Skip to main content
Glama

sb_set

Writes style, config, or specials keys to one node or many in a single save and live frame, per breakpoint by default, with base:true setting the fallback layer and unset removing keys.

Instructions

Write style, config or specials keys on one node, or on many through edits (one save, one live frame). Per BREAKPOINT by default; base:true writes the fallback layer, right for a value that should not vary.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "sb_set"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNo
baseNo
keysNo
editsNo
forceNoOverride a render-inference guard; reported as forced
stateNoAn interaction state — "hover", or "stuck" for how a pinned element looks once it is stuck (needs a sticky/fixed self-or-ancestor; a descendant styles itself through the host).
unsetNoKeys to REMOVE from the same slot — the only way to undo a write. Setting null is not the same: null is a stored value, so the override still counts as present.
dry_runNo
namespaceNo
breakpointNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.103.0
    • changedInput schema / properties / edits / items / required
      Previous value: -[
      -  "id",
      -  "namespace",
      -  "keys"
      -]New value: +[
      +  "id",
      +  "namespace"
      +]
  2. Changed1 schema field changedv0.63.0
    • addedInput schema / properties / force
      Added value: +{
      +  "description": "Override a render-inference guard; reported as forced",
      +  "type": "boolean"
      +}
  3. Changed3 schema fields changedv0.12.0
    • addedInput schema / properties / edits / items / properties / unset
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedInput schema / properties / state / description
      Previous value: -"An interaction state, e.g. \"hover\""New value: +"An interaction state — \"hover\", or \"stuck\" for how a pinned element looks once it is stuck (needs a sticky/fixed self-or-ancestor; a descendant styles itself through the host)."
    • addedInput schema / properties / unset
      Added value: +{
      +  "description": "Keys to REMOVE from the same slot — the only way to undo a write. Setting null is not the same: null is a stored value, so the override still counts as present.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  4. First observedv0.1.4

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly=false, destructive=false), and the description adds real behavior beyond that: bulk edits coalesce into "one save, one live frame", and writes land on the breakpoint layer by default with `base` targeting the fallback layer. It omits the render-inference guard and the existence of `dry_run`, but the layer/atomicity semantics are a meaningful addition.

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?

Two dense sentences with no filler, and the primary write scope is front-loaded before the layering caveat. The phrasing "one save, one live frame" is terse to the point of jargon, which costs a little clarity against its brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A 10-parameter mutation tool with nested `edits`, no output schema, and no annotations on reversibility. The description covers the core write semantics but leaves out `dry_run` (the main safety valve) and `force`, so an agent cannot fully plan a safe call from the description alone.

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?

At 30% schema coverage the description must compensate, and it does explain the two highest-risk knobs (`base` and the default breakpoint scoping) plus the id-vs-edits split. Several parameters — `dry_run`, `namespace`, `keys`, and the per-edit `breakpoint`/`state` fields — remain undocumented in the description, relying on the schema's own partial descriptions.

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 (write style/config/specials keys) and explicitly covers both modes: one node via `id`, many via `edits`. It does not name a sibling to differentiate from (e.g. sb_bind, sb_remove), so it stops short of the top of the scale, but an agent can tell what this does without opening the schema.

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?

Gives one concrete selection rule — `base:true` for values that should not vary, otherwise per-breakpoint is the default — which is genuinely useful. However, it never says when to reach for this tool instead of alternatives like sb_bind or sb_remove, and says nothing about when to prefer `edits` over a single call.

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