Skip to main content
Glama

FaultKey · CausalLayer

by io.github.smq9sn5jck-cloud

evaluate_prospective_response

Deterministic prospective-evaluation gate (FK-METHOD-2026-006). Pass a ProposedAction BEFORE the agent delivers a response; receive one of three verdicts: 'allow', 'require_revision' (with specific factor-keyed directives), or 'block'. Uses the same four-factor engine that issues post-hoc certificates, so a single incident chains: prospective_pre_image -> response -> certificate -> anchor. This is a policy gate on structured action metadata, NOT a content safety classifier on raw prose. Thresholds are per-jurisdiction (EU strictest, US most permissive); read via GET /api/v2/gate/thresholds. Overrides are allowed but REQUIRE a governance rationale so the audit trail is complete. Cost: 1 credit. Pure deterministic.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesThe structured ProposedAction to evaluate.
overridesNoOptional per-call threshold override. Rationale REQUIRED for audit.

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden. It discloses several important behavioral traits: determinism, credit cost, per-jurisdiction thresholds, override requirements with governance rationale, and its relationship to the certificate engine. It could add more about error handling or exact return structure, but the provided details are substantive.

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?

Every sentence in the description carries meaningful information: method reference, usage timing, verdicts, engine linkage, exclusion, threshold access, override policy, cost, and determinism. It is front-loaded with the core purpose and contains no filler.

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?

Given the tool's complexity (nested action object, overrides) and absence of an output schema, the description covers the core aspects: what input is expected, what verdicts to expect, when to call, and governance constraints. It does not specify exact response structure, but the verdict list is sufficient for an agent to understand the contract.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and each property already has a description, so the baseline is 3. The tool description adds meaning beyond the schema by explaining that the 'action' parameter is a structured ProposedAction (not prose) and that 'overrides' require a governance rationale for audit. This enriches the schema's formal definitions.

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 clearly identifies the tool as a 'Deterministic prospective-evaluation gate' that evaluates a ProposedAction and returns one of three verdicts. It distinguishes itself from sibling verification tools by explicitly positioning it as a pre-response gate rather than a post-hoc certificate tool, and it clarifies it is not a content safety classifier.

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 description states clearly WHEN to use it: 'Pass a ProposedAction BEFORE the agent delivers a response.' It also provides exclusion guidance: 'NOT a content safety classifier on raw prose.' While it does not explicitly name alternative sibling tools, it gives enough context to infer appropriate use cases.

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

All FaultKey · CausalLayer 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

A4.2/5.0
Disambiguation4/5

Most tools have distinct purposes, but submit_incident and submit_otel_trace both create certificates from different input sources, and verify_certificate and verify_certificate_recompute both verify but via different methods. Descriptions and input types make them distinguishable, so ambiguity is low.

Naming Consistency4/5

All names use snake_case and generally follow a verb_noun pattern (e.g., submit_incident, verify_certificate). Deviations like verify_certificate_recompute (verb_noun_modifier) and evaluate_prospective_response (verb_adjective_noun) are minor and remain predictable.

Tool Count5/5

10 tools is well within the ideal 3-15 range and maps cleanly to the domain: incident submission, text extraction, pre-response gating, certificate verification, remediation simulation, jurisdiction analysis, and issuer/anchor metadata queries. Each tool serves a distinct workflow step without redundancy.

Completeness4/5

The core lifecycle (extract → submit → verify → analyze) is well covered. However, several tools reference external catalog endpoints (e.g., /jurisdiction/catalog, /remediation/catalog, /gate/thresholds) that are not exposed as MCP tools, forcing an agent to make separate HTTP calls to use these tools effectively. This is a minor workaround, not a critical gap.

Resources