Skip to main content
Glama

What happened since I last looked

get_my_new_events

What happened on the account while you were away: fills, rejections, approvals, positions closed (stop, take-profit, plan, liquidation), plan rules fired, price alerts, warnings near liquidation or the daily loss limit. Reading moves your place on, so a new session gets only what is new: act on each event before the next read; to read again, pass an earlier last_event_id as after (your place stays put). Use at the start of a session, or with wait_seconds (up to 30) to wait for the next event. Not for current state (use get_my_positions). Next: act on what changed, e.g. get_my_positions.

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": "get_my_new_events"
  }
}

Input Schema

NameRequiredDescriptionDefault
afterNoAn event id (last_event_id of an earlier answer) to read after it and keep your own place; leave out to continue from where you last checked
limitNoAt most this many events, 1-100
typesNoOnly these event types, e.g. ["plan.triggered", "position.closed"]
wait_secondsNoWhen nothing is new, wait up to this long (0-30) for the next event

Output Schema

NameRequiredDescriptionDefault
moreYesTrue when more events are waiting: call again at once
sinceYeslast_check (where this agent last stopped), after, or first_look (the last 24 hours)
eventsYesEvents in the order they happened
deprecationNoPresent only while this tool is deprecated: replacement, removal_date, changelog
last_event_idNoPass as after to keep your own place; null when nothing new was read

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations show readOnlyHint=false and idempotentHint=false, which could confuse an agent for a 'get' tool; the description resolves this by disclosing that reading advances the cursor and that passing an earlier last_event_id keeps the place put. That is exactly the context annotations cannot carry. Remaining gap: it does not discuss ordering guarantees or what happens if a read is interrupted mid-cursor-advance.

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 purpose, then cursor semantics, then usage and next step — a sensible order. It is dense and somewhat run-on, packing event types, cursor rules and alternatives into roughly three sentences, but nearly every clause carries information.

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?

The tool has an output schema, so return values need no explanation; the description instead covers the non-obvious parts: what event categories appear, how the cursor is consumed, how to replay from a saved id, and how to long-poll. Nothing an agent needs in order to call it correctly is missing.

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 baseline is 3, but the description adds real semantics: the default behavior of a read is to consume events, while `after` pins your own position. It also motivates wait_seconds as a wait-for-next-event mechanism rather than just restating its 0–30 range. `types` and `limit` are not elaborated beyond the schema.

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?

States a specific verb+resource: an event feed of what happened on the account since the last read, and enumerates the event categories (fills, rejections, positions closed, plan rules fired, alerts, warnings). It also explicitly excludes current-state reads by naming get_my_positions as the alternative, so an agent can separate it from siblings 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use (start of a session, or with wait_seconds to long-poll for the next event), explicit when-not (not for current state — use get_my_positions), and a follow-up action ('act on what changed'). The guidance is actionable and names the alternative tool.

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