Jornalo — futures trading journal

Find trades open on a day

find_trades

Read-only

Find the trades that were open on a given calendar day — to match a screenshot, a note or a question like 'my ZN trade on 27 March' to a real trade id. date (YYYY-MM-DD) is read in the user's configured timezone (override with timezone, an IANA name); a trade matches when its [entry, exit] window touches that day, so multi-day swings match every day they were open; toleranceDays (0-3) widens the window — report the date difference to the user when you rely on it. symbol matches the instrument family, micro ≡ mini (GC finds MGC, 6B finds M6B, NQ finds MNQ). Optional accountId (comma-separated, from list_accounts) and side. Results include local entry/exit times, the existing images and the mirrored copies in other accounts. If two trades of the same family match the same day, ask the user or read the chart's time axis — never pick one silently.

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": {
      "date": "<date>"
    },
    "name": "find_trades"
  }
}

Input Schema

Name	Required	Description
`date`	Yes	Calendar day, YYYY-MM-DD, in the user's timezone.
`side`	No
`symbol`	No	Instrument root, e.g. ZN, NQ, 6B. Micros match their mini.
`timezone`	No	IANA timezone overriding the user's setting, e.g. Europe/Madrid.
`accountId`	No	Account id(s) from list_accounts, comma-separated. Omit for all accounts.
`toleranceDays`	No	Widen the window by N days on both sides. Default 0.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 18, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the rest — and it does: timezone resolution and override behavior, the [entry, exit] window match semantics including multi-day swing duplication, toleranceDays widening with the obligation to report the resulting date difference, micro≡mini family equivalence, and the tie-break rule. This is unusually rich behavioral disclosure.

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?

A single dense paragraph, front-loaded with purpose before mechanics, with no repeated or filler sentences. It runs long due to the many genuine behavioral rules it must convey, so packing is justified even if it is not maximally scannable.

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?

With no output schema, the description compensates by describing what results contain (local entry/exit times, existing images and mirrored copies in other accounts). Combined with the matching semantics and tie-break guidance, an agent has everything needed to call and interpret this correctly.

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 already 83%, but the description adds real meaning beyond it: toleranceDays is described as widening the window and requiring a user-visible date-difference report, symbol equivalence (GC finds MGC, 6B finds M6B, NQ finds MNQ) clarifies matching behavior, and accountId is tied to list_accounts with comma-separated semantics.

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 clause names a specific verb and resource ('Find the trades that were open on a given calendar day') and frames the intent (matching a screenshot, note, or question to a real trade id). This is clearly distinguishable from list_trades and list_recent_trades_for_tagging by its date-scoped, identity-resolution purpose.

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?

It states the concrete triggering scenarios ('my ZN trade on 27 March', a screenshot, a note) and gives an operating rule for ambiguity ('ask the user or read the chart's time axis — never pick one silently'). It never explicitly names a sibling like list_trades as the alternative for unfiltered lookups, so it stops short of full when/when-not routing.

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

All Jornalo — futures trading journal 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.

Resources

Need Help?