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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful context that the output is human-readable narrative text covering events, expectations, and impacts, but it does not disclose behaviors like post-fetch filtering or default date ranges.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with no filler: the first captures the user need, the second defines the tool's role, and the third lists filtering dimensions. It earns its length and is front-loaded with the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With complete schema coverage and safe-operation annotations, the description covers the main missing piece — what the output looks like (forecaster text about events, expectations, and impacts). It is slightly less complete on explicit routing to sibling event-catalogue tools, but that is inferred from the 'narrative layer' framing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 100% coverage of all 7 parameters, so the description does not need to duplicate parameter details. It does add a high-level explanation of filtering by message type and event class, though it uses informal labels like 'summary' rather than the schema's exact 'report' and does not map terms to specific parameter names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb-plus-resource purpose: it returns DONKI alerts, watches, warnings and weekly summary reports — the narrative forecast layer. It explicitly contrasts itself with 'event catalogues,' which distinguishes it from sibling catalogue tools like donki_cme, donki_geomagnetic_storms, and donki_solar_energetic_particles.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

It gives clear context by framing the tool as the answer to 'What is the current space weather forecast?' and describing it as a human forecaster's narrative over event catalogues. This implies when to use it versus the raw event data siblings, though it never names an alternative or states a when-not-to-use condition.

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