publish a saved MMM or VAR draft as immutable recipe revisions. Supply a new UUID publication_id and reuse it with identical arguments after an uncertain response; a replay returns the same revisions. Without target: new recipes, one per prepared brand, atomic. With target={recipe_id, expected_version}: revision N+1 of that recipe under its row lock, the draft's base revision recorded as the source. 412 stale_version when the recipe moved since expected_version: the draft and every edit are kept, so re-read the recipe and publish again on top, or drop target to branch into a new recipe. 409 target_requires_single_recipe for a multi-brand draft; 409 when the draft's own target names a different recipe; 404 for a recipe outside the study. Backend compiles the saved snapshot with shared wizard rules; never send separately prepared settings. Does not fit, consume an attempt or designate a champion. MMM priors the draft leaves unset are filled with smart defaults at publication (the Prior Builder's own calculation over the whole source) and frozen; replay does not rebuild them. VAR requires family-specific evidence assessment; MMM policies cannot establish VAR acceptance. Enabled invalid MMM calibration fails publication; VAR calibration is unsupported. Preserve disabled authoring observations.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`reason`	Yes
`target`	No
`draft_id`	Yes
`publication_id`	Yes
`expected_version`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.8.2Sep 27, 2026

addedInput schema / properties / target

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "description": "Publish into an existing recipe as its next revision (jellyfish #881). expected_version is the recipe version you last read; 412 stale_version when it moved, with the draft and every edit kept.",
+      "properties": {
+        "expected_version": {
+          "minimum": 1,
+          "type": "integer"
+        },
+        "recipe_id": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "recipe_id",
+        "expected_version"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Target"
+}

Addedv0.5.0Sep 20, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations cover the safety profile (idempotentHint=true, openWorldHint=true, destructiveHint=false), and the description goes well beyond them: it explains the publication_id replay contract, atomic per-brand creation, row-lock semantics, the 412/409/404 error taxonomy, and what survives a failed publish (draft and edits kept). It also discloses non-obvious side effects like unset MMM priors being filled and frozen, which the annotations cannot convey.

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 core action and idempotency contract are front-loaded, and nearly every sentence carries operational weight (error codes, defaults, MMM/VAR distinctions). The prose is very dense and the mid-section error/rules sentences run long, which slightly hurts scannability, but little is pure 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?

An output schema exists, so return values need no explanation, and the description still supplies the failure modes, atomicity guarantee, idempotency/replay behavior, and MMM vs VAR constraints an agent needs to call this safely. Given the tool's complexity, nothing essential is missing.

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

Parameters4/5

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

With schema description coverage at 0% for the top-level params, the description must compensate, and it does for the important ones: publication_id (new UUID, reuse on uncertain responses), target (recipe_id + expected_version, 412 semantics), and the interaction with expected_version. It leaves reason and draft_id uninterpreted, so the coverage is strong but not total.

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 opening sentence names a specific verb (Publish), resource (saved MMM or VAR draft), and result (immutable recipe revisions), which cleanly separates it from siblings like create_recipe_draft, update_recipe_draft, and revise_study_recipe. The two-mode framing (new recipe vs. next revision) further sharpens what the tool concretely does.

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 prescribes the two operating modes: omit target for new recipes (one per prepared brand), or pass target={recipe_id, expected_version} to publish revision N+1, and explicitly tells the agent to 'drop target to branch into a new recipe' on a 412. It does not name sibling alternatives for the create-vs-revise decision, so it stops short of the explicit when-not/alternative routing that earns a 5.

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

Deploy Server