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

With no annotations, the description carries the full burden of behavioral disclosure. It is transparent that the result is a forecast, that the crossing date is returned only 'if it does' occur within the horizon, and that a local normal is also reported. However, 'near-term' is vague, and the description does not mention horizon length, data recency, or billing/side effects, leaving some behavior to be inferred from the schema and output schema.

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 description is front-loaded with the trigger, then the returns, then the rationale; all parts contribute to understanding. It is compact, though the first line is a sentence fragment and the soil-vs-air metaphor is somewhat decorative rather than strictly operational.

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 six-parameter tool with an output schema, the description provides the core semantics and lets the output schema cover return shapes. It does not define the forecast horizon, mention required authentication or credit billing, or explicitly differentiate this from siblings like planting_window, so an agent still has some selection uncertainty.

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 documentation covers about 83% of parameters, so the baseline is 3. The description adds little parameter-level meaning beyond the schema; 'planting depth' maps to the 'band' parameter, but the schema already explains the depth ranges more precisely than the description does.

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 opens with the specific trigger ('crosses a planting threshold') and states the verb 'Returns' with a clear resource: a near-term soil-temperature forecast at planting depth, including the crossing date and the climatological normal. It also distinguishes itself from air-temperature tools by explaining that soil is the steadier signal and the real decision driver, not a single warm afternoon.

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?

The description gives clear context for when to call it: when a grower needs to know whether to plant this week and how much time remains, based on soil rather than air temperature. It stops short of 5 because it does not explicitly name sibling alternatives or state when not to use this tool.

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