Surface AI

Set the control variant

variant_set_control

DestructiveIdempotent

Make a variant the control of its segment — the baseline the others are measured against — replacing the current control. An archived variant can't be the control. Status is unchanged; use variant_set_status for that.

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": {
      "surface_id": "<surface_id>",
      "variant_id": "<variant_id>"
    },
    "name": "variant_set_control"
  }
}

Input Schema

Name	Required	Description	Default
`surface_id`	Yes	The surface id, from surface_list.
`variant_id`	Yes	The variant id, from variant_list.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 12, 2026
- changedInput schema / properties / surface_id / description
```
Previous value: -"The surface id."New value: +"The surface id, from surface_list."
```
First observedNov 11, 2026

TDQS

A4.2/5.0

Behavior4/5

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

The annotations already flag destructiveHint=true and idempotentHint=true, so the bar is lower; the description still adds real context by stating that the current control is replaced and that archived variants are rejected. It does not say what happens to historical results or segments already measured against the old baseline, which would matter for a destructive change.

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?

Three short sentences: the effect first, the constraint second, the sibling redirect last. Nothing is repeated and no sentence is wasted.

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?

For a two-parameter mutation with no output schema and meaningful annotations, the description covers effect, precondition, and alternative adequately. Only the downstream consequence of swapping the measurement baseline is left implicit.

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% and both parameters already document their source lookup (surface_list, variant_list), so the schema does the heavy lifting. The description adds no format or relationship detail between surface_id and variant_id, matching the baseline of 3.

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 description gives a specific verb and resource ('Make a variant the control of its segment') and immediately defines what control means ('the baseline the others are measured against'), which is the key concept an agent needs. It also names the sibling it is not, variant_set_status.

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 explicitly carves out the adjacent operation ('Status is unchanged; use variant_set_status for that') and states a precondition ('An archived variant can't be the control'). That is clear routing plus a hard constraint, though it doesn't discuss surface readiness or when reassigning control is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Surface AI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?