Skip to main content
Glama
Sign In

Stride — AI software delivery platform

by page.stride
OverviewDiscussionsAdmin

Refine UI design

stride.refine_ui_design

Refine one option of an existing UI design with a natural-language instruction — appends a new version (the prior version is kept). Identify the design by UUID and the option by its key (A/B/C…). Can take up to ~4 minutes, longer than many MCP clients wait. If it is still running after about 52 seconds this tool answers "still running" with a toolCallId and finishes in the background, saving the result when done. Meanwhile a repeat call for the same story (for a refine, the same option) starts nothing and answers "still running" again; stride.get_tool_call_status follows the run: given that toolCallId and waitSeconds 40 it waits for the run (a 3-minute run takes about 5 calls) and returns the result once it is saved, or says it failed. Cancelling the call before it answers stops the run and saves nothing.

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": {
      "designId": "<designId>",
      "optionKey": "<optionKey>",
      "instruction": "<instruction>"
    },
    "name": "stride.refine_ui_design"
  }
}

Input Schema

NameRequiredDescriptionDefault
designIdYesUUID of the UI design.
optionKeyYesOption key to refine (e.g. "A").
instructionYesWhat to change (e.g. "make the header sticky, warmer accent").

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations: appends a new version and keeps the prior one (clarifying that destructiveHint=false while the call still mutates), gives the ~4 minute runtime, the ~52 second cutoff after which it returns a toolCallId and finishes in the background, and states that cancelling before it answers saves nothing. That is exactly the timing, async and cancellation context an agent cannot get from readOnlyHint/openWorldHint/idempotentHint.

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?

Front-loaded with the core operation, then the async protocol, then cancellation — a sensible order with no filler. It is dense and somewhat run-on in the async section, but nearly every clause carries operational meaning.

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

Completeness5/5

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

No output schema exists, and the description covers what an agent needs: what comes back on success ('still running' plus toolCallId), how to retrieve the eventual result, how many polls a long run takes, and what happens on failure or cancellation. Nothing material is missing for correct invocation.

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 designId, optionKey and instruction are already documented. The description only restates them (UUID for the design, key A/B/C for the option) without adding format or constraint detail, so baseline 3 applies.

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?

States a specific verb and resource: refine one option of an existing UI design with a natural-language instruction, and says it appends a new version rather than replacing. It implicitly contrasts with stride.generate_ui_design by scoping to an existing design, and the designId/optionKey/instruction framing makes the operation unmistakable.

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 stride.get_tool_call_status when the tool answers 'still running', and warns that repeating the same call starts nothing. It stops short of naming generate_ui_design as the alternative for creating a new design from scratch, but the 'existing' qualifier carries most of that.

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

All Stride — AI software delivery platform toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources