Skip to main content
Glama

Quesen Deterministic Agent Decision Layer

by io.github.Shxnque

quesen.report

Post-decision outcome feedback. Accepts request_id + outcome (RUG/LOSS/OK/WIN/UNKNOWN) plus optional post-trade metadata. Aggregated deterministically for SKIP-rate vs realized-outcome correlation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
notesNoOptional free-text notes about the outcome (post-mortem, context, references). Stored verbatim for audit.
venueNoVenue or platform where the trade/signal was executed (e.g. 'raydium', 'jupiter', 'uniswap-v3'). Free-form label for downstream grouping.
outcomeYesReal-world outcome once known. RUG = rug-pull / total loss; LOSS = negative PnL; OK = neutral / no material result; WIN = positive PnL; UNKNOWN = outcome not yet observable.
request_idYesThe `request_id` returned by a prior quesen.validate call. Ties the reported outcome back to the exact decision that produced it.
signal_hashNoOptional hash/fingerprint of the original signal (URL, token address, message id) so outcomes can be joined across systems that don't share Quesen request_ids.
realized_pnlNoRealized profit/loss in the caller's chosen unit (e.g. USD, SOL, ETH). Sign convention: positive = profit, negative = loss. Fed into the aggregate `pnl_mean` counter.
elapsed_secondsNoSeconds elapsed between the original quesen.validate decision and the observation of this outcome. Non-negative.
client_request_idNoOptional caller-side trace id. Echoed verbatim in the response for cross-system correlation.

Schema Changelog

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

  1. Changed8 schema fields changed
    • addedInput schema / properties / client_request_id / description
      Added value: +"Optional caller-side trace id. Echoed verbatim in the response for cross-system correlation."
    • addedInput schema / properties / elapsed_seconds / description
      Added value: +"Seconds elapsed between the original quesen.validate decision and the observation of this outcome. Non-negative."
    • addedInput schema / properties / notes / description
      Added value: +"Optional free-text notes about the outcome (post-mortem, context, references). Stored verbatim for audit."
    • addedInput schema / properties / outcome / description
      Added value: +"Real-world outcome once known. RUG = rug-pull / total loss; LOSS = negative PnL; OK = neutral / no material result; WIN = positive PnL; UNKNOWN = outcome not yet observable."
    • addedInput schema / properties / realized_pnl / description
      Added value: +"Realized profit/loss in the caller's chosen unit (e.g. USD, SOL, ETH). Sign convention: positive = profit, negative = loss. Fed into the aggregate `pnl_mean` counter."
    • addedInput schema / properties / request_id / description
      Added value: +"The `request_id` returned by a prior quesen.validate call. Ties the reported outcome back to the exact decision that produced it."
    • addedInput schema / properties / signal_hash / description
      Added value: +"Optional hash/fingerprint of the original signal (URL, token address, message id) so outcomes can be joined across systems that don't share Quesen request_ids."
    • addedInput schema / properties / venue / description
      Added value: +"Venue or platform where the trade/signal was executed (e.g. 'raydium', 'jupiter', 'uniswap-v3'). Free-form label for downstream grouping."
  2. First observed

TDQS

A3.6/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states 'Aggregated deterministically for SKIP-rate vs realized-outcome correlation', which hints at deterministic processing, but it doesn't disclose whether the call is idempotent, reversible, or what happens on duplicate submissions. For a write-operation tool (posting outcome feedback), missing information about side effects, idempotency, and error handling is a significant gap. The description is too thin on behavioral traits.

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?

The description is two sentences, tightly written, with the essential purpose front-loaded. The first sentence states what it does and what it accepts; the second mentions the deterministic aggregation purpose. Every sentence contributes value with no filler. It could arguably be split into a structured list for the outcome enum, but it remains concise and readable.

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

Completeness3/5

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

For a tool with 8 parameters and no output schema, the description adequately covers the core purpose but omits workflow context beyond what the schema provides (e.g., the dependency on a prior quesen.validate call is only in the schema, not the description). It also doesn't mention error scenarios or return behavior. Given the schema covers parameter semantics thoroughly, the description is acceptable but not comprehensive. A bit more workflow guidance would improve it.

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 already documents all 8 parameters, including the outcome enum values and the requirement that request_id come from a prior quesen.validate call. The description adds a little context by mentioning the aggregation correlation (linking outcome and realized_pnl), but it doesn't provide meaningful semantics beyond what the schema already states. Baseline 3 is appropriate given high coverage.

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 'Post-decision outcome feedback', which clearly states the verb and resource (reporting outcomes after a decision). It explicitly lists the required inputs (request_id + outcome) and the accepted outcome enum, which distinguishes it from siblings like quesen.validate (which produces decisions) and quesen.simulate (which predicts outcomes). The purpose is unambiguous and specific.

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 'Post-decision outcome feedback' clearly implies the tool is used after a decision has been made and the outcome is known, which is a clear context. It doesn't explicitly name alternatives or exclusions, but the sibling tool names (validate, simulate) make the use case obvious without needing explicit 'when not to use' statements. The absence of explicit alternatives is a minor gap, but the context is clear enough for an agent to select it correctly.

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