Kellian

Prepare 1–50 unsigned EIP-712 limit-order payloads without placing them

kellian_batch_prepare_orders

Prepare 1–50 unsigned EIP-712 orders in one request; this creates signing payloads only and accepts nothing into matching.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "orders": "<orders>",
      "walletAddress": "<walletAddress>",
      "idempotencyKey": "<idempotencyKey>",
      "walletSignature": "<walletSignature>",
      "signatureTimestamp": "<signatureTimestamp>",
      "proofNonce": "<proofNonce>"
    },
    "name": "kellian_batch_prepare_orders"
  }
}

Input Schema

Name	Required	Description
`orders`	Yes
`proofNonce`	Yes	Required single-use nonce for the wallet proof. Fetch from POST /api/auth/nonce; consumed on verification so the proof cannot be replayed.
`walletAddress`	Yes	Checksummed or lowercase 20-byte EVM address (0x + 40 hex).
`idempotencyKey`	Yes
`walletSignature`	Yes	Action-bound wallet proof. Sign the canonical 'problee-mcp-auth:…' challenge (binds agent, apiKey, tool, scope, chain, resource, payloadHash, nonce, timestamp).
`signatureTimestamp`	Yes	Unix timestamp (seconds) used in the signed challenge message

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 5, 2026

TDQS

A3.5/5.0

Behavior3/5

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

The description usefully discloses the crucial non-effect ('accepts nothing into matching'), which is real context beyond the annotations and consistent with destructiveHint=false and idempotentHint=false. What it omits: that proofNonce and idempotencyKey are consumed/single-use, that supplying orderSignature inline turns this into a submission, and what repeats do — meaningfully more than the annotations alone but far from complete for a 6-param authenticated call.

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?

One front-loaded sentence, no redundancy, and the batch-size bound plus the non-placement guarantee are the two facts an agent needs first. Nothing is wasted.

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

Completeness3/5

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

An output schema exists and the input schema is unusually rich, so return values and field semantics need no repetition. However, for an authenticated batch prepare step that feeds a placement sibling, the description leaves the end-to-end workflow and the signature/nonce lifecycle 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?

The description introduces no parameter-level information at all; the schema (67% coverage) and the deeply documented nested order object carry the entire burden. Baseline 3 applies because the structured schema already explains price grids, decimals, and clOrdId semantics in far more detail than the description does.

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?

States a specific verb and resource ('Prepare 1–50 unsigned EIP-712 orders in one request') with an explicit scope ceiling of 50, and the clause 'creates signing payloads only and accepts nothing into matching' implicitly separates it from the placement sibling. It stops short of naming kellian_batch_place_orders, so the differentiation is inferential rather than explicit.

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

Usage Guidelines3/5

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

The 'payloads only' framing implies this is the pre-signing step in a two-step flow, so usage is inferable, but there is no explicit 'use this before X, use Y instead to submit' routing. Nothing tells the agent what to do with the returned payloads or which sibling completes the flow.

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

All Kellian 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.

Resources

Need Help?