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

With no annotations, the description carries the full burden and does substantial work: it discloses uncertainty ('It may be wrong'), states that unavailable evidence is named rather than inferred, names the human as final authority, and explicitly disclaims lightning detection while clarifying that wind, model precipitation and thunderstorm indications are included. This is exactly the kind of beyond-schema disclosure that matters. It stops short of stating latency, cost, or whether the call is purely read-only, which keeps it off 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.

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

The purpose is front-loaded, but the middle sentence is a run-on that chains a scope exclusion with return contents ('the outcome includes wind and model precipitation and thunderstorm indications and is not lightning detection'), which is harder to parse than it needs to be. The caveat sentence is dense but earns its place; the return-contents list could be tightened.

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?

For a 5-parameter, 100%-covered schema with no output schema, the description compensates by describing the shape of the result (thresholds, exceeded conditions, divergence, unknowns, uncertainty) and by flagging the time constraint's implication of current-only assessment. The one remaining gap is the absence of any routing signal relative to get_forecast_trust, which overlaps with the 'historical forecast reliability' claim.

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 coverage is 100%, so lat/lng ranges, the ISO 8601 time pattern, the current-conditions-only constraint, and the domain/field alias agreement rule are all already documented. The description adds only that the assessment is 'at a coordinate' for 'an activity', which is marginal. Baseline 3 applies when the schema does the heavy lifting.

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 names the resource (an activity at a coordinate) and enumerates what the response contains (thresholds, exceeded conditions, source divergence, unknowns, uncertainty), so an agent can tell it produces an operability assessment rather than a raw forecast. It also draws a scope boundary against the drone rain/thunderstorm model. However, the framing verb 'decision support' is abstract rather than a concrete action, and no sibling tool (notably get_forecast_trust, which sounds closely related) is named for contrast.

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?

There is no statement of when to call this versus get_forecast_trust, list_domains, or sense_location, and no prerequisites beyond the 'current conditions only' note that lives in the schema, not the description. The only routing information given is a negative scope boundary about a separate drone/thunderstorm model, which is not a sibling tool. The agent must infer that this is the general-purpose assessment endpoint.

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