aivy-mcp

Official

Overview Schema Source Related Servers Discussions Admin

get_curve

Retrieve power and state-of-charge history for a site across 1-day, 7-day, or 30-day ranges. Use it to inspect PV, load, battery, grid, and SOC time series before summarising.

Instructions

Power and SOC history. range 1d = 5-minute points for one local day (day = YYYY-MM-DD, default today); 7d / 30d = daily values. Returns times (UTC), local_times, and series per channel (pv, load, battery, grid, soc). Large: summarise before quoting.

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": {
      "site_id": "<site_id>"
    },
    "name": "get_curve"
  }
}

Input Schema

Name	Required	Default
`day`	No
`range`	No	1d
`site_id`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.9.0Nov 6, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With no annotations at all, the description carries the full burden and does a decent job: it discloses return shape (UTC times, local_times, per-channel series), granularity differences by range, the default day, and a practical warning that responses are large and should be summarised rather than quoted. It omits auth/permission requirements and any size or pagination limits, which keeps it from a 5.

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?

Dense and front-loaded: the resource is stated first, then range semantics, then the return shape, then the size warning. The mid-sentence line break inside the range explanation slightly hurts scannability but no sentence is wasted.

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?

For a three-parameter read tool with an output schema present, the description covers what the schema cannot: resolution-by-range, date format, timezone handling, and output volume. The remaining gaps (permissions, maximum window, channel availability per site) are minor given the output schema documents the response.

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 description coverage is 0%, so the description must supply meaning, and it does for the two non-obvious parameters: range values 1d/7d/30d with their differing resolution, and day as YYYY-MM-DD defaulting to today. site_id is left unexplained, but its meaning is unambiguous alongside list_sites.

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?

"Power and SOC history" names the resource (power/SOC time series) and implicitly the operation (retrieve history), and the mention of channels (pv, load, battery, grid, soc) makes clear it is not the same as get_status or get_energy_mode. It does not explicitly contrast itself with siblings, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied through the range semantics: 1d gives 5-minute points for a single local day, 7d/30d give daily values. That tells an agent how to pick a range, but there is no explicit "use this instead of get_status / get_prices" guidance and no stated prerequisites (e.g. site must be connected).

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