Skip to main content
Glama

Quesen Deterministic Agent Decision Layer

by io.github.Shxnque

quesen.validate

Deterministic pre-decision risk validation for autonomous agents. Returns PROCEED / REVIEW / SKIP plus risk_score, confidence, and named conflict triggers. Same input -> same output; every response embeds engine_version + weights + thresholds for full replay.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
domain_age_daysNoAge of the target domain in days.
engagement_ratioNoEngagement ratio in [0, 1].
client_request_idNoOptional caller-side trace id (echoed in response).
scam_keyword_countNoCount of known scam keywords detected.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden. It discloses determinism ('Same input -> same output'), replayability via embedded engine_version/weights/thresholds, and the nature of outputs. It does not explicitly state side effects, but 'validation' strongly implies a read-only operation.

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

Conciseness5/5

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

Two tight sentences front-load the core purpose and then provide deterministic/replay guarantees. Every sentence adds distinct information, with no filler or repetition.

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?

The description sufficiently explains what the tool returns given there is no output schema: the decision, risk score, confidence, conflict triggers, and replay metadata. It does not cover error behavior or exact response structure, but for a validation tool with all-optional parameters this is a minor gap.

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 100%, so the schema fully documents all four parameters. The description adds no parameter-level meaning, which is acceptable but not value-adding; baseline 3 applies.

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?

Description states a clear purpose: deterministic pre-decision risk validation. It also specifies the exact output categories (PROCEED / REVIEW / SKIP) and supporting signals, which differentiates it from siblings like health, report, simulate, and version.

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

Usage Guidelines4/5

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

The phrase 'pre-decision risk validation for autonomous agents' gives a clear usage context: call before making a decision. It does not explicitly name alternatives or when not to use the tool, but the context is strong enough to guide selection.

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

All Quesen Deterministic Agent Decision Layer toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation5/5

Each tool has a clearly distinct role: health for liveness, validate for pre-decision risk, report for post-decision feedback, simulate for counterfactual scoring, and version for configuration. Even the minor overlap between health and version is resolved by their descriptions (liveness probe vs. full config).

Naming Consistency4/5

All tools share a consistent 'quesen.' prefix and lowercase single-word naming, which is predictable. However, the suffix words are not uniformly verbs or nouns (health, version vs. validate, simulate), so the semantic pattern is mildly inconsistent.

Tool Count5/5

Five tools is well-scoped for a decision-layer server. Each tool covers a distinct core concern without redundancy or excessive surface area.

Completeness4/5

The set covers the core decision lifecycle: validate pre-decision, report post-decision, simulate counterfactuals, and inspect configuration. The main minor gap is that aggregated report results are described but there is no tool to retrieve them.

Resources