Skip to main content
Glama
singlestore-mcp-server

singlestore-mcp-server

by jonasliesas

notebook_save

Save a notebook as an .ipynb file in the SQL folder or to SAS Viya by reference, with overwrite and version-conflict handling to prevent unintended changes.

Instructions

Save a notebook (nbformat 4 JSON) as a .ipynb file in the SQL folder, or on SAS Viya by its ref.

SAS Viya (``name`` a ``sas-content://`` / ``sas-server://`` ref; SAS Content stores it as
``application/x-ipynb+json``): ``expected_version`` is the version the notebook opened; a newer one on Viya
answers ``conflict`` (nothing written), an existing file on Save as ``exists``, a ref of another connection
``connection_mismatch`` (``use_active`` saves it to the same path on the active connection) - as the SQL
Editor's Save does.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "notebook": "<notebook>"
    },
    "name": "notebook_save"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
notebookYes
overwriteNo
use_activeNo
expected_versionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.11.0
    • addedInput schema / properties / expected_version
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Expected Version"
      +}
    • addedInput schema / properties / use_active
      Added value: +{
      +  "default": false,
      +  "title": "Use Active",
      +  "type": "boolean"
      +}
  2. Addedv0.8.1

TDQS

A3.5/5.0
Behavior4/5

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

Adds substantial behavior beyond the annotations: it documents the Viya error contract ('conflict' with nothing written, 'exists', 'connection_mismatch') and the 'use_active' escape hatch that saves to the same path on the active connection. Annotations only say readOnlyHint=false and destructiveHint=false, so this write-failure semantics detail is genuinely additive. Minor gap: it never explicitly ties the 'exists' outcome to the overwrite parameter or says what a successful save returns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence is front-loaded and clear, but the second paragraph is a run-on with stacked parentheticals and dash clauses ('a ref of another connection connection_mismatch (use_active saves it to the same path on the active connection) - as the SQL Editor's Save does') that takes effort to parse. Information density is high but structure costs readability.

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?

Covers the Viya path well, including failure modes, but is asymmetric: the 'SQL folder' destination is named without saying where it is, whether overwrite applies there, or how conflicts resolve locally. For a 5-parameter write tool with a nested notebook object and no output schema, the local-path half and the overwrite semantics remain underspecified.

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 0%, so the description must carry parameter meaning, and it partially does: it explains the accepted ref formats for 'name' (sas-content:// / sas-server://), the semantics of 'expected_version' (the version the notebook opened at), and 'use_active'. However 'notebook', 'overwrite', and the SQL-folder form of 'name' get no parameter-level explanation, leaving roughly half the parameters undocumented.

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?

States a specific verb and resource ('Save a notebook (nbformat 4 JSON) as a .ipynb file') and names the two destinations: the SQL folder or SAS Viya by ref. It does not explicitly differentiate itself from near-siblings like sql_editor_save_file or notebook_open, but the resource and format are specific enough that an agent can identify the operation.

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

Usage Guidelines3/5

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

Usage context is implied through the destination modes ('in the SQL folder, or on SAS Viya by its ref') and the analogy 'as the SQL Editor's Save does', which tells the agent when the Viya path applies. There is no explicit statement of when to choose this over sql_editor_save_file or notebook_open, and no prerequisite guidance (e.g., must the notebook already be open?).

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