Fetch Hive

Test a workflow on sample data

test_run_draft

Destructive

Run a workflow once as a test: steps that read from connected apps get realistic sample data, and steps that send messages, change things in apps or wait for a person are switched off, so nothing reaches anyone. Use it to prove a change works and see which step breaks. It costs money like a run (with a cost cap): call it first without approved to get the cost, and only call again with approved: true after the person says yes. Then call get_test_run until done is true; check_test_run scores the result and says what to improve.

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": {
      "workflow_id": "<workflow_id>"
    },
    "name": "test_run_draft"
  }
}

Input Schema

Name	Required	Description
`inputs`	No	Start input values. Inputs left out use their example value or a sample.
`approved`	No	true only after the person has agreed to the test run and its cost.
`workflow_id`	Yes	The workflow to test.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.4/5.0

Behavior3/5

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

The description adds substantial behavior the annotations don't convey: read steps receive realistic sample data, side-effecting and human-wait steps are disabled, and the run incurs cost subject to a cap. However, the annotations declare destructiveHint=true and openWorldHint=true, which sits in mild tension with the promise that 'nothing reaches anyone'; the description doesn't reconcile that or explain why a test run is marked destructive.

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?

Purpose and the safety scope are front-loaded, followed by the cost/approval loop and the polling handoff. Every sentence carries information, though the final paragraph packs three separate instructions (cost, approval, polling, scoring) into a dense block that could be split for scanability.

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?

For a non-idempotent, cost-incurring run tool with no output schema, the description covers the prerequisites (human consent), the multi-call protocol, and which siblings continue the flow. Nothing an agent needs in order to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description earns more by explaining approved as a two-phase cost-consent gate ('call it first without approved to get the cost') rather than a plain boolean. It adds little for inputs beyond noting omissions fall back to example or sample values, which the schema already says.

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 opens with a specific verb and resource, 'Run a workflow once as a test', then immediately defines the scope in terms of what is simulated versus suppressed. That framing lets an agent separate it from run_workflow (a real, effect-carrying run) without reading either schema.

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

Usage Guidelines5/5

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

It states the use case ('prove a change works and see which step breaks') and gives an explicit call sequence: first without approved to obtain cost, then with approved: true only after the person agrees, then poll get_test_run until done is true. It even hands off to check_test_run for scoring, leaving nothing to inference.

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

All Fetch Hive tools Inspect

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

Need Help?