Gear MCP Server

Endpoint history

get_endpoint_history

Read-onlyIdempotent

Retrieves historical readings for one IoT endpoint between two UTC dates, ordered oldest first with minimum, maximum, and average values; limits results to 5,000 points and flags truncation.

Instructions

Readings of one endpoint between two dates, oldest first, with min/max/avg. Up to 5000 points; for long ranges ask for a shorter one or accept the truncated flag.

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": {
      "endpoint_id": "<endpoint_id>",
      "date_from": "<date_from>"
    },
    "name": "get_endpoint_history"
  }
}

Input Schema

Name	Required	Description
`date_to`	No	UTC date, "2026-10-01" or "2026-10-01T08:00:00Z"
`date_from`	Yes	UTC date, "2026-10-01" or "2026-10-01T08:00:00Z"
`max_points`	No	Default 1000
`endpoint_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 30, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare this as a read-only, idempotent, non-destructive open-world call. The description adds non-obvious behavior beyond that: result ordering (oldest first), aggregation (min/max/avg), and a 5000-point ceiling with a truncation flag, which is not visible in the schema since there is no output schema.

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?

Two sentences with zero padding, and the most important constraint (point cap and truncation) is placed after the core definition without burying it. Every clause carries information the caller needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly supplies the return shape (ordered readings with min/max/avg) and explains the truncation flag. Minor gaps remain: it does not clarify units/granularity of readings or whether pagination exists beyond truncation.

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 coverage is 75%, with dates documented in-schema including accepted formats; only endpoint_id lacks a schema description. The description adds the 5000-point maximum context that relates to max_points but does not explain max_points' default of 1000 or what endpoint_id refers to, so it is baseline value only.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource (readings of one endpoint), a scope (between two dates), and the shape of the result (oldest first, min/max/avg). It is clearly distinguishable from the sibling list/get tools, which cover facilities, devices, and alarms rather than historical time-series readings.

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 gives actionable guidance for the main failure mode: with a cap of 5000 points, narrow the range or accept the truncated flag. It does not describe when-not-to-use or name alternatives, but no sibling offers comparable history retrieval, so the context is adequate.

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

Deploy Server