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

Annotations already declare destructiveHint=true and non-idempotent, so the bar is lower, and the description still adds real context: the side effect of emailing subscribers, the fact that probes pause and the status page flips to "Under maintenance". It explains why the destructive flag matters, though it doesn't say what happens on failure or whether the window can be undone.

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?

Front-loads the purpose, then layers constraint, required pairing, and the notify gate. Five sentences all carry information, with only mild redundancy between "set it true only when the user asked to email subscribers" and the closing "can email subscribers" warning.

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 8-parameter mutation tool with no output schema and no annotations beyond hints, the description covers the operationally risky parts (side effects, duration bounds, required check/component pairing). What it lacks — weekdays semantics, time/zone formats, and any mention of what the call returns — is a modest gap.

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 0%, so the description has to carry the load. It documents duration_seconds (60 through 7 days), endpoint_ids as "the check", status_components as its public component, and the notify_subscribers default — but name, timezone, starts_at, and especially the non-obvious weekdays recurrence field are left unexplained.

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?

Opens with a specific verb+resource ("Schedule a maintenance window"), which cleanly separates it from update_maintenance_window, cancel_maintenance_window, and list_maintenance_windows. It doesn't explicitly name a sibling, so it stops short of a 5.

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?

Gives a concrete precondition ("run only when the user asked to schedule this window") and a conditional default rule for notify_subscribers ("set it true only when the user asked to email subscribers"). No named alternative tool or exclusion is given, but the gating conditions are explicit enough to route the agent.

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