Skip to main content
Glama

Hermes Plant — Agent Commerce Assurance

by io.github.JesseGdotIO

Action Safety - one-cent preflight

action_safety_quick_gate
Idempotent

AI agent action safety quick gate ($0.01 over x402 or free-tier quota). Deterministically scores a consequential action and returns the exact next call: proceed, request full DestructGuard evidence, or run the complete Action Safety workflow.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoWorking directory or execution context
repoNoRepository or project context
actorNoAgent or tool requesting the action
payerNoOptional wallet/account identifier; stored only as a hash
apiKeyNoFree-tier / plan API key (hp_free_… or a pass key). Forwarded as X-API-Key so paid tools serve from your monthly quota with NO x402 wallet. Get a free key (250 calls/mo) at https://hermesplant.com/pricing.
branchNoBranch or environment context
intentNoWhy the action is being requested
channelNoDiscovery channel or source tag
commandYesShell, SQL, Git, deploy, or infrastructure action to preflight
campaignNoCampaign tag for downstream telemetry
diffStatNoOptional git diff --stat or change summary
xPaymentNoRaw X-PAYMENT proof from an x402-compatible wallet/client
actorTypeNoCaller type for analytics: agent, human, synthetic, system, or unknown
syntheticNoMark this paid retry as an internal test/probe for analytics exclusion
paymentSignatureNox402 payment proof to forward as PAYMENT-SIGNATURE and X-PAYMENT on retry
paymentIdentifierNoOptional x402 payment identifier for idempotency/retry correlation

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYesTrue when the upstream storefront call returned a 2xx response
httpStatusYesUpstream HTTP status code
paymentRequiredNoTrue when the response is an x402 HTTP 402 payment challenge

TDQS

A4.2/5.0
Behavior4/5

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

The description adds useful behavioral context beyond annotations: determinism, cost, and the three decision outcomes. Annotations already declare idempotentHint=true and destructiveHint=false, and the description aligns with these, so there is no contradiction.

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?

The description is two sentences: the first front-loads cost and purpose, the second defines deterministic behavior and decision outputs. Every word earns its place; no filler or redundancy.

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 (16 params) and the presence of an output schema, the description adequately conveys cost, determinism, and the three decision branches. It could explicitly state that no action is executed, but 'preflight' and 'scores' make this sufficiently clear.

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 structured parameter descriptions already document all 16 parameters. The tool description adds no extra parameter-level semantics, which is acceptable given the schema's completeness.

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 specifies a concrete action: deterministically score a consequential action and return the exact next call (proceed, request full DestructGuard evidence, or run the complete Action Safety workflow). It clearly identifies the tool as a cheap preflight gate and differentiates it from the full Action Safety workflow.

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 establishes clear usage context through cost ('$0.01 over x402 or free-tier quota') and role ('quick gate', 'preflight'), implying it should be used before committing to expensive/full workflows. However, it does not explicitly name sibling alternatives or state when not to use it, so it lacks full alternative guidance.

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

All Hermes Plant — Agent Commerce Assurance 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

A3.6/5.0
Disambiguation4/5

Most tools have clearly distinct purposes. Some overlap exists (e.g., dealanalyzer_analyze combines CashflowLens and WaterfallLens; action_safety_run includes DestructGuard evidence), but descriptions explicitly clarify scope so an agent can choose correctly.

Naming Consistency2/5

Naming patterns are mixed: some verbs precede nouns (get_product, purchase_with_x402), others follow nouns (bond_analyze, portfolioguard_score), and some are multi-word (action_safety_quick_gate). This inconsistency makes tool selection less predictable.

Tool Count3/5

At 25 tools, the server is at the heavy end and spans diverse subdomains (safety, payments, financial analytics, storefront). While each tool serves a purpose, the broad scope makes it feel overloaded for a single server.

Completeness3/5

Core assurance workflows (safety, payment, verification) are covered, but gaps exist: no refund/cancellation tools, no attestation lookup, and no way to retrieve 30-day action-safety status records. Financial analytics also have limited coverage (no equities).

Resources