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

Annotations already communicate that this is a mutating, destructive operation (readOnlyHint=false, destructiveHint=true), so the description's job is to add context. It does: 'The pages show the change; subscribers are not notified' discloses a real behavioral consequence not derivable from annotations or schema. This is exactly the kind of side-effect information that helps an agent set expectations correctly. It stops short of describing effects on existing scheduled windows or whether changes are immediately visible vs. staged.

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?

Two sentences with zero filler. The first sentence front-loads the verb and enumerates all operation categories compactly; the second adds the single most decision-relevant side effect. Every clause earns its place.

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 an 11-parameter destructive mutation with no output schema, the description reasonably covers the full action space and one key side effect. However, it omits partial-update semantics (only uuid is required, so calling with just uuid presumably touches nothing), validation relationships (e.g., end_date after start_date), and any notion of idempotency. The openWorldHint=true annotation signals unknown extra behaviors that the description does not attempt to bound. Adequate, but with clear gaps for such a complex tool.

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 every parameter already has rich documentation with formats and examples (e.g., ISO 8601 dates, 'mw_...' UUID format, per-language behavior). The description adds a light action-to-parameter mapping ('rename it' → name/title, 'post a public update' → message/language, 'change monitors or status pages' → add/remove arrays), but the schema carries the heavy lifting. Baseline 3 is appropriate.

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 concrete action verbs ('Reschedule', 'rename', 'change', 'post') applied to a specific resource (maintenance window) and enumerates exactly what can be modified: schedule, name, monitors, status pages, and public updates. This clearly differentiates it from siblings like create_maintenance_window, cancel_maintenance_window, and complete_maintenance_window by naming the operations only update performs.

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 action list ('reschedule', 'rename', 'change monitors or status pages', 'post a public update') gives clear context for what the tool is for, but it never explicitly states when NOT to use it or names alternatives. An agent must infer that early termination is handled by cancel_maintenance_window or that a brand-new window belongs to create_maintenance_window. Usage guidance is implied rather than stated.

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