Skip to main content
Glama

TWAP plan (dry run)

blazar_plan_twap
Read-onlyIdempotent

Dry-run TWAP planner: splits a swap into N slices every intervalSeconds and compares with one swap now (impact per slice, estimated gain in bps, schedule with min-out per slice). Never sends anything; build each slice with blazar_build_swap when it is due.

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": {
      "tokenIn": "<tokenIn>",
      "tokenOut": "<tokenOut>",
      "amount": "<amount>",
      "slices": "<slices>",
      "intervalSeconds": "<intervalSeconds>"
    },
    "name": "blazar_plan_twap"
  }
}

Input Schema

NameRequiredDescriptionDefault
amountYesAmount of tokenIn in HUMAN units, not wei: "1.5" = 1.5 POL, "250" = 250 BZB. Set amountIsBaseUnits=true to pass wei/base units instead.
slicesYesNumber of equal slices, 2-48.
tokenInYesToken to sell: symbol (POL, WPOL, BZB, USDC, USDT, WETH, WBTC) or its listed 0x address (see blazar_tokens). "POL" is the native gas token; WPOL is the ERC-20.
tokenOutYesToken to buy: symbol (POL, WPOL, BZB, USDC, USDT, WETH, WBTC) or its listed 0x address. Choose "POL" to receive native POL (auto-unwrapped).
slippageBpsNoPer-slice slippage for min-out. Default 50.
intervalSecondsYesSeconds between slices, 30-86400.
amountIsBaseUnitsNoIf true, amount is in base units (wei for 18-decimal tokens; 6 decimals for USDC). Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so 'Never sends anything' mainly reinforces that. The real added value is the disclosure of what the dry run returns — per-slice impact, estimated gain in bps, and a schedule with min-out per slice — which no annotation or output schema provides.

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?

Two sentences with zero padding: the dry-run nature and mechanics come first, the hand-off instruction second. Every clause either defines the computation or routes the agent.

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 seven-parameter, no-output-schema planning tool, the description covers what it computes, that it is non-executing, what the result contains, and the follow-up call. Nothing an agent needs in order to invoke it correctly is missing.

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 amount units, token symbols, slices range and intervalSeconds bounds are all already documented. The description's mentions of 'N slices every intervalSeconds' and 'min-out per slice' restate rather than extend the schema's own wording for slices, intervalSeconds and slippageBps.

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 ('Dry-run TWAP planner: splits a swap into N slices every intervalSeconds') plus the analytic comparison it performs against a single swap. This clearly separates it from blazar_build_swap, which the description positions as the execution counterpart.

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?

Gives a clear execution boundary ('Never sends anything; build each slice with blazar_build_swap when it is due'), which tells the agent exactly what to do after planning. It stops short of stating when-not to plan a TWAP at all (e.g., versus blazar_quote or blazar_compare_venues for single-swap sizing), so the alternative set is only partially covered.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources