Skip to main content
Glama
Sign In
SAS MCP Server

SAS MCP Server

Official
by sassoftware
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Validate Published Model

validate_published_model

Scores sample rows with a published model copy in its destination and returns results for comparison with the registered model, confirming the copy behaves the same.

Instructions

Check a published model by scoring a few rows with the published copy.

Model Manager's publish validation: the first rows rows of the table are scored in the destination itself (MAS, CAS, ...), and the scored rows come back. Compare them with test_score_model on the registered model to confirm the copy behaves the same. Name the copy by published_model_id (see list_published_models), or by model_id and destination_name.

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": {
      "caslib_name": "<caslib_name>",
      "table_name": "<table_name>"
    },
    "name": "validate_published_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsNoHow many rows to score (default 10, at most 100).
model_idNoThe registered model, instead of published_model_id.
table_nameYesA loaded CAS table holding the model's inputs.
caslib_nameYesCaslib of the input table.
timeout_secondsNoHow long to wait (default 180).
destination_nameNoWith model_id (default: the deployment's ``MCP_DEFAULT_PUBLISH_DESTINATION``).
published_model_idNoThe published copy's ID.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.19.2

TDQS

A4.5/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description adds genuinely useful context beyond them: the scoring executes inside the destination environment (MAS, CAS) rather than locally, and the scored rows are returned for comparison. It does not describe what happens if scoring exceeds timeout_seconds or whether any state is written in the destination, which is the remaining gap for a non-read-only tool.

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 purpose and the comparison workflow are front-loaded in the first two sentences, with identification mechanics last. A few phrases, such as 'Model Manager's publish validation' and the repeated '(see list_published_models)', are marginally redundant but still earn their place by orienting the agent.

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?

With an output schema present, return values need no explanation, and the description still notes that scored rows come back. For a 7-parameter tool with two identification paths it covers what an agent needs to call it correctly; only failure and timeout behavior are left unaddressed.

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 coverage is 100%, so the baseline is 3, but the description adds the relationship the schema only hints at: the copy is named either by published_model_id alone, or by model_id combined with destination_name. That pairing logic is the main source of caller error and is clarified here, along with the pointer to list_published_models for ID discovery.

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 states a specific verb and resource: score a few rows using the *published* copy of a model. That scope is precisely what separates it from the sibling test_score_model, which acts on the registered model, so an agent can route between them without opening either schema.

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 gives an explicit use case (confirm the published copy behaves the same as the registered model) and names the comparison tool, test_score_model, along with the condition that selects it. It also names list_published_models as the way to obtain the published_model_id, so the prerequisite step is spelled out rather than inferred.

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