Skip to main content
Glama

Donki Notifications

donki_notifications
Read-onlyIdempotent

"What is the current space weather forecast?", the alerts, watches, warnings and weekly summary reports NASA DONKI issues to spacecraft operators. This is the narrative layer over the event catalogues: a human forecaster's text saying what happened, what is expected and what the impact is. Filter by message type (alert, watch, warning, summary) or by event class (CME, flare, geomagnetic storm, SEP, radiation belt enhancement).

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "type": "all",
      "limit": 3,
      "end_date": "2026-09-17",
      "start_date": "2026-09-10",
      "include_body": false
    },
    "name": "donki_notifications"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoMessage class: "all" (default), "FLR" (flare), "SEP", "CME", "IPS" (interplanetary shock), "MPC" (magnetopause crossing), "GST" (geomagnetic storm), "RBE" (radiation belt enhancement), "report" (weekly summary).
limitNoMax messages to return (default 20, max 100).
_apiKeyNoNASA API key (optional, defaults to DEMO_KEY)
end_dateNoEnd date YYYY-MM-DD (optional; defaults to today).
start_dateNoStart date YYYY-MM-DD (optional; DONKI defaults to ~30 days ago).
include_bodyNoInclude the full message text (default true). Set false for a compact index, these bodies are long.
message_typeNoFilter the returned rows by the DONKI messageType field: "Alert", "Watch", "Warning" or "Report". Applied after fetching.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / include_body / description
      Previous value: -"Include the full message text (default true). Set false for a compact index — these bodies are long."New value: +"Include the full message text (default true). Set false for a compact index, these bodies are long."
  2. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/open-world, so the safety profile is covered. The description adds real value by characterizing the payload semantics — forecaster text saying what happened, what is expected, and what the impact is — which matters given there is no output schema. It omits operational caveats such as the DEMO_KEY rate limits or the default ~30-day window, keeping it short of 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?

Three sentences, front-loaded with the user-phrased purpose, then the layer explanation, then the filtering options. The quoted question and the 'what happened, what is expected and what the impact is' clause are slightly expansive but they carry real semantic content rather than filler.

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 7-optional-parameter read tool with no output schema, the definition supplies purpose, content character and both filter axes, which is enough to call it correctly. The remaining gap is return-shape detail — the agent must infer that rows are message objects with long bodies — though the schema's include_body field partly compensates.

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%, so baseline is 3, but the description earns an extra point by disambiguating the confusingly similar 'type' (event class) versus 'message_type' (alert/watch/warning/summary) split conceptually rather than merely restating the fields. It gives representative values (CME, flare, geomagnetic storm, SEP, radiation belt enhancement) that help the agent reason about filter choice.

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?

Concrete verb-plus-resource framing: it returns NASA DONKI alerts, watches, warnings and weekly summaries, described as 'the narrative layer over the event catalogues.' That explicitly separates it from the per-phenomenon siblings (donki_cme, donki_geomagnetic_storms, donki_solar_energetic_particles) without the agent needing to open 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 Guidelines4/5

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

The 'narrative layer over the event catalogues' framing and the quoted user question ('What is the current space weather forecast?') give a clear use context: reach for this when the agent wants human forecaster commentary rather than raw event parameters. It stops short of naming a specific catalogue sibling as the alternative when structured data is wanted, so it lacks an explicit exclusion.

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.