Fortunest demo

Upcoming events

events

Read-onlyIdempotent

DEMO portfolio (synthetic, shared, read-only). Read the portfolio's forward calendar as a dated list instead of the whole context: earnings dates, ex-dividend and dividend-pay days for the holdings the Events card tracks, central-bank rate decisions and scheduled data releases for the portfolio's jurisdictions, and the tax-free lot maturities from the Taxes digest. kinds filters to any of: earnings, dividends, macro, maturities (default all). days is the window ahead (1-365, default 30, today counts as upcoming); symbols filters to those tickers; limit (1-50, default 20) and offset page the list, which is sorted by date and, on a shared date, by position size. byKind counts the whole window BEFORE the kinds filter, so one call shows what else is coming. servedFrom says where the answer came from: 'context' is the assistant's cached list (the nearest 20 events within 45 days), 'engine' means the events calendar itself was asked for the full window. THE EARNINGS CALENDAR: ask with kinds=['earnings'] alone and the answer is one row PER SYMBOL instead of one per date (bySymbol true) — symbol, name, scope, weightPct, nextEarnings (its next reporting day inside the window), lastReport {date, epsActual, epsEstimate, surprisePct, verdict} and filingUrl/filingSearchUrl when a filing is known, sorted soonest first with companies that have no date in the window last. scope picks whose: holdings (default), watchlist (the user's favourites, up to 20) or both. past is days BACK for recent reports (0-180, default 0). scope and past apply to that per-symbol answer only. This is the multi-symbol view market_lookup can only give one symbol at a time. Dates only — never a forecast of what will be reported, and never advice.

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": "events"
  }
}

Input Schema

Name	Required	Description	Default
`days`	No
`past`	No
`kinds`	No
`limit`	No
`scope`	No
`offset`	No
`symbols`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so safety is covered; the description goes well beyond by disclosing that kinds=['earnings'] alone silently switches the response shape to one row per symbol with bySymbol true, that byKind counts the window BEFORE the kinds filter, that sorting is by date then position size, and what servedFrom ('context' vs 'engine') means. It also states limits explicitly ('Dates only — never a forecast... never advice'), which is meaningful behavioral context for an agent summarizing results.

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

Conciseness3/5

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

It is front-loaded — the first sentence states purpose and scope — but the body is a dense wall of text with mid-sentence rules crammed in (byKind ordering, servedFrom values, the entire bolded 'THE EARNINGS CALENDAR' mode switch). Nearly every sentence carries information, yet the lack of paragraphing or bullets for what are effectively two distinct response modes makes it harder to parse than it needs to be.

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 7-parameter, dual-mode tool with no output schema, the description covers everything an agent needs: filtering, paging, sort order, the mode switch, the return fields of the per-symbol earnings row (symbol, name, scope, weightPct, nextEarnings, lastReport fields, filing URLs), and the provenance signal. No structural field is left undocumented.

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 0%, so the description must carry all parameter meaning and it does: days (1-365, default 30, today counts as upcoming), kinds (the four enum values, default all), symbols (ticker filter), limit (1-50, default 20), offset (paging), scope (holdings/watchlist with the up-to-20 note/both), and past (0-180 days back, default 0). It adds semantics the schema cannot express, notably that today counts as upcoming and that scope/past are inert unless the per-symbol earnings shape is triggered.

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 and resource immediately ('Read the portfolio's forward calendar as a dated list') and enumerates exactly which event types appear: earnings dates, ex-dividend/dividend-pay days, central-bank decisions, scheduled data releases, and tax-free lot maturities. It also carves out a named alternative ('the multi-symbol view market_lookup can only give one symbol at a time'), so an agent can distinguish it from a per-symbol lookup 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?

Gives clear use context ('instead of the whole context') and an explicit routing rule against market_lookup for multi-symbol earnings. It also warns that scope and past apply only to the per-symbol earnings answer, which prevents misuse. It stops short of stating when-not to use it (e.g., relative to holdings or tax_lots for point-in-time data), so it is clear but not fully exclusionary.

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

All Fortunest demo 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.