Skip to main content
Glama
Sign In
SAS MCP Server

SAS MCP Server

Official
by sassoftware
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Test Score Model

test_score_model

Verify a registered SAS model runs by scoring a sample of table rows in the Model Manager compute context and returning output columns; check readiness before publishing or monitoring.

Instructions

Score a few rows with a registered model and return the scored rows.

Model Manager's own score test: it takes the first rows rows of the table, scores them with the model in the "SAS Model Manager compute context", waits, and returns them with the model's output columns (for example P_BAD1 and I_BAD). Use it to check that a model runs before publishing or monitoring it. Nothing is left behind: the scratch tables and the score definition are removed. It takes about 15 seconds plus a compute session start.

The table needs the model's input variables (get_model lists them). For a whole table use score_table.

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": {
      "model_id": "<model_id>",
      "caslib_name": "<caslib_name>",
      "table_name": "<table_name>"
    },
    "name": "test_score_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsNoHow many rows to score (default 10, at most 100).
model_idYesThe model's ID.
table_nameYesA loaded CAS table holding the model's inputs.
caslib_nameYesCaslib of the input table.
timeout_secondsNoHow long to wait for the score test (default 180).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.19.2

TDQS

A4.7/5.0
Behavior5/5

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

Annotations declare readOnlyHint=false without explaining why, and the description fills that gap: it says scratch tables and a score definition are created and then removed, so nothing is left behind. It also discloses latency (about 15 seconds plus a compute session start) and the timeout behavior, which no annotation conveys.

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?

The action-and-scope sentence is front-loaded, followed by cleanup, timing, prerequisite, and alternative in a compact sequence. Every sentence adds a fact an agent would otherwise have to discover by calling the tool.

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?

For a bounded mutation-plus-read tool with an output schema, the description covers side effects, cleanup, latency, prerequisites, and the sibling alternative. Nothing needed to invoke it correctly is missing.

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 coverage is 100%, so all five parameters are already documented, including the rows default/limit and the timeout. The description adds only the pointer to get_model for discovering required input variables, which the schema's table_name description already covers in substance. Baseline 3 is appropriate when the schema carries the semantics.

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?

States a specific verb and resource ('Score a few rows with a registered model and return the scored rows') and immediately bounds the scope to a small sample. It names the sibling that covers the other case ('For a whole table use score_table'), so an agent can separate the two 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?

Gives an explicit purpose ('Use it to check that a model runs before publishing or monitoring it'), an explicit alternative for the full-table case, and a prerequisite ('The table needs the model's input variables'). That covers when to use it, when not to, and how to satisfy the input requirement.

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