Simba MCP Server

Official

by getsimba-ai

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

Update Study

update_study

Destructive

Update study settings by replacing all fields; pass the current version to prevent stale updates and set state, limits, question, and context as needed.

Instructions

Replace owner-controlled study settings. Send the full object: every field is assigned, so read the study first and pass its current values plus version (stale versions fail with 412). Omitting state or limits does not preserve them; omitting context keeps the stored context and an empty string clears it. State is active, paused or archived; paused blocks new reservations and does not cancel running work. Editing question or context triggers no action.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`name`	Yes
`state`	No	Backend state: active, paused or archived.	active
`context`	No	Optional scope, data caveats and assumptions a reader needs to interpret results. Not rules; see question. Omit to leave unchanged on update; send an empty string to clear.
`version`	Yes
`question`	Yes	What the study should find out, in one or two sentences. Stored and shown to humans; never executed or used as an acceptance rule. Do not put thresholds, validation rules or fit limits here: those belong in a quality policy, recipe revisions and max_attempts/max_concurrent. Exploratory and reliability questions are valid.
`study_id`	Yes
`max_attempts`	Yes
`max_concurrent`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.6.1Sep 24, 2026

addedInput schema / properties / context

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional scope, data caveats and assumptions a reader needs to interpret results. Not rules; see question. Omit to leave unchanged on update; send an empty string to clear.",
+  "title": "Context"
+}

addedInput schema / properties / question / description

Added value: +"What the study should find out, in one or two sentences. Stored and shown to humans; never executed or used as an acceptance rule. Do not put thresholds, validation rules or fit limits here: those belong in a quality policy, recipe revisions and max_attempts/max_concurrent. Exploratory and reliability questions are valid."

addedInput schema / properties / question / examples

Added value: +[
+  "How much do paid search and paid social contribute to weekly sales after price, promotions and seasonality?",
+  "Which carryover and saturation choices does the data support for TV, and how sensitive are contributions to them?",
+  "Can a weekly model across all channels produce estimates that hold up on a temporal holdout?"
+]

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 already mark this as destructive and non-idempotent, but the description adds substantial behavioral detail: every field is assigned, stale versions fail with 412, omitting state or limits drops them, omitting context preserves it, empty string clears it, and paused does not cancel running work. This goes well beyond the structured annotations.

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?

Every sentence carries essential operational information, and the most important concept—full replacement—is front-loaded. The description is dense but efficient, with no filler or repetition of schema content.

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 destructive, non-idempotent update with 8 parameters and low schema coverage, the description covers the major gotchas: read-before-update, optimistic concurrency via version, omission semantics, and state behavior. The output schema exists, so return values need no description, but a bit more detail on max_attempts/max_concurrent and the exact meaning of 'triggers no action' would make it fully complete.

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?

Schema description coverage is only 38%, but the description compensates for the most important parameters: version's concurrency role, state's allowed values and side effects, context's preserve/clear behavior, and question's 'no action' semantics. Parameters like max_attempts and max_concurrent are only addressed as 'limits', so not every parameter is fully elaborated, but the critical ones are covered.

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 opens with a precise verb and resource: 'Replace owner-controlled study settings.' It immediately clarifies that this is a full-object replacement, not a partial update, and the resource 'study settings' distinguishes it from sibling tools like update_run or update_recipe_draft.

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?

The description gives strong process guidance: read the study first, pass current values plus version, and understand omission semantics for state, limits, and context. It does not explicitly name alternatives or when-not-to-use conditions, but the context is clear enough for an agent to use this tool correctly.

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

Deploy Server