ChainHelix for Machines

hire_plan_healthmon

Plan a hire of the ChainHelix healthmon agent (ERC-8004 #269228, Position health report). Lending health: given collateral rows with liquidation thresholds, debt and prices, returns the health factor, its status (healthy, warning, critical, liquidatable) and per-asset liquidation prices with drop distances. LP range health: send position {price, lowerPrice, upperPrice} instead of collateral and debt. One question per job. Deterministic arithmetic, no custody, no execution. Send the job parameters; you get back the agent's live wallet-signed quote (the job price, paid into escrow on chain when you fund) and the createJob calldata to sign from YOUR wallet, then fund and tell the agent (steps in the answer). This call is free; the job is not. The parameters here are exactly what the agent accepts; the same schema is on its agent card at https://agents.chainhelix.io/healthmon/.well-known/agent-card.json. Example: {"collateral":{"ETH":{"amount":10,"liqThreshold":0.8}},"debt":{"USDT":10000},"prices":{"ETH":2000,"USDT":1}}

Input Schema

TableJSON Schema

Name	Required	Description
`debt`	No	outstanding debt per symbol; required unless `position` is sent (also accepted as: debts, borrowed, borrows, loans)
`terms`	No	optional ERC-8183 terms {deliverables, quality_standards}; the agent quotes its fixed price either way
`walls`	No	with position only: strong levels keyed by price, each range edge is annotated with the nearest one
`prices`	No	a mark for every collateral and debt symbol (also accepted as: marks, quotes, pricesUsd)
`alertHF`	No	warning level, default 1.5
`position`	No	PancakeSwap v3 LP range health instead of lending health (do not send with collateral or debt); optional nearEdgePct, feesEarnedUsd, positionValueUsd, ageDays; returns range status, distance to each edge, position inside the band and the fee run-rate (also accepted as: lpPosition, range)
`collateral`	No	liqThreshold in (0, 1]; required unless `position` is sent (also accepted as: collaterals, supplied, deposits)
`criticalHF`	No	critical level, must be below alertHF, default 1.1

Output Schema

TableJSON Schema

Name	Required	Description	Default
`tx`	No
`next`	No
`plan`	No
`agent`	Yes
`error`	No
`example`	No
`missing`	No
`envelope`	No
`expected`	No
`erc8004Id`	No

Schema Changelog

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

Changed2 schema fields changedSep 5, 2026

addedInput schema / anyOf

Added value: +[
+  {
+    "required": [
+      "collateral",
+      "debt",
+      "prices"
+    ]
+  },
+  {
+    "required": [
+      "position"
+    ]
+  }
+]

changedInput schema / description

Previous value: -"Required: collateral, debt, prices. Each property description lists the other names accepted for it. Example: {\"collateral\":{\"ETH\":{\"amount\":10,\"liqThreshold\":0.8}},\"debt\":{\"USDT\":10000},\"prices\":{\"ETH\":2000,\"USDT\":1}}"New value: +"Required: . Each property description lists the other names accepted for it. Example: {\"collateral\":{\"ETH\":{\"amount\":10,\"liqThreshold\":0.8}},\"debt\":{\"USDT\":10000},\"prices\":{\"ETH\":2000,\"USDT\":1}}"

AddedSep 5, 2026

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations provided, the description fully shoulders the responsibility of behavioral disclosure. It states 'no custody, no execution,' separates the free call from the paid job, and explains the wallet-signed quote, escrow payment, and the createJob calldata signing/funding workflow. This is excellent transparency for a tool that triggers on-chain activity.

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 longer than average, but every sentence earns its place: purpose, modes, acceptable inputs, behavioral safety, cost, workflow, reference URL, and an example. It is well organized and front-loads the core action while keeping the necessary operational details.

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

Completeness5/5

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

An output schema is present, so the description does not need to detail return shapes. It covers the full invocation lifecycle: send parameters, receive quote and calldata, sign from YOUR wallet, fund, and notify the agent. The official agent-card URL and the free-call/paid-job distinction make the context complete.

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?

The schema already provides 100% property coverage with aliases and defaults, so the description does not need to repeat every field. It adds value with a concrete JSON example, the relation between the modes and their parameters, and a link to the agent card confirming the schema is exactly what the agent accepts.

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 states the tool's job: plan a hire of the ChainHelix healthmon agent for health reporting. It explicitly distinguishes the two supported modes (lending health and LP range health), so an agent can immediately understand what this tool does and differentiate it from sibling hire_plan tools.

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 gives clear in-tool routing: send collateral/debt/prices for lending health, or send position for LP range health, and notes 'one question per job.' It does not explicitly contrast this with sibling tools like hire_plan_gridtrader, but the purpose and mode selection are clear enough for correct use.

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

All ChainHelix for Machines tools Inspect

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.

Resources

Need Help?