mt5-mcp

Overview Schema Source Related Servers Discussions Admin

probe_history

Survey how far back daily, weekly, or monthly bars reach for a symbol or every symbol, and save the series with a coverage index for planning history downloads.

Instructions

Probe how far back daily, weekly, or monthly bars already go, and save that series by default.

Omit symbol to survey every symbol, or pass a group mask. Daily bars are stored as data//rates/D1/.csv with a survey.json index. The tool result is the summary, not the bars. This does not measure M1. history_coverage reads the earliest M1 bar already on disk. extend_history with kind=m1 downloads older months until one comes back empty.

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": "probe_history"
  }
}

Input Schema

Name	Required	Default
`save`	No
`group`	No
`limit`	No
`symbol`	No
`timeframe`	No	D1

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 6, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false and openWorldHint=true, and the description backs that up by disclosing the on-disk write path (data/<terminal>/rates/D1/<SYMBOL>.csv plus a survey.json index) and that saving is the default. It further clarifies the return surface is a summary, not the bars themselves. Missing only operational traits such as how long a full-universe survey takes or whether existing files are overwritten.

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?

Front-loads the core action and default-save behavior, then layers storage detail and exclusions. The file-path sentence is dense but genuinely informative; no filler sentences, though the path notation could be trimmed for readability.

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?

No output schema exists, so the description compensates by stating the result is the summary rather than the bars, and it covers the disk artifacts created. Combined with the sibling disambiguation, an agent has enough to invoke this correctly; only limit semantics are absent.

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 0%, so the description must carry the load; it explains symbol (omit = survey all), group (group mask), timeframe (daily/weekly/monthly), and implies save=true is the default behavior. The limit parameter is never mentioned, leaving one of five parameters with no semantics anywhere.

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: probe how far back daily/weekly/monthly bars already go, and note that the series is saved by default. It explicitly scopes out M1 coverage and names the siblings (history_coverage, extend_history) that handle that case, so an agent can separate this from adjacent tools without reading 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?

Gives concrete routing rules: omit symbol to survey every symbol, or pass a group mask. It also draws explicit boundaries against history_coverage (earliest M1 bar on disk) and extend_history with kind=m1 (downloads older months until a month comes back empty), which is exactly the when-to-use-this-vs-alternatives guidance.

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