Skip to main content
Glama
Smart Quota Orchestrator

Smart Quota Orchestrator

by ElNeMeR70

sqo_council_review

Audits code from four adversarial senior perspectives—exploit races, SRE timeouts/swallowed exceptions, UX, and minimalism—to surface risks before PR review at no extra LLM token cost.

Instructions

4-Persona Adversarial Engineering Council (v12.0 Quantum): audits code from 4 senior seats (Exploit Hunter TOCTOU race conditions, 3 AM SRE missing HTTP timeouts & swallowed exceptions, UX Critic, Karpathy Minimalist) with 0 extra LLM token cost!

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": {
      "workspace": "<workspace>"
    },
    "name": "sqo_council_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
workspaceYesWorkspace root directory.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv13.0.0

TDQS

C2.8/5.0
Behavior2/5

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

With no annotations, the description carries the full burden. It does not say whether the audit is read-only or writes files/reports, whether the workspace root is scanned recursively, how long it takes, or how findings are surfaced. The '0 extra LLM token cost' claim is a performance/marketing assertion rather than operational guidance an agent can act on.

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 front-loaded sentence, which is good, but a large share of the text is branding and sales copy ('v12.0 Quantum', '0 extra LLM token cost!') that does not help an agent decide or invoke. The persona list earns its place; the version tag and cost exclamation do not.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an audit tool that takes a whole workspace root, there is no output schema and no description of what comes back (findings list? severity? per-persona sections?), no side-effect disclosure, and no scope boundaries. The definition is materially incomplete for correct invocation and result interpretation.

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?

There is exactly one required parameter (`workspace`), and the schema already documents it at 100% coverage as the workspace root directory. The description adds no syntax, scope, or behavioral nuance about that directory (e.g., whether subtrees or generated files are included), so the baseline of 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?

Names a specific verb+resource ('audits code') and characterizes the operation concretely by enumerating the four review personas and what each hunts for (TOCTOU races, missing HTTP timeouts, swallowed exceptions). An agent can tell this apart from a generic PR review, though it never names or contrasts with any sibling tool.

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

Usage Guidelines2/5

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

There is no statement of when to choose this over sqo_pr_review or the other review-oriented siblings, nor any prerequisite, scope limit, or exclusion. The only hint is the persona framing, which implies 'broad adversarial audit' but leaves the selection decision to inference.

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