Skip to main content
Glama

Get the Continue in builder link

builderLink
Read-onlyIdempotent

Get the link that opens one owned app in Tofu’s builder, where a person keeps changing an app by chatting — the same page Continue in builder opens on the dashboard. state is ready when the builder can open this app: url is the builder’s page for it, and message is the sentence that goes with the link. The person opens it themselves, signed in to Tofu as the account that owns the app; the link carries no token, so it opens nothing for anybody else, and the builder starts from the app’s newest code and changes nothing until the person asks it for a change. Otherwise url is null and state says why: not_offered (the builder can’t open apps yet), code_not_held (Tofu doesn’t hold this app’s code: it was sent as a folder Tofu doesn’t keep, or linked to GitHub the older way) or app_type (the builder runs a Vite app or a static site for now), with message saying the same in one sentence. It writes nothing, and another account’s app answers not found.

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": {
      "projectId": "<projectId>"
    },
    "name": "builderLink"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectIdYes

Output Schema

NameRequiredDescriptionDefault
urlYes
stateYes
messageYes
projectIdYes

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?

Beyond the readOnly/idempotent/closed-world annotations, it discloses that the link carries no token and therefore opens nothing for other people, that the builder starts from the app's newest code, that nothing mutates until the person requests a change, and that another account's app returns not found. These are exactly the auth and side-effect facts an agent cannot infer from annotations.

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?

The purpose is front-loaded and the state enumeration is organized in a single pass, so it reads as dense rather than rambling. Some phrasing is redundant, e.g. restating the dashboard-page equivalence and repeating that `message` says the same thing in one sentence, which could be trimmed without losing 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?

Output schema exists, yet the description still explains the ready/not-ready contract and each failure state clearly, and it covers authentication, ownership scoping, and the absence of writes. For a one-parameter read tool with full annotations and an output schema, nothing an agent needs in order to call it correctly is missing.

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 0% for the single `projectId` parameter, so the description must carry the burden. It conveys indirectly that the identifier refers to an app the caller owns ('one owned app', 'another account's app answers not found'), but never names or explains `projectId` itself, its UUID form, or how to obtain one. The discussion of `state`, `url`, and `message` concerns outputs, not the input.

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 first sentence gives a specific verb and resource: 'Get the link that opens one owned app in Tofu's builder,' and anchors it to a user-visible surface ('the same page Continue in builder opens on the dashboard'). An agent can tell this apart from the sharing/auth/database siblings without opening any 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 states the conditions under which the tool is useful (`state` is `ready` when the builder can open this app) and enumerates the three failure conditions with their meanings. It does not name any sibling tool or say what to call instead when `state` is `not_offered`, `code_not_held`, or `app_type`, so it stops short of explicit alternative routing.

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.

Resources