Skip to main content
Glama
Sign In

Human Creative AI Workflow & Eval Lab

by io.github.jdurey
OverviewDiscussionsAdmin

audit_workflow_guardrails_50v

Runs a 50-vector multi-family prompt-injection, policy-bypass, and stem-withheld answer-leak stress test judged by 3 independent LLM vendor families, producing a hardened v2.0 system prompt and 300-DPI Executive Audit PDF ($199 Stripe / $2.50 x402 USDC, or set preview_mode=true for a free 5-vector Edge dry-run).

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": {
      "client_name": "<client_name>",
      "bot_or_workflow_name": "<bot_or_workflow_name>",
      "system_prompt_or_rules": "<system_prompt_or_rules>"
    },
    "name": "audit_workflow_guardrails_50v"
  }
}

Input Schema

NameRequiredDescriptionDefault
client_nameYesOrganization or product name.
preview_modeNoSet true for an instant free 5-vector Edge guardrail preview.
contact_emailNoDelivery email for the 50-vector PDF & JSON telemetry pack.
payment_tokenNoOptional Stripe or x402 payment token.
bot_or_workflow_nameYesTarget assistant, agent, or workflow name.
system_prompt_or_rulesYesCurrent system prompt, policy boundaries, or protected decision rules.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is covered. The description adds material context those annotations cannot convey: the run is a 3-vendor-family judged evaluation, pricing is $199 Stripe or $2.50 x402 USDC, artifacts include a v2.0 prompt plus a 300-DPI PDF and JSON telemetry, and a free preview path exists. It omits what happens to the submitted system prompt (retention) and expected latency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single sentence and the core purpose is front-loaded, which is good, but the sentence is overloaded with marketing qualifiers ("300-DPI Executive Audit PDF", "$199 Stripe / $2.50 x402 USDC") that make it dense and harder to parse than a short purpose sentence plus a separate delivery/cost sentence would be.

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?

With six parameters, no output schema, and no nested objects, the description does the heavy lifting of describing deliverables (hardened v2.0 prompt, PDF, JSON telemetry) and the free-versus-paid split, which is the main thing an agent needs. Remaining gaps are secondary operational details like runtime, prompt retention, and whether the PDF is emailed to contact_email.

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 coverage is 100%, so every one of the six parameters is already documented in the input schema, including preview_mode and its free-preview meaning. The description restates preview_mode and pricing but adds no new semantics for client_name, contact_email, payment_token, or system_prompt_or_rules, so the baseline 3 applies.

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 a specific verb and resource: a 50-vector prompt-injection/policy-bypass/answer-leak stress test with a hardened system prompt and audit PDF as output. It is clearly distinct from the sibling tools (diagnose, sandbox, rubric calibration, SOP compilation), though it never explicitly contrasts itself with any of them.

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?

It implies the usage path by offering preview_mode=true as a free 5-vector Edge dry-run versus the paid 50-vector full run, which is genuine selection guidance. However, it never says when this tool applies versus diagnose_ai_workflow or the judge-rubric sibling, and no prerequisites for the paid path are given.

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

All Human Creative AI Workflow & Eval Lab toolsInspect
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