Skip to main content
Glama

Fleet network access (binding constraints)

get_network_access
Read-onlyIdempotent

How often binding network (transmission) constraints limited each NEM battery's access to the energy market over a date window, split by direction. Per unit: pct_discharge_limited, pct_charge_limited, pct_top_price_discharge_limited (share of the top-10% regional price intervals that were discharge-limited), pct_neg_price_charge_limited (share of negative-price intervals that were charge-limited), commissioning_days and top_constraint (AEMO constraint ID, direction, description). Also the constraints behind the most fleet exposure. This is EXPOSURE, not lost revenue: a binding constraint caps what a unit could do, not what it wanted to do, and AEMO often resolves it by moving other units — never present these as lost dollars or lost dispatch. Commissioning units (commissioning_days > 0) dispatch on test schedules; leave them out of comparisons. Check commercial_context: TOLLED/CONTRACTED units dispatch for an offtaker. Minimum window is 30 days (shorter is widened); data from July 2024; constraint data lags about two days (days_covered vs days_requested). Large response (every unit); for one battery use get_battery_network_access.

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": {
      "date_from": "<date_from>",
      "date_to": "<date_to>"
    },
    "name": "get_network_access"
  }
}

Input Schema

NameRequiredDescriptionDefault
date_toYesEnd date YYYY-MM-DD.
date_fromYesStart date YYYY-MM-DD. Ranges under 30 days are widened to the last 30 days ending date_to.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), but the description adds traits annotations cannot express: 30-day minimum window with widening, data starting July 2024, ~2-day constraint lag surfaced via days_covered vs days_requested, and large response size covering every unit. It also pre-empts a serious misinterpretation (never present as lost dollars or lost dispatch).

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-loaded with purpose, then metric definitions, then caveats — a sensible order for a dense statistical tool. It is long and slightly repetitive in the exposure/lost-revenue warning ('not what it wanted to do... never present these as lost dollars or lost dispatch'), but the metric glossary earns its space given there is no output schema.

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 takes on the burden of explaining return values and does so field by field, including the top_constraint structure and the fleet-level constraint exposure. Coverage, latency, window floor, unit exclusions, and interpretation caveats are all present, which is complete for a read-only fleet aggregate.

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 coverage is 100% and the schema already documents YYYY-MM-DD formats and the 30-day widening rule, so the description's repeated widening note adds little. It does add meaning beyond the schema by tying date windows to the two-day data lag and days_covered/days_requested, which affects how the agent should read the range it requested.

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?

Opens with a specific resource and metric: 'how often binding network (transmission) constraints limited each NEM battery's access to the energy market... split by direction.' It names the exact per-unit outputs and explicitly contrasts itself with the sibling get_battery_network_access for single-battery queries, so an agent can distinguish it without reading a 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?

Gives explicit routing ('for one battery use get_battery_network_access') plus exclusions: leave commissioning units out of comparisons, check commercial_context for TOLLED/CONTRACTED units. It also frames the intended interpretation ('EXPOSURE, not lost revenue'), which tells the agent what question this tool answers versus a revenue tool like get_battery_revenue.

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.

Resources