Surface AI

Set up a surface on a page

surface_setup

The way to add a surface to a page, in one step: the content fields it swaps, the goals it optimizes, and the variants — with the integration bundle deployed. Returns the install guide for adding the snippet to that page. Ask the user to choose the fields, goals and variants first; the new_surface prompt walks through it. Prefer data-attribute selectors such as [data-surface-field="headline"], added to the page source. Variants go live as soon as the snippet is deployed. Counts toward the plan's surface limit; a name already used in the organization is rejected.

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": {
      "name": "<name>",
      "page_url": "<page_url>",
      "fields": "<fields>",
      "goals": "<goals>",
      "variants": "<variants>"
    },
    "name": "surface_setup"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	Unique within the organization.
`goals`	Yes	What success looks like; the first is the one the bandit optimizes.
`fields`	Yes	Page elements each variant replaces.
`page_url`	Yes	The live URL of the page.
`variants`	Yes	Exactly one is the control: the page's current copy, setting every field.
`description`	No	Optional note shown in the dashboard.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 12, 2026
- addedInput schema / properties / description / description
```
Added value: +"Optional note shown in the dashboard."
```
- addedInput schema / properties / fields / items / properties / description / description
```
Added value: +"What the field is, e.g. Hero headline."
```
- addedInput schema / properties / goals / items / properties / dom_event / description
```
Added value: +"click for a button or link, submit for a form."
```
- addedInput schema / properties / variants / items / properties / is_control / description
```
Added value: +"True for the control only."
```
First observedNov 11, 2026

TDQS

A3.9/5.0

Behavior3/5

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

Adds real behavioral context beyond the annotations: it returns an install guide, variants go live as soon as the snippet is deployed, the call counts toward the plan's surface limit, and a duplicate name in the organization is rejected. What it does not cover is permission/auth requirements, rollback or what happens to partially created state on failure for a non-idempotent mutation.

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?

A single dense paragraph that front-loads the purpose, then behavior, then parameter guidance, then limits. Every sentence carries information – no restatement of the title and no 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?

For a six-parameter, five-required mutation with nested variant objects and no output schema, the description covers purpose, prerequisites, side effects, quota limits and the returned install guide. Only failure/rollback semantics and permission requirements are left implicit.

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 still adds meaning: it frames fields as elements each variant replaces, goals as what success looks like, and variants as the control-plus-alternatives set to choose. It also gives selector-style guidance (prefer [data-surface-field=...]) that the schema does not state as a preference.

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: 'the way to add a surface to a page, in one step', and enumerates the constituents (fields, goals, variants, integration bundle deployed). It is clearly a creation tool, distinguishable in spirit from surface_update or variant_create, though it never names a sibling or explicitly excludes one.

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?

Gives a concrete precondition workflow: 'Ask the user to choose the fields, goals and variants first; the new_surface prompt walks through it', and recommends data-attribute selectors for the page source. It lacks explicit 'use X instead when...' routing against siblings, but the when-to-use context is clear.

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?