TWZRD Agent Intelligence

low_level_preflight

Read-onlyIdempotent

Low-level preflight check. Returns a richer result object including
paid_quick_endpoint ($0.001 first hop) and optional paid_trust_endpoint ($0.05 V7).
wash_flagged=true never soft-allows. Unlabeled leftover 0.05 / leftover=0 is not a unit price.

Prefer get_readiness_card_tool for most callers. Use this when you need
max_spend_recommendation_usdc, full_report_hint, or the suggest_full_report
flag. The embedded `readiness_card` carries the SAME full shape as
get_readiness_card_tool (see the outputSchema).

Hard-stops:
  wash_flagged=true never soft-allows (decision=block; no warn/allow/quick).
  Unlabeled leftover 0.05 / leftover=0 is not a unit price; read readiness_card.price_kind.

Input Schema

TableJSON Schema

Name	Required	Description
`price_usdc`	No	Caller-supplied exact unit price in USDC. Leave unset unless you have an exact quote. Unlabeled leftover 0.05 / leftover=0 is not a unit price.
`agent_intent`	No	What the agent intends to do with the purchased response or tool.
`buyer_wallet`	No	Buyer's Solana wallet public key; enables buyer-context evidence in scoring.
`resource_url`	No	Canonical endpoint URL for the resource, if available.
`resource_name`	No	Provider or listing identifier to evaluate before payment.
`seller_wallet`	No	Seller's Solana wallet public key for reputation and spend checks.
`marketplace_score`	No	Optional marketplace-provided score (0-100) for blend-in scoring context.

Output Schema

TableJSON Schema

Name	Required	Description
`reason`	No	Decision-consistent one-line rationale.
`decision`	No	Spend decision: "allow" \| "warn" \| "block". wash_flagged=true never soft-allows — this field is block (no warn/allow/quick).
`evidence`	No	Evidence bullets behind the decision.
`trust_score`	No	Composite trust signal, 0-100.
`readiness_card`	No	The full ReadinessCard shape (same keys as get_readiness_card_tool).
`full_report_hint`	No	How to fetch the paid full report.
`paid_quick_endpoint`	No	First paid hop: $0.001 score-only teaser, if seller identity is known.
`paid_trust_endpoint`	No	Optional $0.05 V7 receipt path, if seller identity is known.
`suggest_full_report`	No	Whether to upsell the paid V7 receipt report.
`max_spend_recommendation_usdc`	No	Suggested per-call spend ceiling for this decision.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 2, 2026

changedOutput schema / properties / suggest_full_report / description

Previous value: -"Whether to upsell the paid v6-receipt report."New value: +"Whether to upsell the paid V7 receipt report."

Changed2 schema fields changedSep 18, 2026

addedOutput schema / properties / paid_quick_endpoint

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "First paid hop: $0.001 score-only teaser, if seller identity is known.",
+  "title": "Paid Quick Endpoint"
+}

changedOutput schema / properties / paid_trust_endpoint / description

Previous value: -"Paid trust endpoint path, if seller identity is known."New value: +"Optional $0.05 V7 receipt path, if seller identity is known."

Changed2 schema fields changedSep 12, 2026

changedInput schema / properties / price_usdc / description

Previous value: -"Quoted payment amount in USDC for this intended request."New value: +"Caller-supplied exact unit price in USDC. Leave unset unless you have an exact quote. Unlabeled leftover 0.05 / leftover=0 is not a unit price."

changedOutput schema / properties / decision / description

Previous value: -"Spend decision: \"allow\" | \"warn\" | \"block\"."New value: +"Spend decision: \"allow\" | \"warn\" | \"block\". wash_flagged=true never soft-allows — this field is block (no warn/allow/quick)."

First observedJul 11, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint, yet the description adds real behavioral context beyond them: hard-stop rules where wash_flagged=true forces decision=block with no warn/allow/quick path, and the pricing interpretation rule that an unlabeled leftover 0.05 / leftover=0 is not a unit price. Some of this is output-interpretation guidance rather than tool behavior, but the hard-stop semantics are genuinely additive.

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?

The opening leads with edge-case pricing jargon rather than a plain statement of purpose, which hurts front-loading. Content is also duplicated: 'wash_flagged=true never soft-allows' appears twice, and the 'Unlabeled leftover 0.05 / leftover=0' rule is restated in the body and again in the schema. The material earns its place but the redundancy and ordering cost it.

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?

An output schema exists and the description correctly points to it ('see the outputSchema') rather than re-documenting return values, and it flags that the embedded readiness_card has the SAME shape as the sibling tool. For a 7-parameter, zero-required evaluation tool this covers routing, hard-stops, and return structure adequately. It stops short of stating any required auth or wallet prerequisites.

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?

With 7 parameters at 100% schema description coverage, the schema already documents each field's meaning, so the baseline is 3. The description echoes one schema rule for price_usdc ('Unlabeled leftover 0.05 / leftover=0 is not a unit price') but adds no new per-parameter syntax or constraints beyond that. Credit is limited because the schema is doing the heavy lifting.

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 the tool as a 'Low-level preflight check' and immediately clarifies what it returns (a richer result object with paid_quick_endpoint / paid_trust_endpoint), so an agent can see this is a deeper evaluation pass. It distinguishes itself from the closest sibling by naming get_readiness_card_tool and the extra fields only this tool exposes. The core entity being preflighted (an x402 resource/seller before payment) is only inferable from the parameter names, not stated outright.

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

Usage Guidelines5/5

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

It explicitly routes callers: 'Prefer get_readiness_card_tool for most callers. Use this when you need max_spend_recommendation_usdc, full_report_hint, or the suggest_full_report flag.' That names the alternative and the exact conditions that select this tool over it. Nothing about when to reach for this versus the readiness card is left to inference.

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

All TWZRD Agent Intelligence tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.