Skip to main content
Glama

Agent swarm plan

agent_swarm_plan
Read-onlyIdempotent

Decompose a complex goal into a deterministic multi-agent DAG with exact BigInt micro-USDC split (zero rounding drift), verified x402 tool assignments, SHA-256 swarmManifestHash, and unsigned ERC-8183 G2 Jobs createJobWithTerms escrow calldata on Base or Arc. $0.004 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without payment for the terms, sign them with your own wallet, call again with payment.

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": {
      "goal": "<goal>"
    },
    "name": "agent_swarm_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalYesgoal description for the multi-agent swarm (6 to 400 chars)
chainNoescrow chain: base (default) or arc
paymentNoa signed x402 payment (the base64 payload you would put in PAYMENT-SIGNATURE). Pass it and the purchase completes inside this tool call.
workersNonumber of worker roles in DAG (2 to 6, default 3)
providerNooptional 0x lead worker address (defaults to zero address)
budgetUsdNototal USDC budget (0.01 to 10000, up to 6 decimals, default 0.05)
evaluatorNooptional 0x arbitrator address (or from) for ready-to-broadcast createJobWithTerms calldata
reviewHoursNoreview window in hours (1 to 168, default 24)
killFeePercentNokill fee percent on rejected work (0 to 25, default 0)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Well beyond the annotations, the description discloses price ($0.004 per call), accepted payment assets (USDC on Arc/Base/Solana, XNT on X1), the two-step signing flow, and the exact artifacts produced (DAG, manifest hash, unsigned calldata). It does not reconcile the fact that a purchase settles inside the call with the readOnlyHint=true annotation, nor does it say what happens if payment verification fails, which is the only real transparency gap.

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 output is front-loaded with the core capability in one dense sentence, followed by pricing and the invocation protocol, so the most important information comes first. It is jargon-heavy but every clause carries distinct information; a light edit could split the first sentence for readability.

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

Completeness4/5

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

For a 9-parameter, no-output-schema tool, the description covers what is produced (DAG, hash, unsigned calldata) and how payment works, which is the information an agent most needs before calling. It is slightly incomplete on failure/error behavior and on what the returned 'terms' payload contains, but the essential call-shaping context is present.

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 every parameter (goal, chain, payment, workers, provider, budgetUsd, evaluator, reviewHours, killFeePercent) is already documented in structured form. The description adds meaningful semantics only for `payment` by explaining the sign-then-resubmit lifecycle; the remaining params get no additional meaning from the prose. Baseline 3 applies with a small credit for the payment-flow context.

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 states a specific verb and a very concrete resource: 'Decompose a complex goal into a deterministic multi-agent DAG' with BigInt micro-USDC splitting, x402 tool assignments, a SHA-256 swarmManifestHash, and unsigned ERC-8183 createJobWithTerms escrow calldata. The sibling list contains arc_* market/reputation/registry tools, none of which produce swarm plans or escrow calldata, so this is clearly differentiable without opening a schema.

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?

The last sentence gives an explicit two-phase invocation protocol: call once without `payment` to get terms, sign with your own wallet, call again with `payment`. That is concrete when-and-how guidance, but no alternatives or exclusions are named (e.g. what to do if you do not want to pay, or which sibling to use for simpler goals).

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