Skip to main content
Glama
Sign In

ChainHelix for Machines

by io.chainhelix.mcp
OverviewDiscussionsAdmin

hire_plan_gridtrader

Read-only

Plan a hire of the ChainHelix gridtrader agent (ERC-8004 #269224, Grid trading ladder). Given a mark price and a budget, returns a symmetric buy/sell grid: buy levels below the price, sell levels above, equal USD size per level, and when strong price walls are supplied each level is annotated with its nearest wall and flagged if it sits on one. Deterministic arithmetic, no custody, no execution. Not a bounded-loss or profit-target strategy: fees, slippage, gas and PnL are not computed. 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; an example is in the input schema description.

Input Schema

NameRequiredDescriptionDefault
lowerNogrid lower bound in price; with upper, an alternative to spanPct
priceNocurrent mark price (also accepted as: mid, midPrice, mark, markPrice, currentPrice, spot)
termsNooptional ERC-8183 terms {deliverables, quality_standards}; the agent quotes its fixed price either way
upperNogrid upper bound in price; with lower, an alternative to spanPct
wallsNoknown support/resistance walls keyed by price, touches is an integer 1 to 10000; levels on a wall are flagged
levelsNogrid lines per side, default 5 (also accepted as: gridLevels, nLevels)
spanPctNohalf-width of the grid in percent, below 100, default 5; or send lower and upper (absolute bounds) and the half-width is derived from the wider side (also accepted as: rangePct, widthPct)
budgetUsdNototal capital to ladder (also accepted as: capitalUsd, budget, capital, notionalUsd, sizeUsd)
wallBandPctNodistance in percent that counts as on a wall, default 0.7

Output Schema

NameRequiredDescriptionDefault
txNo
nextNo
planNo
agentYes
errorNo
exampleNo
missingNo
envelopeNo
expectedNo
erc8004IdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / x-lexicon / bundleSha256
      Previous value: -"670f7504e3de5031beccee25a2d24e4515f68b893295f6d5b0d3a0665498b2c9"New value: +"25cc80db6d8e9eac73d47a50f7ad6333a21f1972d008a8fed0159de8bfb4b519"
  2. Changed2 schema fields changed
    • changedInput schema / x-lexicon / bundleSha256
      Previous value: -"e5b4290024a229f2bdf97f8fc6a0079c3fe13b77267f41fdcffeb8b26aa1c41e"New value: +"670f7504e3de5031beccee25a2d24e4515f68b893295f6d5b0d3a0665498b2c9"
    • changedInput schema / x-lexicon / version
      Previous value: -"0.1.0"New value: +"0.2.0"
  3. Changed1 schema field changed
    • changedInput schema / x-lexicon / bundleSha256
      Previous value: -"a1c2e10fd3177d6b4d59ca78693e8fb36880165cf0f735f680dd86a510411178"New value: +"e5b4290024a229f2bdf97f8fc6a0079c3fe13b77267f41fdcffeb8b26aa1c41e"
  4. Changed1 schema field changed
    • changedInput schema / x-lexicon / bundleSha256
      Previous value: -"1eeb782ee15fe69fc80776948e0556fa6b795e210e6305935b2c97b73d955cda"New value: +"a1c2e10fd3177d6b4d59ca78693e8fb36880165cf0f735f680dd86a510411178"
  5. Changed1 schema field changed
    • changedInput schema / x-lexicon / bundleSha256
      Previous value: -"c014292cad7497ce9fd68c33345ac32cb42b672c8e77d6c749c26e162cc207e4"New value: +"1eeb782ee15fe69fc80776948e0556fa6b795e210e6305935b2c97b73d955cda"
  6. Changed3 schema fields changed
    • addedInput schema / x-aliases
      Added value: +{
+  "budgetUsd": [
+    "budget_usd",
+    "capitalUsd",
+    "budget",
+    "capital",
+    "notionalUsd",
+    "sizeUsd"
+  ],
+  "levels": [
+    "gridLevels",
+    "nLevels"
+  ],
+  "price": [
+    "px",
+    "Price",
+    "_price",
+    "mid",
+    "midPrice",
+    "mark",
+    "markPrice",
+    "currentPrice",
+    "spot"
+  ],
+  "spanPct": [
+    "rangePct",
+    "widthPct"
+  ]
+}
    • addedInput schema / x-lexicon
      Added value: +{
+  "bundleSha256": "c014292cad7497ce9fd68c33345ac32cb42b672c8e77d6c749c26e162cc207e4",
+  "name": "ChainHelix Agentic Lexicon",
+  "resolve": "lexicon_resolve",
+  "spec": "lexicon_spec",
+  "version": "0.1.0"
+}
    • addedInput schema / x-vocab
      Added value: +{
+  "budgetUsd": "agent.budgetUsd",
+  "levels": "market.levels",
+  "lower": "market.lower",
+  "price": "market.priceApi",
+  "spanPct": "market.spanPct",
+  "terms": "data.terms",
+  "upper": "market.upper",
+  "wallBandPct": "market.wallBandPct",
+  "walls": "market.walls"
+}
  7. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations declare readOnlyHint=true, and the description is consistent and additive: 'Deterministic arithmetic, no custody, no execution' explains why the call is read-only, while disclosing the downstream flow (wallet-signed quote, escrow funding, createJob calldata to sign from the caller's wallet) and the cost boundary. That is exactly the extra context annotations cannot carry for a planning tool that fronts an on-chain hire.

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?

Front-loaded with the capability and output shape, then layering the caveats and the hire flow in a sensible order. It is dense and runs long for a single description, but nearly every sentence carries non-redundant information (scope, exclusions, cost, calldata handoff), with only minor repetition around the free/paid distinction.

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?

For a 9-parameter tool with nested objects and a single readOnlyHint annotation, the description supplies what the structured fields cannot: the computational model, what is deliberately not computed, the settlement flow, and the caller's responsibility to sign from their own wallet. An output schema exists, yet the description still usefully sketches the return (live quote plus createJob calldata), leaving nothing an agent needs to call it correctly unstated.

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% and every property already documents defaults, ranges, aliases and the spanPct-vs-lower/upper interaction, so the structured data does the heavy lifting. The description adds only a framing note ('The parameters here are exactly what the agent accepts') and points to the example rather than restating field semantics, which matches the baseline-3 case for high-coverage schemas.

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?

States a specific verb and resource ('Plan a hire of the ChainHelix gridtrader agent') and immediately pins down the output shape: a symmetric buy/sell grid with buy levels below and sell levels above the mark price, equal USD size per level. Naming the agent identity (ERC-8004 #269224, Grid trading ladder) distinguishes it from the sibling hire_plan_healthmon/rebalancer/yieldopt tools without the agent needing to open their schemas.

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?

Clearly frames the use case and explicitly excludes adjacent intent with 'Not a bounded-loss or profit-target strategy: fees, slippage, gas and PnL are not computed,' which keeps the agent from hiring this planner for risk-managed strategies. It also sets the free-vs-paid expectation ('This call is free; the job is not'). It stops short of naming the sibling planners as alternatives for those excluded cases, so routing is implied rather than explicit.

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 toolsInspect
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.

Resources