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

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, and the description goes well beyond them: ~25 km grid snapping, the GFS baseline and modulator set, the meaning of the capped_gun flag, and the 'marked, isolated' vs severe interpretation rule. That is exactly the interpretive context annotations cannot supply.

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?

Front-loaded with purpose, then scoring mechanics, then the critical basin-scale warning. Every sentence carries information, though the CAPE/lifted-index/lapse-rate detail is denser than selection alone requires — defensible since there is no output schema to explain the score.

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 no output schema, the description does the work of explaining what comes back (a 0-10 hourly score plus a capped_gun flag) and how to phrase it. The remaining hole is parameter documentation, which leaves an otherwise complete definition slightly short.

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?

Schema description coverage is 0%, so the description must carry the parameter burden. It implies a point (latitude/longitude) and an hourly score that hints at a time dimension, but never documents the days parameter, its default of 3, the coordinate format, or the returned time resolution. The gap is real.

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?

States a specific output (thunderstorm environment at a point, scored 0-10 per hour) and a specific basis (convective ingredients, not a rain field). This cleanly separates it from get_forecast and get_zone_alerts, which an agent could otherwise confuse with it.

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?

Explicitly bounds the tool: it describes an environment at basin scale, does NOT locate individual cells, and routes the agent to list_models_for_location for convection-resolving coverage. It also gives phrasing rules for downstream output. It stops short of stating when to prefer this over get_forecast or get_zone_alerts for the same point.

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