lpagent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_gridsA | List the built-in benchmark grids and whether their load types are known. Custom pandapower grids (.json/.xlsx files) can also be loaded with load_grid. |
| load_gridB | Load a grid: summary of loads, total power, voltage levels and whether load types are known. |
| get_grid_loadsB | Page through the load table (index, name, bus, p_mw, q_mvar, detected type). |
| list_bdew_profilesA | List BDEW profiles, categories with default profiles, registered custom profiles and the mix syntax. |
| register_profileA | Register a user-supplied profile: CSV with 1 day, 7 days (Mon-Sun) or a full year of values, any units (rescaled to 1,000 kWh/a). Use its name in category_profiles / load_profiles. |
| get_default_settingsC | Default settings with explanations. |
| get_bdew_curveC | One BDEW profile for a year (W per 1,000 kWh/a): CSV, plot and statistics. |
| assign_load_typesB | Assign a category (residential, commercial, industrial, agricultural, residential_pv, residential_pv_battery, mixed) and profile to every load. Precedence: mapping > grid metadata > distribution > default_category. Returns assignment_id and a per-category summary. |
| generate_profilesB | Generate P/Q time series per load and year; saves CSVs and a manifest (settings, assumptions, checksums); returns per-year and ensemble statistics. |
| plot_runC | Plot a run (PNG): year, week, day, load-duration curve or daily means. |
| get_runC | A run's results, methods text, a manifest section, or checksum verification. |
| list_runsA | List the runs of this session (newest first). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Each tool has a clearly distinct purpose: listing/loading grids, inspecting loads, managing BDEW profiles, assigning load types, generating/plotting/retrieving runs. The few closely related tools (list_grids vs load_grid, load_grid vs get_grid_loads) are differentiated by their descriptions (summary vs detailed table vs listing). No two tools appear to do the same thing.
All 12 tools use snake_case with a consistent verb_noun pattern (list_*, load_*, get_*, register_*, assign_*, generate_*, plot_*). The verbs are appropriate and predictable, making the set easy to navigate.
12 tools is well within the ideal 3–15 range for a specialized load-profile agent. Each tool covers a distinct step in the workflow, and there is no obvious redundancy or missing core operation that would inflate the count.
The surface covers the end-to-end workflow: list/load grids, inspect loads, manage BDEW profiles, assign types, generate profiles, and retrieve/plot runs. Minor gaps exist—no update/delete for registered profiles and no per-load assignment retrieval—but these are not likely to block typical agent tasks.