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

Annotations only supply destructiveHint=true, so the description must carry the rest, and it does: it discloses the actual effect (alert silencing), the non-obvious time handling (RFC3339 values read as local time in `timezone`), and an account-level feature gate. It stops short of covering repeat semantics or whether the window can later be edited/removed, but it adds substantially beyond the single annotation.

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-loaded with the action and effect, then constraints, then the API mapping. Four short clauses, no filler, and the most decision-relevant facts (silencing behavior, timezone interpretation, tests-or-tags requirement) come first.

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 7-parameter mutation with no output schema, the description covers the effect, prerequisites, timing semantics, and target scoping. Minor gaps remain: it does not indicate what is returned (e.g. an id for later get/update), nor whether repeat_interval has a default or whether omitted optional fields behave in any surprising way.

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 a 3 would be the baseline, but the description goes further: it clarifies that start_at/end_at only use the date and time component and are interpreted in `timezone`, and it supplies a cross-parameter requirement (tests and/or tags) that the schema does not express at all — neither field is in the required list.

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 and resource ('Schedule a maintenance window') plus its functional effect ('silences alerts for the given uptime checks'). An agent can immediately distinguish this from the sibling read tools (get_maintenance_window, list_maintenance_windows) and the other create_* check tools.

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 selection constraint ('At least one of tests or tags is required') and a hard precondition ('Only works on accounts using the newer maintenance-windows feature'), which tells the agent when this call will fail. It does not explicitly name an alternative tool, but for a create operation among mostly read siblings the routing need is low.

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