Skip to main content
Glama
Koniverse

senti-mcp-server

by Koniverse

Get an account performance summary

get_account_performance
Read-only

Summarize a single MT5 account's performance over a date window: net P&L, win rate, profit factor, ROI, IRR, and live terminal state. Use for any performance question.

Instructions

Summarize how one MT5 account has performed over a date window: net P&L, win rate, profit factor, gross profit and loss, deal counts, costs, cash flow, period ROI and IRR, lifetime IRR, and the live terminal state. This is the default tool for any performance question — the response is a fixed-size summary that does not grow with the window. accountId is the id field from list_accounts — NOT login. Omit from/to for the last 30 days. reporting is an ISO-4217 currency code (default USD), not a reporting period. A null live block means the terminal was unreachable, not that the account is empty.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoWindow end, inclusive (UTC, YYYY-MM-DD).
fromNoWindow start (UTC, YYYY-MM-DD).
accountIdYesThe `id` field from list_accounts. Not the `login` (MT5 account number).
reportingNoISO-4217 currency the money figures are normalized to. Defaults to USD.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
liveYes
notesYes
metricsYes
lifetimeIrrYes
portfolioReturnYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv2.9.0
    • removedOutput schema / properties / lifetimeIrr / properties / earliestMs / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / lifetimeIrr / properties / earliestMs / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedOutput schema / properties / lifetimeIrr / properties / irr / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / lifetimeIrr / properties / irr / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • changedOutput schema / properties / live / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "balance": {
      -        "type": "number"
      -      },
      -      "currency": {
      -        "anyOf": [
      -          {
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ]
      -      },
      -      "equity": {
      -        "type": "number"
      -      },
      -      "leverage": {
      -        "type": "number"
      -      },
      -      "margin": {
      -        "type": "number"
      -      },
      -      "marginFree": {
      -        "type": "number"
      -      },
      -      "marginLevel": {
      -        "type": "number"
      -      },
      -      "name": {
      -        "anyOf": [
      -          {
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ]
      -      },
      -      "profit": {
      -        "type": "number"
      -      }
      -    },
      -    "required": [
      -      "balance",
      -      "equity",
      -      "profit",
      -      "margin",
      -      "marginFree",
      -      "marginLevel",
      -      "leverage",
      -      "currency",
      -      "name"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "balance": {
      +        "type": "number"
      +      },
      +      "currency": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "equity": {
      +        "type": "number"
      +      },
      +      "leverage": {
      +        "type": "number"
      +      },
      +      "margin": {
      +        "type": "number"
      +      },
      +      "marginFree": {
      +        "type": "number"
      +      },
      +      "marginLevel": {
      +        "type": "number"
      +      },
      +      "name": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "profit": {
      +        "type": "number"
      +      }
      +    },
      +    "required": [
      +      "balance",
      +      "equity",
      +      "profit",
      +      "margin",
      +      "marginFree",
      +      "marginLevel",
      +      "leverage",
      +      "currency",
      +      "name"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedOutput schema / properties / portfolioReturn / properties / irr / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / portfolioReturn / properties / irr / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedOutput schema / properties / portfolioReturn / properties / roi / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / portfolioReturn / properties / roi / type
      Added value: +[
      +  "number",
      +  "null"
      +]
  2. Addedv1.2.0

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the readOnlyHint annotation, it discloses meaningful behavior: the summary is fixed-size and does not grow with the window, and a null live block means the terminal was unreachable rather than the account being empty. These are exactly the kind of non-obvious behavioral details an agent needs.

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

Conciseness5/5

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

Every sentence earns its place: the first defines the tool's output, the second establishes its default role, and the remaining sentences clarify parameter gotchas and null semantics. The most important usage guidance is front-loaded, with no 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?

Given the output schema exists, the description does not need to spell out return fields, yet it still covers defaults, parameter identity traps, and the live-block null meaning. For a read-only summary tool with one required parameter, this is fully sufficient for an agent to invoke it correctly.

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 coverage is 100%, but the description adds essential disambiguation: accountId is the id from list_accounts and not the MT5 login, reporting is a currency code rather than a reporting period, and omitting from/to defaults to the last 30 days. This goes well beyond the schema's own descriptions.

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 names a specific verb (summarize), a specific resource (one MT5 account over a date window), and enumerates the exact metrics returned (net P&L, win rate, profit factor, gross profit/loss, deal counts, etc.). It also explicitly positions itself as the default tool for performance questions, which distinguishes it from breakdown and timeseries siblings.

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?

The description clearly says this is the default tool for any performance question and explains that the response stays fixed-size regardless of window length, which guides selection. It also gives concrete invocation guidance like omitting from/to for the last 30 days, but it does not name specific sibling alternatives to use instead for specialized performance breakdowns.

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