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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description still adds real consequence information beyond the annotations: 'Canceling also cancels its upcoming pickups', plus the auth requirement. It stops short of saying whether a cancel can be undone or whether the operation is atomic across the listed fields.

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?

One sentence front-loads the primary state changes before the attribute edits, and the parenthetical '(until a date, or until resumed)' disambiguates pause modes efficiently. The trailing auth sentence is short and earns its place. Minor density in the middle clause list, but no filler.

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 destructive, 7-parameter mutation with no output schema, the description covers the side effect of cancel and the login prerequisite, which are the two things most likely to cause a bad call. What remains missing is whether cancel is reversible and whether multiple fields can be combined in one call, keeping it below the top score rather than inadequate.

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 57%, and the description restates the fields that the schema already documents well (pausedUntil date, bag count, job notes, detergent and scent). cancelReason has no schema description and is not covered by the description either, leaving a gap. The null-resets-to-Laundry-preferences behavior is valuable but is already present in the schema.

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 concrete operations on a specific resource: pause, resume, cancel, and edits to bag count, Job notes, detergent and scent. An agent knows exactly what capability is behind the name. It does not differentiate against the sibling change_subscription, which plausibly overlaps with the 'change its bag count / detergent / scent' half, so a 5 is not warranted.

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 enumerates what can be done but never states when to choose this tool over change_subscription or when-not to use it. Usage is only implied by the operation list. The one piece of genuine guidance is the prerequisite 'Needs the customer's Happy Hamper login', which tells the agent a credential context is required.

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