Skip to main content
Glama

Manawa Terminal

Create alert

create_alert

Create a price alert, an event alert, a clock, or a trailing alert.

Calling this stores the alert. A clock may omit the ticker.

Args:
    symbol: Stock symbol (e.g. "AAPL"). Required for price and event alerts. Optional for a clock.
    alert_type: "target_price", "movement_pct", "event", "schedule", or "trailing"
    direction: For price alerts: "above", "below", or "either". For trailing: "long" or "short".
        Long trails the high since arming; short trails the low. Fires when price gives
        back trail_pct percent or trail_amount from that extreme.
    threshold: Required for price alerts — price level or percentage move. Not used for trailing.
    notes: Optional description. Not the agent instruction.
    event_types: Required when alert_type is "event". Live-tape ids such as
        filing_13f, politician_senate, options_unusual, ipo_upcoming.
    event_filters: Optional slices. Example: {"politician_senate": {"type": ["purchase"]}}.
        An omitted field matches every value.
    name: Optional title. Blank is filled from the rule.
    agent_instruction: What the agent does when this fires. Empty means notify only.
    max_fires: How many fires before it leaves Active. Omit to keep a repeating alert firing.
    schedule_at: ISO time. Required when alert_type is "schedule".
    schedule_tz: IANA zone. UTC when omitted.
    schedule_repeat: once, daily, weekdays, weekly, or monthly. Default once.
    skill_id: Strategy id this alert belongs to. Required when rule_ref is set.
    rule_ref: The section tag of the strategy rule this alert serves; the agent
        reads that section when the alert fires (STRATEGY_ALERTS=1).
    off_hours: "defer" (wake at next session open) or "now" (act while closed).
        Used when ALERT_OFF_HOURS=1 and the alert has an agent instruction.
    trail_pct: Trailing give-back percent (0 < x <= 50). Exactly one of trail_pct or trail_amount.
    trail_amount: Trailing give-back absolute amount (> 0). Exactly one of trail_pct or trail_amount.
    activate_at: Optional price that must be reached before trailing starts.

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": "create_alert"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
notesNo
symbolNo
rule_refNo
skill_idNo
directionNo
max_firesNo
off_hoursNo
thresholdNo
trail_pctNo
alert_typeNo
activate_atNo
event_typesNo
schedule_atNo
schedule_tzNo
strategy_idNoStrategy this call belongs to. UUID from list_strategies. The card this call writes keeps that id. Omit when the call is not part of a strategy.
trail_amountNo
event_filtersNo
schedule_repeatNo
agent_instructionNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / activate_at
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "number"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Activate At"
      +}
    • addedInput schema / properties / off_hours
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Off Hours"
      +}
    • addedInput schema / properties / rule_ref
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Rule Ref"
      +}
    • addedInput schema / properties / skill_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Skill Id"
      +}
    • addedInput schema / properties / trail_amount
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "number"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Trail Amount"
      +}
    • addedInput schema / properties / trail_pct
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "number"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Trail Pct"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / strategy_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Strategy this call belongs to. UUID from list_strategies. The card this call writes keeps that id. Omit when the call is not part of a strategy.",
      +  "title": "Strategy Id"
      +}
  3. Changed12 schema fields changed
    • addedInput schema / properties / agent_instruction
      Added value: +{
      +  "default": "",
      +  "title": "Agent Instruction",
      +  "type": "string"
      +}
    • addedInput schema / properties / alert_type / default
      Added value: +""
    • addedInput schema / properties / event_filters
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": true,
      +      "type": "object"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Event Filters"
      +}
    • addedInput schema / properties / max_fires
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Max Fires"
      +}
    • addedInput schema / properties / name
      Added value: +{
      +  "default": "",
      +  "title": "Name",
      +  "type": "string"
      +}
    • addedInput schema / properties / schedule_at
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Schedule At"
      +}
    • addedInput schema / properties / schedule_repeat
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Schedule Repeat"
      +}
    • addedInput schema / properties / schedule_tz
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Schedule Tz"
      +}
    • addedInput schema / properties / symbol / anyOf
      Added value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedInput schema / properties / symbol / default
      Added value: +null
    • removedInput schema / properties / symbol / type
      Removed value: -"string"
    • removedInput schema / required
      Removed value: -[
      -  "symbol",
      -  "alert_type"
      -]
  4. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnly=false, destructive=false, openWorld=false), the description discloses persistence ('Calling this stores the alert'), lifecycle semantics (max_fires before it leaves Active), firing-time agent behavior (agent_instruction, rule_ref section read when STRATEGY_ALERTS=1), and off-hours gating tied to ALERT_OFF_HOURS=1. Those are behavioral facts an agent cannot infer from the annotation set.

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 one-line purpose, then a clean per-parameter Args list where each entry adds new information rather than restating the schema. It is long, but with 20 parameters that length is mostly earned; a little tightening (e.g. the separate 'Calling this stores the alert' line) would make it a 5.

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 20-parameter mutation with an output schema that already covers return values, the description reaches nearly everything an agent needs: type-specific required fields, mutual exclusion, defaults, and timezone handling. Gaps are minor — it never states that alert_type must always be supplied, and it says nothing about validation failure behavior or duplicate alerts.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 5% and there are zero enums in the schema, so the description carries the burden — and it does: it supplies the alert_type, direction, and schedule_repeat value sets, the above/below/either vs long/short distinction, the trailing give-back mechanics, the 0 < x <= 50 bound, and the exactly-one-of trail_pct/trail_amount constraint. Only strategy_id is left to the schema, which already documents it.

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 opening sentence names a specific verb (create) plus the four alert flavors it can produce — price, event, clock, trailing — and the Args block enumerates the five allowed alert_type values. That is enough to separate it from list_alerts and delete_alert in the sibling set 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?

Guidance is conditional and explicit: which alert types require symbol, threshold, event_types, schedule_at, and exactly-one-of trail_pct/trail_amount. It does not name an alternative tool or an explicit 'do not use this for X' case, so it stops short of a 5.

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