Skip to main content
Glama
Sign In
SAS MCP Server

SAS MCP Server

Official
by sassoftware
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Set Project Champion

set_project_champion
DestructiveIdempotent

Sets a model as its project's champion by copying missing target, event, and variable metadata to the project, so Model Manager accepts and publishes it.

Instructions

Make a model its project's champion, preparing the project as Model Manager's UI does.

The champion is the model a project publishes and monitors. Model Manager refuses a champion until the project has its target fields and its variables, which PROC REGISTERMODEL does not set, so this first copies the model's target, event and event probability variable to the project where they are missing, and adds the model's input and output variables the project lacks. Fields already set are kept.

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": {
      "project_id": "<project_id>",
      "model_id": "<model_id>"
    },
    "name": "set_project_champion"
  }
}

Input Schema

NameRequiredDescriptionDefault
model_idYesA model in that project.
project_idYesThe project's ID.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.19.2

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already flag destructive=true and idempotent=true, but the description goes further by naming exactly what is mutated: the model's target, event, and event probability variable are copied to the project, and missing input/output variables are added. It also states 'Fields already set are kept', which tells the agent what will NOT be overwritten — valuable context beyond the annotations. It stops short of saying whether variable additions can be undone or what the response reports.

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 is front-loaded in the first sentence, followed by the definition of a champion and the concrete side effects. A couple of clauses ('preparing the project as Model Manager's UI does', 'which PROC REGISTERMODEL does not set') are explanatory rather than essential, but they earn their place by justifying the copy behavior.

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 and annotations covering the safety profile, the description only needed to explain the mutation semantics, and it does so concretely. The remaining gap is the absence of guidance relative to the other champion-related tools in the catalog.

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 simple IDs already documented in the schema ('A model in that project', 'The project's ID'). The description adds a constraint by implication (the model must belong to that project) but no new syntax or format detail, so the baseline of 3 applies.

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?

The opening sentence gives a specific verb and resource: 'Make a model its project's champion', and the second sentence clarifies what a champion is (the model a project publishes and monitors). This distinguishes it from a plain register/publish action, but it never names or contrasts the close siblings publish_ml_champion_model or register_ml_champion_model, leaving that differentiation to inference.

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 rather than stated: the reader learns Model Manager refuses a champion without target fields and variables, which explains why this tool exists. There is no explicit 'use this instead of X' routing and no stated preconditions or when-not guidance for the similarly named champion siblings.

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