Skip to main content
Glama

Look Up Recorded Screen

design_preview
Read-onlyIdempotent

Look up a recorded screen by object, context and framework. Returns its running screen URL, content hash, brand and theme. No new screen is generated. object_registry reads the definition behind the screen. Set reproduce true when the command and calls used to generate it are requested.

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": {
      "object": "<object>"
    },
    "name": "design_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
objectYesAn object with recorded screens at this version.
contextNoThe context the screen was composed for.detail
frameworkNoThe framework of the generated app.react
reproduceNoInclude the command and calls for reproducing this result.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / object / enum
      Previous value: -[
      -  "Agent",
      -  "Approval",
      -  "Article",
      -  "Invoice",
      -  "Media",
      -  "Organization",
      -  "Plan",
      -  "Product",
      -  "Relationship",
      -  "Subscription",
      -  "Transaction",
      -  "Usage",
      -  "User"
      -]New value: +[
      +  "Agent",
      +  "Approval",
      +  "Article",
      +  "Grant",
      +  "Invoice",
      +  "Media",
      +  "Organization",
      +  "Plan",
      +  "Product",
      +  "Relationship",
      +  "Subscription",
      +  "Task",
      +  "Transaction",
      +  "Usage",
      +  "User"
      +]
  2. Changed1 schema field changed
    • changedInput schema / properties / object / enum
      Previous value: -[
      -  "Agent",
      -  "Article",
      -  "Invoice",
      -  "Media",
      -  "Organization",
      -  "Plan",
      -  "Product",
      -  "Relationship",
      -  "Subscription",
      -  "Transaction",
      -  "Usage",
      -  "User"
      -]New value: +[
      +  "Agent",
      +  "Approval",
      +  "Article",
      +  "Invoice",
      +  "Media",
      +  "Organization",
      +  "Plan",
      +  "Product",
      +  "Relationship",
      +  "Subscription",
      +  "Transaction",
      +  "Usage",
      +  "User"
      +]
  3. Changed1 schema field changed
    • changedInput schema / properties / object / enum
      Previous value: -[
      -  "Article",
      -  "Invoice",
      -  "Media",
      -  "Organization",
      -  "Plan",
      -  "Product",
      -  "Relationship",
      -  "Subscription",
      -  "Transaction",
      -  "Usage",
      -  "User"
      -]New value: +[
      +  "Agent",
      +  "Article",
      +  "Invoice",
      +  "Media",
      +  "Organization",
      +  "Plan",
      +  "Product",
      +  "Relationship",
      +  "Subscription",
      +  "Transaction",
      +  "Usage",
      +  "User"
      +]
  4. Changed1 schema field changed
    • addedInput schema / properties / reproduce
      Added value: +{
      +  "default": false,
      +  "description": "Include the command and calls for reproducing this result.",
      +  "type": "boolean"
      +}
  5. Changed3 schema fields changed
    • addedInput schema / properties / context / description
      Added value: +"The context the screen was composed for."
    • addedInput schema / properties / framework / description
      Added value: +"The framework of the generated app."
    • addedInput schema / properties / object / description
      Added value: +"An object with recorded screens at this version."
  6. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the bar is lower. The description still adds real value by disclosing the return payload (running screen URL, content hash, brand, theme) and explicitly ruling out generation of a new screen, which is the main behavioral ambiguity for a 'preview'-named tool.

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?

Four short sentences, front-loaded with the lookup action and followed by the return payload, the non-generation caveat, the sibling routing, and the reproduce condition. No filler, though the sibling and reproduce sentences could be ordered slightly more tightly.

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 four parameters, three enums, a required object, and no output schema, the description covers the essentials: what is looked up, what comes back, what does not happen, and where to go for the definition. Minor gaps remain around error behavior for unrecorded combinations, but nothing needed to invoke it correctly is missing.

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 description coverage is 100%, so the baseline is 3. The description adds meaning on top by framing object/context/framework as the lookup key set and by explaining when to set reproduce (when the generating command and calls are requested), which is a decision cue the schema's terse 'Include the command and calls' does not fully convey.

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 opens with a specific verb and resource ('Look up a recorded screen') and immediately names the lookup dimensions (object, context, framework). It also distinguishes this tool from object_registry, which 'reads the definition behind the screen,' so an agent can separate a screen fetch from a definition fetch without opening either schema.

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 gives clear usage context: this is a read-only lookup, 'No new screen is generated,' and the sibling object_registry is named for retrieving the underlying definition. It also states the condition for setting reproduce. It stops short of explicit when-not guidance or listing other alternatives, so it is clear but not exhaustive.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.