Skip to main content
Glama

Prepare: fire the triggers that hold now

trigger_fire
Read-onlyIdempotent

For executor agents: the triggers that hold right now by the account's own check (on one account, read on chain; or across every trade account as Borro's keeper publishes them at /triggers.json each minute while the market is open, with the few simulated here checked on chain again), each with the unsigned fire transaction from the wallet, simulated from it, and the tip it pays in USDG. Anyone may fire a trigger whose condition holds and is paid its tip: a share of the closed notional at the feed, capped (tip_bps, at most 50 basis points, and never more than the USDG the close returns) (the account's own agent firing earns nothing: its tip goes to the owner). The close goes through the account at the feed's price within the trigger's slip, the rest stays in the account, and nothing else moves. A trigger whose close would fail (slip, the pool, a paused desk) reverts and stays live. Its bound starts at 50 basis points past the feed until the trigger is armed, then widens: when it is not armed yet, the arm transaction (anyone may send it) comes before the fire, and bound says whether the pool's fill fits the bound now or from when. Send a fire with a gas limit of 3,000,000. Triggers do not fire while the stock market is shut or the feed has not printed within 25 hours; a price crossed while it is shut (a weekend, a holiday) fires once the market opens again, at the price the feed prints then, within the trigger's slip, and after a gap that price can be well past the trigger's. With account and id: that one trigger, refused in words when it does not hold. When none holds: the nearest ones and how far they are. Borro's keeper fires them too, by its own rules: Borro's keeper charges all its work on a trigger (screens, checks and simulations, 1 unit each; arms and resets, 5) to the trigger's root owner until the trigger fires, when it is given back. Owners go in this order: owners with a fire on record (a fire Borro's keeper itself sent for them and was paid for, its tip at least the fire's gas, in the last 30 days; fires by the account's own owner or agent, by other executors, or with no tip never count), then the least such work today, then the oldest trade account. Each fire on record also allows its owner one reserved arm or reset. An owner past 200 units a UTC day gets no more unpaid or subsidised keeper work that day (triggers on the low-tip allowance, arms, resets); a trigger whose tip covers its gas is never held back by it. A trigger whose tip does not cover its gas is fired by Borro's keeper from its root owner's low-tip allowance alone (0.0001 ETH of gas a UTC day, at most 40 root owners a day, in that owner order); any executor may fire it sooner for its tip.

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": {
      "wallet": "<wallet>"
    },
    "name": "trigger_fire"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoWith account: one trigger's number
walletYesThe executor's address (any address; the tip goes to it)
accountNoOne trade account (optional; default every account)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses many behavioral traits: it returns unsigned simulated transactions, includes tips in USDG, specifies failure/revert behavior, market-hours gating, gas limit guidance, keeper ordering, allowances, and subsidy rules. These details materially inform an executor agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a dense, run-on block mixing invocation guidance with extensive keeper economics, allowance rules, and owner ordering. Important front-loaded information exists, but much of the text is not necessary for selecting or invoking the tool and is hard to scan.

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?

Given the absence of an output schema and the complexity of firing triggers, the description is complete: it covers return contents, simulation, tip behavior, failure modes, market closures, account/id narrowing, and keeper constraints. An executor agent has enough context to invoke it correctly.

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 100%, so the schema already documents all three parameters. The description still adds useful meaning: wallet is the executor address receiving the tip, account defaults to every account when omitted, and id selects one trigger only with account.

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?

The title and opening sentence clearly identify the tool as preparing unsigned fire transactions for triggers whose conditions currently hold, including the simulated transaction and tip. It is specific about the resource and scope, but it does not explicitly differentiate itself from siblings such as trigger_list or trigger_set.

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 description explains executor-agent usage, how account/id narrows to one trigger, and what happens when none holds. However, it does not explicitly say when to use this versus trigger_list, trigger_set, or trigger_cancel, leaving sibling selection mostly implied.

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