Skip to main content
Glama

NEM Explorer (ScadaMiner)

search_entities

Read-onlyIdempotent

Search the warehouse for entities that match a single term. Returns ranked candidates with similarity scores; the agent decides which (if any) the user meant. Entity types: duid (5-letter+ codes like ARWF1), station (station-level results that group all DUIDs at that station), region (canonical IDs NSW1/VIC1/QLD1/SA1/TAS1/SNOWY1), interconnector (Basslink, Heywood, QNI, VNI, Murraylink, Directlink, Project EnergyConnect), and fuel_type (Coal/Gas/Hydro/Wind/Solar/Battery/Biomass/Diesel). DUID matches also carry region, fuel_type, registered_capacity_mw and schedule_type (SCHEDULED/SEMI-SCHEDULED/NON-SCHEDULED), plus a note when the schedule type limits which tables hold rows for the unit: read it before querying bids, dispatch targets or constraints. Pick search terms from the user's question yourself. Call once per term — do not pass the whole question. Similarity is 0..1; treat scores below 0.7 with scepticism (the query term is probably a generic English word, not an entity reference).

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": {
      "query": "<query>"
    },
    "name": "search_entities"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of candidates to return, ranked by similarity. Defaults to 10 and is clamped to 1..=50. Increase when the term is ambiguous and you want to see more options.
queryYesA single term to search for. Pick this from the user's question yourself: a station name ("Hornsdale"), a DUID code or prefix ("ARWF1", "HBESS"), a region alias ("victoria"), an interconnector alias ("basslink"), or a fuel type ("wind"). Do not pass the whole question — call this tool once per term you want to look up.
typesNoOptional filter to specific entity types. Valid values: "duid", "station", "region", "interconnector", "fuel_type". Omit to search across all types.
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. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the read-only, idempotent and non-destructive annotations, the description discloses ranking behavior, similarity-score semantics and threshold, DUID metadata fields returned, and that a `note` must be read before querying bids, dispatch targets or constraints. This is materially useful behavioral context not present in the annotations.

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?

The description is front-loaded with purpose and return behavior, then moves through entity types, metadata caveats, invocation rules and score threshold. Every sentence adds actionable information, and the dense enumeration is justified by the domain.

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 adequately explains the return format, including ranked candidates, similarity scores, DUID metadata and the meaning of `note`. It also covers the main failure mode, low-confidence generic terms, so an agent has enough information to call and interpret the tool 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?

Schema description coverage is 100%, so the baseline is 3, but the description adds domain examples for entity types such as canonical region IDs and interconnector names. It reinforces the single-term query semantics, though the `limit` and `question_id` parameters are left to the schema.

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?

The description gives a specific verb and resource ('Search the warehouse for entities') and immediately clarifies the return shape: ranked candidates with similarity scores. The enumerated entity types make clear that this is not a column search or concept lookup, so an agent can distinguish it from siblings such as search_columns.

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 provides clear usage rules: pick search terms yourself, call once per term, never pass the whole question, and treat similarity scores below 0.7 sceptically. It lacks explicit naming of alternative tools, but the entity-type scope and single-term guidance give sufficient context for correct invocation.

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.