Skip to main content
Glama
Sign In
SAS MCP Server

SAS MCP Server

Official
by sassoftware
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Run Performance Definition

run_performance_definition

Runs a defined performance assessment to score period tables, calculate KPIs, and report champion KPI alert violations, optionally waiting for completion.

Instructions

Run a performance definition: score and assess each period table, then calculate the KPIs.

Name the definition, or the project when it has just one. The run goes on in the background. With wait_seconds the tool waits up to that long (at most 600); when the run has finished it has Model Manager calculate the project's KPIs, as Model Manager's own monitoring workflow does, and reports the KPI alert rules the champion breaks. Otherwise call again with wait_seconds, or read get_project_kpis later. Runs over two small periods took from half a minute to two minutes on SAS Viya 2026.10.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "run_performance_definition"
  }
}

Input Schema

NameRequiredDescriptionDefault
project_idNoThe project instead, when it has one definition.
wait_secondsNoHow long to wait for the run (default 0).
performance_definition_idNoFrom ``create_performance_definition``.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.19.2

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say the call is not read-only and not idempotent; the description goes well beyond by disclosing that the run is asynchronous, that wait_seconds caps at 600, that re-invoking is the polling pattern, that KPIs and champion alert rules are produced, and giving observed latency of 30 seconds to two minutes. That is exactly the context an agent needs to plan timeouts and polling.

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 action is front-loaded and every sentence carries information: target selection, async note, wait behavior, fallback polling, and timing. The Model Manager paraphrase clause is slightly verbose and could be trimmed without losing meaning.

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 mutating, async job-launch tool with an output schema, the description covers everything an agent needs: what triggers, how to wait, the wait limit, polling fallback, and side effects. Return-value detail is correctly left to the output schema.

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 real meaning beyond the schema: the 600-second ceiling on wait_seconds (the schema only states a default of 0) and the conditional semantics of using project versus definition. It does not expand further on identifier formats, which is the only gap.

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 plus the work performed: "Run a performance definition: score and assess each period table, then calculate the KPIs." It also makes clear the run triggers downstream Model Manager KPI calculation, so an agent understands both the action and its consequence.

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?

It tells the agent how to address the target (name the definition, or the project when it has only one) and explicitly offers the alternative path to results: call again with wait_seconds, or read get_project_kpis later. There is no explicit when-not-to-use guidance versus tools like run_ml_project, but the polling alternative is concrete.

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