Skip to main content
Glama

NEM Explorer (ScadaMiner)

list_tables

Read-onlyIdempotent

List every available NEM data table from semantic.table_selector_index. By default returns the whole catalogue (one row per table) with a one-line curated summary per table, plus domain, time_column, and data-availability bounds (data_available_from / data_available_to). grain is omitted from the default view (the summary already encodes it) — pass detailed=true for it. A single call gives you the full warehouse map — no pagination, no truncation. Optional domain filter (bids, billing, constraints, demand, dispatch, fcas, forecasting, fpp, interconnectors, metering, mtpasa, network, operations, predispatch, pricing, registration, settlements, stpasa, trading) or keywords (case-insensitive substring across name/summary/description/tags) narrows the set when you already know what you want. Pass detailed=true to also include the full description, grain, key_columns, join_keys, related_tables, question_tags, and caveats. For full column metadata and curated caveats on one table, prefer get_table_schema.

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": "list_tables"
  }
}

Input Schema

NameRequiredDescriptionDefault
domainNoFilter to a single domain. Valid values: "bids", "billing", "constraints", "demand", "dispatch", "fcas", "forecasting", "fpp", "interconnectors", "metering", "mtpasa", "network", "notices", "planning", "predispatch", "pricing", "registration", "settlements", "stpasa", "topology", "trading".
detailedNoWhen true, include rich metadata (description, caveats, key_columns, related_tables). Defaults to false so the response stays small enough to fit in the model context. Combine with `domain` or `keywords` to avoid blowing past the row cap.
keywordsNoCase-insensitive substring keywords. A table matches when every keyword appears somewhere in its object_name, description, or question_tags. Use this to find tables for a specific topic without dumping the full index.
question_idNoOptional UUID returned by an earlier `start_question` call. When provided, this tool call is attributed to that question.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / domain / description
      Previous value: -"Filter to a single domain. Valid values: \"bids\", \"billing\",\n\"constraints\", \"demand\", \"dispatch\", \"fcas\", \"forecasting\", \"fpp\",\n\"interconnectors\", \"metering\", \"mtpasa\", \"network\", \"notices\",\n\"predispatch\", \"pricing\", \"registration\", \"settlements\", \"stpasa\",\n\"topology\", \"trading\"."New value: +"Filter to a single domain. Valid values: \"bids\", \"billing\",\n\"constraints\", \"demand\", \"dispatch\", \"fcas\", \"forecasting\", \"fpp\",\n\"interconnectors\", \"metering\", \"mtpasa\", \"network\", \"notices\",\n\"planning\", \"predispatch\", \"pricing\", \"registration\", \"settlements\",\n\"stpasa\", \"topology\", \"trading\"."
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Adds real context beyond the readOnly/idempotent/openWorld annotations: one row per table, curated summary per row, availability bounds returned, grain withheld by default, and a stated rationale ("the response stays small enough to fit in the model context"). However, "no pagination, no truncation" sits in tension with the schema's own warning about a row cap on detailed responses, so the size guarantee is not fully trustworthy.

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 behavior and the routing hint before the option detail, and every sentence carries operational information. The long parenthetical domain enumeration largely duplicates the schema's enum and adds bulk without adding meaning.

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?

With no output schema, the description carries the full return-value burden and does so: row granularity, which fields appear by default, which fields require detailed=true. Filtering behavior, defaults, and the alternative tool are all covered, so an agent has everything needed to call it correctly.

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?

Goes beyond the schema by explaining the default value of detailed and what each flag buys you in the response. But the inline domain list diverges from the schema's valid values — it names "operations" (absent from the schema) and omits notices, planning, and topology — and the keywords description says matching spans name/summary/description/tags while the schema says object_name/description/question_tags, so an agent could pass an invalid domain or mis-model keyword behavior.

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 ("List every available NEM data table from semantic.table_selector_index") and immediately distinguishes itself from the sibling that goes deeper ("For full column metadata and curated caveats on one table, prefer get_table_schema"). An agent can pick between list_tables and get_table_schema without opening either schema.

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?

Explicitly frames the default call as the full warehouse map, then gives the two narrowing conditions ("when you already know what you want" for domain/keywords) and the escalation path to get_table_schema for per-table depth. Both when-to-use and when-to-use-something-else are stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.