Nyria

Send trade alert

nyria_send_alert

Destructive

Send a trade alert to your Nyria strategy. The alert is parsed and forwarded to every bot on the strategy. If the strategy has live bots, this places real orders in your broker account, exactly like the webhook; the alert also reaches accounts that copy the strategy. Preview first when unsure. Alerts cannot set position size on entries (the bot controls sizing); an exit may close a share of the position with "percent", above 0 to 100. Stop orders are attached only when a JSON alert carries them (see the message field). The reply lists an order_id per order leg; pass it to nyria_order_status to see each bot's fill.

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": {
      "message": "<message>"
    },
    "name": "nyria_send_alert"
  }
}

Input Schema

Name	Required	Description	Default
`message`	Yes	The alert message, e.g. 'BUY AAPL' or 'SELL TO CLOSE SPY 450C 12/20'. A JSON alert may add order keys: order_type (market, limit, stop, stop_limit, trailing_stop), stop_price, limit_price, trail_percent or trail_amount, stop_loss and take_profit (a price, or a share of the entry price like "2%"; for stocks, ETFs and options only, never crypto; Tradier needs a limit or stop entry), stop_loss_limit, percent (exits: close this share of the position, above 0 to 100, for stocks, ETFs and crypto, not options; the rest stays open until a later exit or FLATTEN, and the close cancels the trade's working stop and target), bots (a list of bot ids to route to; the first 8 characters are enough). Action FLATTEN cancels working orders, then closes every open position the strategy's bots hold. A broker that cannot place a requested order type refuses the alert; it is never sent as a market order.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 3, 2026

changedInput schema / properties / message / description

Previous value: -"The alert message, e.g. 'BUY AAPL' or 'SELL TO CLOSE SPY 450C 12/20'. A JSON alert may add order keys: order_type (market, limit, stop, stop_limit, trailing_stop), stop_price, limit_price, trail_percent or trail_amount, stop_loss and take_profit (a price, or a share of the entry price like \"2%\"; for stocks, ETFs and options only, never crypto), stop_loss_limit, percent (exits: close this share of the position, above 0 to 100, for stocks, ETFs and crypto, not options; the rest stays open until a later exit or FLATTEN, and the close cancels the trade's working stop and target), bots (a list of bot names or ids to route to). Action FLATTEN cancels working orders, then closes every open position the strategy's bots hold. A broker that cannot place a requested order type refuses the alert; it is never sent as a market order."New value: +"The alert message, e.g. 'BUY AAPL' or 'SELL TO CLOSE SPY 450C 12/20'. A JSON alert may add order keys: order_type (market, limit, stop, stop_limit, trailing_stop), stop_price, limit_price, trail_percent or trail_amount, stop_loss and take_profit (a price, or a share of the entry price like \"2%\"; for stocks, ETFs and options only, never crypto; Tradier needs a limit or stop entry), stop_loss_limit, percent (exits: close this share of the position, above 0 to 100, for stocks, ETFs and crypto, not options; the rest stays open until a later exit or FLATTEN, and the close cancels the trade's working stop and target), bots (a list of bot ids to route to; the first 8 characters are enough). Action FLATTEN cancels working orders, then closes every open position the strategy's bots hold. A broker that cannot place a requested order type refuses the alert; it is never sent as a market order."

Changed1 schema field changedNov 3, 2026

changedInput schema / properties / message / description

Previous value: -"The alert message, e.g. 'BUY AAPL' or 'SELL TO CLOSE SPY 450C 12/20'"New value: +"The alert message, e.g. 'BUY AAPL' or 'SELL TO CLOSE SPY 450C 12/20'. A JSON alert may add order keys: order_type (market, limit, stop, stop_limit, trailing_stop), stop_price, limit_price, trail_percent or trail_amount, stop_loss and take_profit (a price, or a share of the entry price like \"2%\"; for stocks, ETFs and options only, never crypto), stop_loss_limit, percent (exits: close this share of the position, above 0 to 100, for stocks, ETFs and crypto, not options; the rest stays open until a later exit or FLATTEN, and the close cancels the trade's working stop and target), bots (a list of bot names or ids to route to). Action FLATTEN cancels working orders, then closes every open position the strategy's bots hold. A broker that cannot place a requested order type refuses the alert; it is never sent as a market order."

First observedNov 3, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare destructive=true, openWorld=true and idempotent=false, so the safety profile is largely covered. The description still earns its keep by disclosing that live bots place real broker orders identically to the webhook, that copying accounts are reached, and that brokers refuse unsupported order types rather than downgrading to market. Slightly incomplete on permissions or rate limits for a live-money mutation.

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?

Front-loaded with the core action and the real-money warning before any caveats, and every sentence is substantive. Some of the middle material (percent range, stop order attachment) duplicates the message field description, adding mild redundancy.

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 destructive, real-money, single-parameter tool with no output schema, the description covers the risk posture, what the reply contains (order_id per leg), and the follow-up call needed to see fills (nyria_order_status). An agent has enough to invoke it correctly and interpret the response.

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 description coverage is 100% and the single message parameter is exhaustively documented, so the baseline would be 3–4 anyway. The description adds a genuine constraint absent from the schema — that alerts cannot set position size on entries because the bot controls sizing — which changes how an agent composes the message. The percent and stop-order explanation largely restates schema content.

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?

Opens with a specific verb and resource ("Send a trade alert to your Nyria strategy") and immediately clarifies downstream effect: parsed and forwarded to every bot on the strategy. It is distinguishable from nyria_preview_alert, which is named explicitly as the dry-run alternative.

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?

Provides a concrete decision rule — "Preview first when unsure" — which routes the agent to the sibling tool with a clear condition. Also scopes what this tool cannot do (no position sizing on entries) and when percent-based exits apply, though it never states when this tool should be avoided outright.

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

All Nyria tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.