Skip to main content
Glama
Sign In

run.zero

by de.run-zero
OverviewDiscussionsAdmin

Get preview link

runzero_work_url
Idempotent

The URL where this app's UNPUBLISHED changes can be looked at, and a link that opens it (the plain hostname refuses without one). Call this after EVERY change to an app that publishes on request, and give the user the link with a plain sentence: their change is on the preview, their real site is untouched, and it goes live when they say so. Without that sentence they look at their own website, see nothing, and conclude the change was lost.

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": {
      "app": "<app>"
    },
    "name": "runzero_work_url"
  }
}

Input Schema

NameRequiredDescriptionDefault
appYesName of the app

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Adds real context beyond annotations: the plain hostname refuses access without the link, so the raw URL alone is insufficient. However, annotations declare readOnlyHint=false on what reads like a getter, and the description never explains that discrepancy or any side effect (e.g. whether it triggers a preview build). With the non-read-only flag unexplained, a 3 is warranted.

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?

Well front-loaded: what it returns first, then when to call, then how to present it. The closing line about the user seeing nothing and concluding the change was lost partly restates the preceding sentence, but it justifies the presentation requirement rather than padding.

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?

There is no output schema, so the description must describe the return value, and it does: a URL plus a link. It omits the exact response shape (single string vs. two fields), which is a minor gap for a one-parameter read helper.

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% with a single required 'app' parameter already documented as 'Name of the app'. The description adds no further meaning about that parameter's format or accepted values, so the baseline 3 applies.

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: returns the URL where an app's UNPUBLISHED changes can be viewed, plus an openable link. That is clear and concrete. It does not differentiate from near-siblings like runzero_deploy_preview or runzero_preview_version, which an agent could reasonably confuse with this 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 strong, explicit call condition: 'Call this after EVERY change to an app that publishes on request.' That is far better than most definitions. It stops short of naming alternatives or saying when this is NOT the right call versus deploy_preview/preview_version.

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

All run.zero 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