Skip to main content
Glama
Sign In
SAS MCP Server

SAS MCP Server

Official
by sassoftware
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Describe Analytic Store

describe_analytic_store
Idempotent

Inspect an analytic store to learn its inputs, outputs, and algorithm, helping you register the model with the correct target and event.

Instructions

Describe an analytic store (a model saved in CAS): its inputs, outputs and algorithm.

Runs PROC ASTORE DESCRIBE. Use it before register_model to see which variables the model expects and produces, and so which target and event to register it with.

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": "describe_analytic_store"
  }
}

Input Schema

NameRequiredDescriptionDefault
table_nameYesThe analytic store table (for example one written by a ``savestate rstore=`` statement).
caslib_nameYesCaslib of the analytic store table.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.19.2

TDQS

A4/5.0
Behavior3/5

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

The description adds real behavioral context beyond the annotations by disclosing that it executes PROC ASTORE DESCRIBE against a CAS table. However, with readOnlyHint=false but destructiveHint=false and idempotentHint=true, the actual effect profile (does it execute code server-side? any cost or latency?) is left for the agent to infer rather than stated.

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?

Two short sentences: the first states what it is and what it returns, the second gives the workflow reason. Purpose is front-loaded with zero filler.

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?

An output schema exists and parameter coverage is complete, so the description only needs to justify invocation, which it does. The one gap is that it does not clarify the apparent read-only nature of the operation against a readOnlyHint of false, which an agent might find confusing.

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 100% and both parameters are documented in the schema itself, so the baseline applies. The description mentions the model variables that will be reported but adds no meaning about what caslib_name or table_name accept beyond the schema, e.g. how to locate the store table.

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 ('Describe an analytic store') and immediately disambiguates the jargon as 'a model saved in CAS'. It further pins down what the description returns: inputs, outputs and algorithm, which is enough for an agent to tell it apart from other describe/catalog tools.

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?

Explicitly says 'Use it before register_model' and explains why: to learn which variables the model expects and produces so the right target and event can be chosen. That is clear situational guidance tied to a named alternative, though no when-not-to-use or failure conditions are given.

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