Spaces by Peakflo

workflow_judge_set

Destructive

Create or replace the quality judge of one workflow (3-5 Jev questions). It is active at once; no person approves it. Use when workflow_get shows needsJudge or a save returns the no-judge warning. Do not name a customer, an id, or a fixed amount in a question. Next step: workflow_test_run, fix until the run is clean and the judge passes, then workflow_save_version. Limits: refused while your own trial runs; a person can edit or turn it off and their change wins. Example: {"workflowId":"invoice-flow","questions":[{"id":"has_total","text":"Does the output state a total amount?","type":"yes"}]}.

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": {
      "workflowId": "<workflowId>",
      "questions": "<questions>"
    },
    "name": "workflow_judge_set"
  }
}

Input Schema

Name	Required	Description	Default
`note`	No
`questions`	Yes
`workflowId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Adds real behavior beyond the annotations: the judge is active immediately with no human approval, the caller's own trial blocks the call, and later human edits override the agent's version. It also states a content restriction (no customer names, ids, or fixed amounts in questions). One gap: it says 3-5 questions while the schema permits 1-8, so an agent following the prose could wrongly split or pad its judge.

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?

Front-loads purpose, then trigger, then constraint, then next step, then limits, then example — a logical flow with no filler sentences. It is on the long side for a small tool, but each sentence carries a distinct constraint or routing instruction.

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 destructive, no-approval write with no output schema and zero schema coverage, it covers activation, blocking conditions, human override, content constraints, and the follow-up sequence. An agent can call it and plan its next steps without further lookups.

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%, so the description is the only place semantics can live. It adds a concrete example for workflowId, id, text, and type, plus the 'no customer/id/amount' rule, but leaves 'note' and the scoring fields (pass_at, fail_at, options, passOptions, appliesTo) entirely unexplained.

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?

States a specific verb and resource ('Create or replace the quality judge of one workflow') plus the 3-5 question count, which cleanly separates it from the read-only sibling workflow_judge_get and from the generic llm_judge_* family. An agent knows exactly what artifact this produces without opening the 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?

Gives explicit triggers ('Use when workflow_get shows needsJudge or a save returns the no-judge warning') plus the surrounding sequence (workflow_test_run, fix until clean, then workflow_save_version). The refusal condition ('refused while your own trial runs') is an explicit when-not.

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

All Spaces by Peakflo tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.