flowforge-mcp

flowforge_manage_branches

List, read, create, or update an assistant's branches to change prompts, voice, or model without touching Main, test each branch, then promote it when ready.

Instructions

List, read, create (fork) or update an assistant's branches.

Use a branch to change prompt/voice/model without touching Main, then run tests against it (flowforge_run_test with branch_id) before promoting. Updating a branch creates a new version on it.

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": {
      "params": "<params>"
    },
    "name": "flowforge_manage_branches"
  }
}

Input Schema

Name	Required	Description	Default
`params`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 6, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already disclose that this is not read-only, not idempotent, and non-destructive. The description adds meaningful behavior beyond that: updating creates a new version, create forks Main when no source is given, and branch changes are isolated from Main until promoted. Permissions or rate-limit behavior are not covered.

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 description is short, front-loaded with the action list, and then explains the branch workflow. Every sentence contributes, though the second sentence could be slightly tighter.

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?

For a multi-action branch-management tool with an output schema, the description covers actions, isolation from Main, testing, promotion, and version creation. It is relatively complete, with only minor gaps around action-specific edge cases and distinctions from assistant-update tools.

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?

The description maps actions to operations ('list', 'read', 'create (fork)', 'update') and notes that updating creates a new version. However, the detailed parameter semantics — fields, branch_id, version='tip', response_format — live in the nested schema rather than the description, and the reported top-level schema coverage is low.

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 uses a specific verb set and resource: 'List, read, create (fork) or update an assistant's branches.' It clearly separates this tool from sibling tools like update_assistant or list_assistants by focusing on branch-level operations.

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 a clear workflow: use a branch to change prompt/voice/model without touching Main, then run tests with branch_id before promoting. This names flowforge_run_test as the related testing tool. It does not explicitly compare against flowforge_update_assistant or state when not to use branches, so it falls short of a 5.

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

Deploy Server