Skip to main content
Glama

pre_trade_bundle

Read-onlyIdempotent

Five pre-trade checks, one GO / HOLD / STOP — Runs pre-trade-gate (risk, sellability, route, deployer), b20-gate (seize/freeze/pause; N/A for non-B20 tokens), owner-powers and dump-risk in parallel on a Base token, with clanker-token-audit as provenance that never moves the verdict. Returns GO/HOLD/STOP, what each check saw, an unverified list, a max size held to 2% impact on the exit-liquidity read, and a receipt. GO only if every applicable check ran clean; if a gating check could not run there is no GO and no charge. Required input: address. Priced $0.15 per call over x402 on Base; send a prepaid x-credit-token header for unlimited calls (no free tier on this tool). No API key required.

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": {
      "address": "<address>"
    },
    "name": "pre_trade_bundle"
  }
}

Input Schema

NameRequiredDescriptionDefault
sellNoToken to spend on the attached buy (optional, default USDC)
takerNoYour wallet — on GO, attaches a ready-to-sign buy (optional)
amountNoExact amount of the sell token to spend (optional)
addressYesToken contract address
slippageNoSlippage for the attached buy, bps (optional, default 100)
amountUsdNoTrade size in USD (optional)

Output Schema

NameRequiredDescriptionDefault
dataNoThe result payload. Shape is service-specific; every field is documented in the tool description.
serviceNoThe service id that answered.
checkedAtNoISO-8601 timestamp of when the underlying reads were taken.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / amount
      Added value: +{
      +  "description": "Exact amount of the sell token to spend (optional)",
      +  "type": "string"
      +}
    • addedInput schema / properties / sell
      Added value: +{
      +  "description": "Token to spend on the attached buy (optional, default USDC)",
      +  "type": "string"
      +}
    • addedInput schema / properties / slippage
      Added value: +{
      +  "description": "Slippage for the attached buy, bps (optional, default 100)",
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / taker
      Added value: +{
      +  "description": "Your wallet — on GO, attaches a ready-to-sign buy (optional)",
      +  "type": "string"
      +}
  3. Added
  4. Removed
  5. Added

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses pricing and auth mechanics ($0.15 via x402 on Base, no free tier, prepaid x-credit-token header for unlimited calls, no API key), the verdict rule (GO only if every applicable check ran clean), the no-charge fail case, and that clanker-token-audit is provenance that never moves the verdict. It also notes the size cap is held to 2% impact on the exit-liquidity read — genuinely non-obvious behavior.

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?

The verdict is front-loaded in the first clause and almost every sentence carries distinct information (verdict logic, N/A handling, pricing, required input). It is a dense, semicolon-chained block rather than a list, which costs some scannability, but there is no filler.

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 high-complexity composite tool, the definition covers composition, verdict semantics, failure/pricing behavior, provenance treatment, and auth model, and an output schema exists so return values need not be expanded further. Nothing an agent needs to decide to call it or interpret GO/HOLD/STOP 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 coverage is 100%, so all six parameters already carry descriptions and the baseline is 3. The description adds only the required-input reminder (address) and implied meaning for the optional buy attachment via the 2%-impact sizing note; it does not clarify sell/taker/amount/slippage interactions beyond what the schema states.

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 names the exact composite operation — five named checks (pre-trade-gate, b20-gate, owner-powers, dump-risk, clanker-token-audit) run in parallel on a Base token — and states the output shape (GO/HOLD/STOP). An agent can distinguish this bundle from the individual gate siblings without opening any schema.

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?

Usage is implied by the composition (this is the bundle of the individual checks) and one conditional is explicit (b20-gate is N/A for non-B20 tokens; no GO if a gating check could not run). However, there is no direct routing against alternatives such as near_pre_trade_gate or pre_trade_gate — the definition never says when an agent should prefer the single-check tool over the bundle, leaving that to inference.

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