senti-mcp-server

Break an account down by day, symbol and hour

get_performance_breakdowns

Read-only

Break down an MT5 account's P&L by day, symbol, and hour over a date window to identify losing symbols and weak trading hours.

Instructions

Break one MT5 account down three ways over a date window: a day-by-day P&L, volume and notional series; a per-symbol P&L and deal-count series; and P&L by hour of the day. Use it for "which symbol is losing me money" or "what hour do I trade worst". For a single whole-account figure — net P&L, win rate, ROI, the live terminal — use get_account_performance instead: it is smaller and it is the default for a performance question. THIS RESPONSE IS SHAPED. The endpoint returns a chart-sized payload, so per-account rows and running totals are dropped, at most ten symbols are kept, and the hourly grid is totalled across the window. Whatever that cost is listed in notes, which is empty when nothing was cut — read it before concluding that a symbol was not traded. accountId is the id field from list_accounts — NOT login. Omit from/to for the last 30 days; a narrower window is also how you see a symbol that was cut. reporting is an ISO-4217 currency code (default USD), not a reporting period.

Input Schema

TableJSON Schema

Name	Required	Description
`to`	No	Window end, inclusive (UTC, YYYY-MM-DD).
`from`	No	Window start (UTC, YYYY-MM-DD).
`accountId`	Yes	The `id` field from list_accounts. Not the `login` (MT5 account number).
`reporting`	No	ISO-4217 currency the money figures are normalized to. Defaults to USD.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`daily`	Yes
`notes`	Yes
`hourly`	Yes
`perSymbol`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv2.9.0Sep 16, 2026
- removedOutput schema / properties / perSymbol / properties / dailyDealsRows / items / additionalProperties / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "number"
-  }
-]
```
- addedOutput schema / properties / perSymbol / properties / dailyDealsRows / items / additionalProperties / type
```
Added value: +[
+  "string",
+  "number"
+]
```
- removedOutput schema / properties / perSymbol / properties / dailyPnlRows / items / additionalProperties / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "number"
-  }
-]
```
- addedOutput schema / properties / perSymbol / properties / dailyPnlRows / items / additionalProperties / type
```
Added value: +[
+  "string",
+  "number"
+]
```
Addedv1.3.0Aug 11, 2026

TDQS

A4.8/5.0

Behavior5/5

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

The description discloses response shaping that annotations don't cover: per-account rows and running totals are dropped, at most ten symbols are kept, the hourly grid is totalled, and cuts are reported in `notes`. It also warns to read `notes` before concluding a symbol was untraded and notes that narrowing the window reveals cut symbols. This adds substantial behavioral context beyond readOnlyHint=true and openWorldHint=true, and does not contradict them.

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 dense but front-loaded: purpose first, then usage guidance, then behavioral caveats, then parameter disambiguation. A few phrases like 'THIS RESPONSE IS SHAPED.' are slightly opaque and the accountId warning repeats the schema, but no sentence is pure filler.

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 an output schema present and readOnly/openWorld annotations, the description covers all operational essentials: what data is returned, how it may be truncated, how to detect cuts, default time window, and the accountId-vs-login trap. An agent has everything needed to invoke the tool 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 100%, so the baseline is 3, but the description adds non-redundant meaning: omitting `from`/`to` defaults to the last 30 days, `reporting` is disambiguated from a reporting period, and accountId is re-emphasized as list_accounts.id, not login. Some duplication exists with schema descriptions, but the default-window behavior is genuinely new.

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 states a precise action: breaking one MT5 account into three series (day-by-day P&L/volume/notional, per-symbol P&L/deal-count, and P&L by hour) over a date window. It also names the sibling get_account_performance and explicitly says what this tool is not (a single whole-account figure), making it easy to distinguish without opening schemas.

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?

It gives concrete example questions ('which symbol is losing me money', 'what hour do I trade worst') for when to use it, and directs the agent to get_account_performance for single whole-account figures, calling it 'the default for a performance question.' This is explicit when/when-not guidance with a named alternative.

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

Deploy Server