Surface AI

Create variants

variant_create

Add variants to a surface, as DRAFT; activate them with variant_set_status. Returns the surface's full variant list.

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>",
      "variants": "<variants>"
    },
    "name": "variant_create"
  }
}

Input Schema

Name	Required	Description	Default
`variants`	Yes	Each an object of field key to value, with the keys the surface's fields use. Optional is_control (one per segment) and segment_id.
`surface_id`	Yes	The surface id, from surface_list.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 12, 2026

changedInput schema / properties / surface_id / description

Previous value: -"The surface id."New value: +"The surface id, from surface_list."

changedInput schema / properties / variants / description

Previous value: -"Variant objects, each with the fields the surface renders."New value: +"Each an object of field key to value, with the keys the surface's fields use. Optional is_control (one per segment) and segment_id."

First observedNov 11, 2026

TDQS

A3.6/5.0

Behavior3/5

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

The annotations already declare this is a non-read-only, non-destructive, non-idempotent write, and the description adds the genuinely useful fact that records land in DRAFT state and require a second call to activate. That is real context beyond the annotations, but permission requirements, duplicate handling, and failure modes are left unstated. With annotations covering the safety profile, this is solid but not rich.

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?

A tight two-clause sentence with the create-and-draft behavior front-loaded, followed by the activation pointer and the return shape. No filler, though the dashes make it slightly telegraphic.

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, the description covers the operation, the lifecycle state, the follow-up call, and what is returned, which is most of what an agent needs. Minor gaps remain around validation errors and duplicate variants.

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%, so the schema already explains surface_id provenance and the variants object shape including is_control and segment_id. The description adds no parameter-level meaning beyond that, which is the expected baseline when the schema does the heavy lifting.

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?

States a specific verb and resource ("Add variants to a surface") plus the resulting state (DRAFT), and points at variant_set_status for activation. It does not distinguish itself from variant_update, so an agent comparing the two write paths still has to infer the difference.

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 routes the agent to variant_set_status when the goal is to make variants live, which is the key follow-up decision. It gives no guidance on when to prefer this over variant_update or what happens if variants already exist.

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?