Skip to main content
Glama

tickerbot_list_events

THE events primitive — one timeline over every event log, cross-ticker: dividends, splits, insider transactions, and analyst actions ("all splits this month", "every analyst action in my universe this week", "AAPL's full corporate history" via ticker), plus two opt-in kinds that join only when named: signal (boolean-flag firings) and news. Rows are { ticker, ts, kind, payload }, newest first. Analyst payloads (history to 2012) carry firm/analyst/action/rating/price_target; filter them with firm=/action= (structured, case-insensitive — a q payload match is case-SENSITIVE) — actions: upgrades, downgrades, initiates_coverage_on, maintains, reiterates, assumes, reinstates, suspends, terminates_coverage_on. Use q for other payload conditions: it speaks the SQL grammar over exactly (ticker, ts, kind, payload jsonb); group_by/select/having roll the stream up (aggregates return truncated: true instead of paginating); join=state attaches the ticker's state as of each event. Requires at least one bound: a ticker scope (ticker/tickers/universe), a time window (from/to), or firm/action — q alone is not a bound.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoSQL WHERE over (ticker, ts, kind, payload jsonb) — ONLY those four identifiers. Payload fields via jsonb operators: payload->>'firm' = 'Goldman Sachs', (payload->>'shares')::numeric > 1e6. On kind=signal this requires `signal` (the firing log is ~175M rows); kind=signal takes no group_by.
toNoWindow end: a bare YYYY-MM-DD means through the END of that day (matching bars/series/spans); a timestamp is exclusive — events strictly before it. `until` accepted as alias.
dirNoAggregate-mode sort direction.
firmNokind=analyst only. Case-insensitive analyst-firm filter (e.g. "Goldman Sachs" matches "goldman sachs") — prefer this over a q payload match, which is case-sensitive.
fromNoEvents at or after this ISO date/datetime (inclusive; a bare YYYY-MM-DD means from the start of that day). `since` accepted as alias.
joinNojoin=state attaches each event's ticker STATE as of that event's moment (the replay join) under a `state` key — "downgrades where rsi_14 was already under 40" composes with q. Free on every plan.
kindNoComma list of kinds to include. Default is the four corporate kinds: dividend, split, insider, analyst. Two more are opt-in and join only when named: `signal` (boolean-flag firings) and `news`.
limitNoPage size. Max 1000.
orderNoAggregate-mode sort column/alias. Default: events.
actionNokind=analyst only. Exact rating-action filter.
cursorNoOpaque cursor from a prior response — carries the original filters, pass it alone (long q values must be resent alongside it).
havingNoPost-aggregation filter (requires group_by), e.g. COUNT(*) > 5.
selectNoAggregate-mode output columns (requires group_by). Default: group keys + COUNT(*) AS events.
signalNokind=signal only. One built-in boolean flag (e.g. golden_cross). REQUIRED to use `q` or `join` on kind=signal — naming the signal is what keeps the query on an index; optional otherwise.
tickerNoSingle-ticker filter, e.g. AAPL.
tickersNoComma-separated tickers, max 50. Mutually exclusive with `universe`.
group_byNoComma list of rollup keys — switches to aggregate rows, e.g. payload->>'firm' AS firm, or kind. `AS` names the JSON key; an un-named payload read is keyed by its payload key (payload->>'firm' -> firm).
intervalNoGrain for join=state replay (finest covering tier by default).
universeNoUniverse slug (top_10, top_100, or a saved one) to scope the stream. Mutually exclusive with `tickers`.
transitionNokind=signal only. `enter` (false->true) or `exit` (true->false). Always optional — an ordinary filter.

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It effectively discloses row format, ordering (newest first), case-sensitivity nuances, aggregate behavior (truncated: true instead of paginating), and the join=state replay behavior. It also notes the historical depth for analyst payloads. This is substantial transparency for a complex query tool.

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 description is long but dense with essential information, front-loading the core purpose with 'THE events primitive'. Each sentence contributes: row format, filters, aggregation, join behavior, and requirements. It is structured logically but could benefit from paragraph breaks for readability; still, it avoids redundancy and earns its length for a 20-parameter tool.

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?

Given the tool's complexity (20 params, no output schema, no annotations), the description covers the most critical aspects: event kinds, row structure, filtering strategies, aggregate mode behavior, join semantics, and mandatory bounds. It does not explicitly cover pagination defaults or all parameter interactions (e.g., transition, interval), but those are documented in the input schema, making the overall package complete enough for an agent.

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%, so baseline is 3. The description adds significant value beyond the schema: it explains q's SQL grammar over (ticker, ts, kind, payload jsonb), the case-sensitivity difference between firm and q payload matches, the required-bound rule, and how group_by/select/having change the output shape. This meaningfully helps the agent use parameters correctly.

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 clearly states the tool's function: listing events across all event logs, with explicit examples ('all splits this month', 'AAPL's full corporate history'). It distinguishes itself from siblings like tickerbot_list_signal_events and tickerbot_get_ticker_history by framing itself as 'THE events primitive' and covering multiple event kinds.

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 strong usage context: it states the tool is for cross-ticker event queries, explains opt-in kinds (signal, news), and gives explicit constraints ('Requires at least one bound... q alone is not a bound'). It also differentiates between firm/action filters and q payload matches. However, it does not explicitly mention when to use alternative tools like list_signal_events or get_ticker_history.

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.

TDQS

A3.9/5.0
Disambiguation4/5

Most tools target distinct resource-action pairs, but get_ticker and get_ticker_history overlap (both return a single historical row via asof), and the four subscribe_* tools are thin wrappers around create_webhook, creating some ambiguity. Detailed descriptions mitigate but don't eliminate confusion.

Naming Consistency4/5

The tickerbot_ prefix and verb_noun pattern are consistent (create_*, get_*, list_*, delete_*, update_*), but subscribe_* deviates from create_* for webhooks, and scan/search_news are bare verbs. Overall predictable.

Tool Count2/5

35 tools is excessive for the domain; many could be consolidated (e.g., four subscribe_* variants into a single parameterized webhook creator, get_ticker/get_ticker_history into one). The breadth of data types justifies some volume, but this exceeds the 25-tool threshold for coherence.

Completeness5/5

Full lifecycle coverage for universes, custom signals, and webhooks; extensive read-side for tickers, series, bars, events, news, and scans. No critical dead ends: anything creatable can be updated/deleted/tested, and data lookups have appropriate query tools.