Skip to main content
Glama

ArcHive

arc_bounty_prepare_create

Creates a sealed bounty, with a predicate helper ("the USDC balance of the target contract drops by at least minDrop" → ERC20_DROP clause), tiers, fees read on-chain, createBounty parameters and an EIP-3009 authorization. PREPARES only: signs and sends nothing, returns the data the user signs in their wallet.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "arc_bounty_prepare_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNo
fromNothe protocol's wallet, which funds and signs
tiersNoseveral tiers [{ minLoss, amount }] in USDC
tokenNo
rewardNothe hunter's reward in USDC (one tier)
targetNowatched contract (e.g. the protocol's vault)
fundingNoinitial funding in USDC (default: one payment of the highest tier, fees included)
minDropNominimum drop that proves the exploit, in USDC
predicateNofull predicate { combine, clauses } (advanced)
productIdNothe Sealed Bounty product (default: the open level's); arc_bounties names the products of each level
singleCapNo
clauseTypeNo
deadlineDaysNo
targetToPauseNo
protocolX25519Nothe protocol's PUBLIC X25519 key (never the private one)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / productId / description
      Added value: +"the Sealed Bounty product (default: the open level's); arc_bounties names the products of each level"
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose the most consequential trait: nothing is signed or sent, so there are no on-chain side effects, and the output is a signable payload. It also notes that fees are read on-chain, hinting at external reads. It omits auth/API-key requirements, failure modes, and whether repeated calls are idempotent.

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?

Two sentences, front-loaded with the action and its payload, then the critical "PREPARES only" constraint in caps so it is not missed. The parenthetical example is slightly dense but earns its place by making the predicate mapping concrete; no filler sentences.

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 15-parameter builder with nested objects, zero annotations and no output schema, the definition supplies the essentials: what is assembled, that fees are read on-chain, that nothing is transmitted, and that the return value is a user-signable payload. What remains unspecified are mutually exclusive parameter combinations (tiers vs. reward vs. full predicate), which is a completeness gap for a tool with 0 required parameters.

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?

Schema coverage is 60% across 15 params, and the description adds real meaning by explaining the construction relationship: minDrop/target collapse into an ERC20_DROP clause via a "predicate helper," while the full { combine, clauses } object is available as the advanced path. That clarifies how the simple and advanced parameters relate, something the schema does not state. Parameters such as k, token, singleCap, deadlineDays, targetToPause and protocolX25519 get no mention in either place.

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 ("Creates a sealed bounty") and enumerates what the payload contains: predicate helper/clause, tiers, on-chain fees, createBounty parameters, EIP-3009 authorization. The "PREPARES only" clarification resolves the tension between the tool name and the word "creates" so the agent understands it is constructing data, not minting a bounty on-chain. It does not explicitly differentiate itself from prepare-style siblings like arc_operator_prepare_bond.

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 rather than stated: "PREPARES only: signs and sends nothing, returns the data the user signs in their wallet" tells the agent this is a pre-signing step that must be followed by a wallet signature. There is no explicit when-to-use/when-not, no named alternative (e.g., raw predicate object vs. helper), and no prerequisite conditions.

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.