Skip to main content
Glama
PHUICMT

mcp-mt5

by PHUICMT
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

smoke_test

Destructive

Detect runtime failures in Expert Advisors by compiling, deploying, and running a 1-day backtest, then scanning the journal for errors.

Instructions

One-call health check for an EA: compile, deploy, run a 1-day headless backtest, scan the journal.

Catches problems that compile cleanly but fail at runtime (OnInit errors, array out of range, divide by zero). ok is true only if every stage passes; stage tells where it stopped. Overwrites the EA of the same name in Experts/. Takes 1-10 minutes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
daysNoLength of the backtest window in days (ends 2 days ago).
periodNoTimeframe code such as M15, H1, D1.M15
sourceYesAbsolute Windows path to the .mq4/.mq5/.mqh source file.
symbolNoSymbol name as shown in Market Watch, e.g. EURUSD.EURUSD
expert_nameNoName to use in Expert= of the generated ini; defaults to the binary's stem.
timeout_secNoGive up after this many seconds.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.5.0
    • addedInput schema / properties / days / description
      Added value: +"Length of the backtest window in days (ends 2 days ago)."
    • addedInput schema / properties / expert_name / description
      Added value: +"Name to use in Expert= of the generated ini; defaults to the binary's stem."
    • addedInput schema / properties / period / description
      Added value: +"Timeframe code such as M15, H1, D1."
    • addedInput schema / properties / source / description
      Added value: +"Absolute Windows path to the .mq4/.mq5/.mqh source file."
    • addedInput schema / properties / symbol / description
      Added value: +"Symbol name as shown in Market Watch, e.g. EURUSD."
    • addedInput schema / properties / timeout_sec / description
      Added value: +"Give up after this many seconds."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "title": "smoke_testDictOutput",
+  "type": "object"
+}
  2. First observedv0.4.1

TDQS

A4.5/5.0
Behavior5/5

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

The description discloses important behavioral traits beyond the annotations: it overwrites an existing EA of the same name in Experts/, takes 1-10 minutes, and reports both `ok` and `stage` so the caller knows where execution stopped. This complements the destructiveHint=true annotation with concrete details and does not contradict it.

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?

Three sentences carry substantial value: the first captures the core action and stages, the second explains the failure modes it detects and the result semantics, and the third discloses side effects and duration. There is no filler or repetition of schema fields.

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 rich input schema, an output schema, and annotations that mark the tool destructive, the description adds the missing context: the overwrite side effect, expected runtime, and the stage/ok behavior. Nothing an agent needs to invoke or interpret this tool correctly is left unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter already carries a meaningful description. The tool description adds only high-level context like '1-day headless backtest,' which aligns with the `days` default but does not materially extend per-parameter semantics. Baseline 3 is appropriate.

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 specific verb and resource ('One-call health check for an EA') and enumerates the four stages it performs: compile, deploy, run a 1-day headless backtest, and scan the journal. This clearly distinguishes it from sibling tools like compile or run_backtest, which perform only individual stages.

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 gives clear context for when to use the tool: it catches problems that compile cleanly but fail at runtime, such as OnInit errors, array out of range, and divide by zero. It does not explicitly name alternatives or state when not to use it, but the 'one-call' framing implies it replaces the multi-step sequence without needing further exclusions.

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

Deploy Server

Other Tools