Skip to main content
Glama
getsimba-ai

Simba MCP Server

Official
by getsimba-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Update Recipe Draft

update_recipe_draft
DestructiveIdempotent

Save draft recipe edits by replacing the stored authoring state with a version-checked snapshot; stale changes are rejected, so reload before retrying.

Instructions

Replace authoring state using the version from get_recipe_draft. Retain every unedited field, including original priors and source bytes. Stale changes fail; reload and reconcile explicitly. Identical retries return the current draft. Does not publish or launch.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYes
draft_idYes
snapshotYesLossless editor authoring state. Backend is authoritative; preserve unknown nested fields. Source bytes are copied into encrypted draft storage (10 MB source limit); metadata limit is 5 MB. No local filesystem paths or executable code.
expected_versionYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.12.0
    • addedInput schema / properties / snapshot / properties / incrementality_tests
      Added value: +{
+  "description": "Optional recorded incrementality tests by reference ({test_id, version?, channel?, confirm_kpi?}); each is derived against every prepared brand's own data when the draft is published, and the revision records which test versions it used. A test that can't calibrate a brand fails publication with its reason.",
+  "items": {
+    "type": "object"
+  },
+  "maxItems": 50,
+  "type": "array"
+}
  2. Addedv0.5.0

TDQS

A4/5.0
Behavior4/5

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

The description adds real semantics beyond the annotations: merge/retention rules ("Retain every unedited field, including original priors and source bytes"), optimistic-concurrency failure ("Stale changes fail; reload and reconcile explicitly"), and scope ("Does not publish or launch"). The idempotent-retry sentence largely restates idempotentHint=true, only adding "returns the current draft."

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?

Four short, front-loaded sentences that each carry a distinct point (source of version, retention rule, concurrency behavior, retry behavior, scope). No filler.

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

Completeness4/5

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

For a complex nested mutation with an output schema and full safety annotations, the description covers mutation semantics, concurrency, idempotency, and scope adequately. The remaining gap is the undocumented top-level identity inputs (draft_id, name), which is minor given rich nested schema documentation.

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?

Top-level schema coverage is 25% and the description never names draft_id, name, or snapshot directly, so those params rely on the nested schema. It does add meaning for expected_version (stale-fail/reload) and for source bytes/priors retention, which partially compensates for the low coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Replace authoring state" gives a specific verb+resource and the phrase "Does not publish or launch" distinguishes it from publish_recipe_draft and create_recipe_draft. It is clear but slightly indirect about the object (recipe draft) since the title carries that load.

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?

"using the version from get_recipe_draft" tells the agent when/how to sequence the call, and "Does not publish or launch" excludes the publish path. It stops short of naming the alternative tool (publish_recipe_draft) explicitly or stating full prerequisites.

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

Deploy Server

Other Tools