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

Beyond the annotations (destructiveHint=true, idempotentHint=true), the description discloses concrete side effects: the window is deleted, it leaves status pages, and subscribers are not notified of the cancellation. This adds meaningful behavioral context the annotations alone do not provide.

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 concise sentences, each earning its place: the action and scope, the side effects, and the alternative for a different case. The most important information is front-loaded.

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 simple one-parameter tool with rich annotations and no output schema, the description fully equips an agent: what the tool does, when it applies, what side effects occur, and which sibling to use instead. Nothing essential is missing.

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 100%, and the single parameter uuid is already documented with its format ('mw_...'). The description does not add parameter-specific detail, but it does not need to because the schema fully covers the parameter semantics.

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 verb ('Cancel') and resource ('maintenance window'), and immediately narrows scope to windows that have not started. It also distinguishes itself from complete_maintenance_window by describing the delete-and-leave-status-pages effect.

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 says when to use it ('a maintenance window that has not started') and when not to, pointing to the sibling tool complete_maintenance_window for an in-progress window. It also warns that subscribers already notified will not be told about the cancellation, setting expectations clearly.

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