flowforge-mcp

flowforge_manage_tests

Destructive

Create, update, delete, attach, and run agent regression tests to validate prompt or flow changes on a branch before publishing.

Instructions

Create/read/update/delete agent tests, attach them to assistants, list a test's runs, run every attached test for an assistant, and manage test folders. Tests are the regression suite for prompt/flow changes - run them on a branch before publishing.

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_tests"
  }
}

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

A3.5/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true and non-idempotent, so the risk profile is known. The description adds useful lifecycle framing (regression suite, branch-before-publish), but does not disclose which actions carry the destructive weight, that delete/detach gate on a confirm flag, or anything about auth scope or error behavior.

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?

Two sentences, tightly written, with the action inventory front-loaded and the workflow rationale second. The action enumeration is dense but each item earns its place by signalling the dispatcher's scope; nothing is padded.

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 ten-action dispatcher with a rich inner schema and an output schema, the description covers scope and intent adequately. Remaining gaps are the safety-critical confirm requirement for delete/detach and routing guidance against the narrower sibling tools, which the description leaves entirely to structured fields.

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 contributes no per-action parameter mapping of its own. In practice the inner ManageTestsInput schema annotates every field by action (confirm for delete/detach, branch_id for run_all, fields shape for create/update), so the agent is not left guessing despite the top-level coverage metric reading 0% on the single 'params' wrapper.

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?

The description names concrete verbs and resources (create/read/update/delete tests, attach to assistants, list runs, run_all, folders) and frames the domain as a regression suite for prompt/flow changes. That is enough to distinguish it from unrelated siblings, but it does not explicitly differentiate itself from close siblings like flowforge_list_tests, flowforge_run_test, or flowforge_get_test_run, which cover a subset of the same surface.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is real usage context: 'run them on a branch before publishing' tells the agent the canonical workflow for run_all. However, there is no when-to-use-this-vs-sibling guidance, even though three sibling tools overlap with its list/get/run actions, and no statement of when not to use the umbrella tool.

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

Deploy Server