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

Annotations already declare this a safe, read-only, closed-world read, so the description does not need to restate safety. It instead adds genuinely non-obvious data semantics: rows are emitted only on change, so a wait value carries forward until the next row, which changes how an agent must interpret results.

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 short sentences, front-loaded with the usage trigger, then the prerequisite, then the result-shape caveat. Every sentence adds information and none repeats the schema or annotations.

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 two-parameter read tool with no output schema, the description covers the trigger, the prerequisite, and the shape of returned data well enough to call it correctly. It stops short of describing what fields a row contains (timestamp, wait, status), which matters slightly more given no output schema exists.

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 both ride_id and days are already documented including the 1-7 bound and default. The description reinforces the ride ID resolution step but never mentions the days parameter or how the 'last week' framing relates to its configurable window.

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 concrete verb and resource: how a ride's posted wait moved over the last week, which is clearly a historical series rather than a snapshot. It implicitly contrasts with the current-wait tools but never names a sibling such as parky_get_waits or parky_get_ride_reliability, so differentiation is left partially to inference.

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 a clear trigger condition (a visitor asks how a wait moved over the last week) plus a prerequisite step (resolve the ride ID first). There is no explicit when-not guidance or named alternative for adjacent questions like best time to visit or reliability.

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